Why study HCP reactions to new data releases at conferences?

Whether you are a newcomer to a disease state, an established force in the market, or even an interested outsider, it is not enough to just know the treatment landscape as it is. You have to know what is coming up in the field and to be in the midst of the innovation that drives every therapeutic area forward. Of course, manufacturers participate in this innovation most directly through clinical trials. However, as treatments continue to be developed and researched, understanding how new data is being socialized among professionals can provide valuable insights into the future of the market landscape.


Fortunately, we can capture the socialization of and reaction to new data at the many professional conferences that occur every year for all manner of disease states. By assessing providers’ thoughts on new data, we can better understand how it could impact their practices and decision-making.

At most medical conferences, new data about treatments naturally take center stage, and inVibe’s 

 studies often use these abstracts as stimuli. However, it would be reductive to say that we are truly studying the abstracts themselves. Our job is to gauge reactions to these abstracts from the HCPs who might (or might not) eventually act on that information. In our experience, the best way to elicit those reactions is to simply get these HCPs talking, which inVibe’s voice response methodology is built to do.


As a result, we have a very straightforward process for developing a new data intelligence study to fit the client’s needs. First, we collaborate with the manufacturer to see what abstracts they most want to gauge reactions to, whether their own treatments or potential competitors. Then, we design our study around those abstracts in order to get at the heart of whatever strategic question we are trying to answer.

Despite the straightforward process we use to build our new data intelligence studies, our methodology can be quite flexible to whatever will best serve the sponsor’s strategic needs. Abstract reactions are always a component of this research, but new data intelligence is also a golden opportunity to trace broader trends and attitudes driving current and future treatment decisions. With inVibe’s framework, we can balance our core goals of following reactions to new data and understanding the treatment landscape this new data is affecting. In addition, our flexibility means that we can emphasize one or the other goal in order to best serve your needs.


For our abstract-based new data intelligence research, we conduct the study immediately after the conference and allow HCPs to review the abstracts before and during their response.  Our team designs the questions to allow HCPs to react to the abstract on its own terms and then put it in the context of their own practice.


This process allows us to gain a deeper understanding of when there are disconnects between positive study outcomes and a lack of any predicted impact, due to factors beyond the results themselves. Let’s think about oncology for an example. Perhaps a new treatment or endpoint being used is not accessible for all practice settings, or perhaps HCPs are already satisfied with a treatment regimen they currently prescribe and are uninterested in alternatives until it shows there is a mature, definitive advantage. We can uncover these less obvious issues simply by listening to these HCPs, and understanding both what they’re telling us and how they say it.

While we are more than capable of partnering with clients on treatment landscape work at any point in a treatment’s trajectory, perhaps one of the most compelling times to do this work is right when that landscape is shifting - when new data about treatments are released and discussed among professionals. At conferences, HCPs think about the future of their practice and interrogate their own strategies. While they are in this mindset, they can share some incredible insight with us outside of the context of abstract reactions.

We can ask HCPs about their current treatment strategy for a patient in a specific subpopulation, and their answer will always be useful in some way to you. However, when we ask this question as a part of conference intelligence, we can capture this answer while it is changing, which can sometimes provide a clearer strategic picture than if we were simply asking about the treatment itself. This is how we find pain points and insufficiencies in current practices, and we can hear how eager HCPs are for solutions that would resolve those problems. It’s not only a fascinating listen, but also an extremely valuable insight.


How do these studies work in a remote world?

One major advantage of inVibe’s study methodology is that it works regardless of whether the conference is held in person, remotely, or some hybrid of the two. HCPs attending a conference remotely can simply use the same tools they used to access the conference to participate in our studies. There is no need to stack travel pressures on top of existing stress for traveling attendees; all they have to do is call and share their thoughts. We can field, analyze and report quickly enough that the insights are still topical, significant, and valuable for any conference in any therapeutic area.

It is an exciting, if kinetic, time to be involved in the development of new treatments. Keeping up with the flow of information can be intimidating.

inVibe is uniquely poised to find the most important and actionable elements of new data, condense that information into a digestible format, and offer strategic partnership to stay on top of the shifting landscape. Whether you have questions about how prescribers react to new data or what priorities are driving their current strategies, we can work with you to answer them.

How inVibe finds the most important and actionable elements of new data

New Data Intelligence: An ear to the future

“Making data collection more efficient, analysis more effective, and insights more actionable.” Such core tenets of inVibe sound pithy and exciting, but perhaps also opaque. How does inVibe truly actualize these aspirations?

The short answer is: We rely on a harmonious blend of skilled humans and cutting-edge technology throughout the project lifecycle, but especially in the analysis phase. On the human side, we have our expert linguists critically investigating the data, forming initial hypotheses, and gleaning deep nuances across responses. Technologically speaking, our bespoke software solutions facilitate and augment our linguists’ discoveries. Together, we’re able to dig deeper into three main areas: what is said, how it’s said, and how it sounds.

Understanding on the most basic level what information our participants conveyed to us is the first step in the analysis journey. After our fielding closes and all responses are in, our linguists set aside dedicated time to simply listen to the data, discover trends and notice anything particularly intriguing or surprising. We also account for any budding hypotheses that we’re interested in exploring further. This initial pass-through of the data and concurrent notetaking ensures we have a sense of each question’s big picture and a rough idea of what key aspects we may want to investigate further in subsequent listens.

With this vague roadmap in hand, we begin to further investigate the responses, breaking them up into meaningful categories in a process known as “tagging.” While we could categorize the data with existing tools like Microsoft Word and Excel, that can be inefficient and inflexible. Luckily for us, the inVibe product team has built a custom online dashboard that allows tagging responses in a clear, quick, and user-friendly way. Once we tag all the data, we can easily sort through tags to see what themes are most prevalent across participants, which allows us to focus our analysis and reporting accordingly. Here you can see tagging in action.

After listening to and tagging all responses for content, we want to dive into the nuances of the language participants use in their answers. This is because as linguists, we know that so much of what we mean is implicit, existing beneath the surface of the literal message. To more deeply understand how we should interpret responses, we “read between the lines.” On a broad level, our linguists analyze how participants 

 their responses. What information do they bring up first? What ideas do they repeat? What are those “noisy silences,” or things left unsaid? Narrowing in, we listen for the 

of language participants employ to express their thoughts. Do they vocalize doubt through hedging – words like “guess” or “unsure”? Are they enthusiastic in their responses, indicating positivity through words like “excited” or “great”? Do they use intensifiers (e.g. “so,” “very,” “extremely”) to emphasize certain points? Taken together, participants’ answer structures and specific language add color and validity to 

 is said, illuminating what is top of mind to participants and how they actually feel. 

Alongside our linguists’ expertise in the realm of “how it’s said” comes 

our AI-powered sentiment analysis algorithm

, which our product team co-built alongside Edge Analytics. Sentiment analysis is a natural language processing (NLP) technique performed on textual data that determines whether data is positive, negative, or neutral. Our algorithm is particularly adept at “subject-aware” sentiment analysis, meaning it specifically considers whether the language used in relation to the subject of the phrase is positive or negative rather than the response on the whole. Such a tool reinforces and supplements our team’s human-powered analysis by scrutinizing language sentiment in context, contributing to a more accurate interpretation of responses.

The final piece of the analysis puzzle is to zoom out above the level of what content is conveyed and what words and structure are used to convey it to understand how it’s conveyed acoustically. In other words, how do “contextualization cues” — features like pitch, tone, and pauses — clue us in to how we should perceive these responses? 

 covers this topic much more in-depth, but simply put, this is once again a partnership between humans and tech. First, our sociolinguists are especially trained to deeply listen for and note these nuances, which validate and enhance our existing analysis. Our intuitions are expanded upon by our established, rigorously tested speech emotion recognition (SER) algorithm, which tracks these contextualization cues present in each response and “translates” them into approximate emotions by scoring valence (positivity), activation (interest), and dominance (confidence). Our tools enable us to plot these emotions on a graph for each prompt, with one dot corresponding to one respondent. Such technology allows us to “see what we hear,” painting an even clearer, more definitive picture of language data for our clients.

This graph represents multiple HCP respondents in terms of their dominance "confidence" (x-axis) and activation "interest" (y-axis) for one prompt. Most responses are falling to the right side of the x-axis, indicating respondents’ more confident and assured as opposed to wavering and unacceptable

At inVibe, we embrace a partnership between human and technological expertise to simultaneously simplify and strengthen the analysis process. We see the value in building unique analysis tools for our researchers because that enables us to deliver more pragmatic insights for our life science clients. If you’re interested in learning more about the inVibe approach, reach out to 

How the inVibe Listening Platform makes data collection more efficient, analysis more effective, and insights more actionable

Imagine: A tech-enhanced, human-led analytical approach 

If you’re familiar with market research, chances are you have a good idea of what an excellent response 

 like. The participant is emotionally engaged and clearly demonstrates their feelings through the speed, volume, and tone of their voice. They talk at length about relevant topics and supply information that directly serves your research goals, addressing every aspect of each question in depth. In short, not only do their answers dazzle—so too does their delivery.

Responses like these can easily stand alone as persuasive testimonials for a wide range of stakeholders. But at inVibe, we don’t just capture what people say—we also help clients strategically harness the power of their words. The better the data we get, the more actionable the insights we can produce. This is why we’ve established rigorous data quality control (QC) procedures that ensure that the responses we collect meet our high standards. Years of honing our process based on research and experience has enabled us to develop a robust, multi-tiered screening system to maximize data quality for analysis.

Our data QC process begins long before we’ve even collected anything, during our study design phase.

Over the past decade, inVibe has presented participants with over 9,000 voice prompts, each of which has been engineered to elicit the richest possible responses. In addition to drawing on our linguistic and behavioral expertise to inform design, we also maintain a comprehensive prompt library where we catalogue and score each prompt based on relevant parameters (such as topic, research goal, and quality of responses elicited). This allows us to repurpose previously successful prompts from similar projects and customize them as needed when designing new studies.

The next portion of our QC process takes place during data collection. We typically over-recruit participants by about 10% and only close the field after we’ve evaluated the quality of the responses we’ve received. This leaves us room to screen out those that don’t satisfy our high standards while still comfortably meeting our quotas. What’s more, our automated technology allows us to collect additional responses speedily and efficiently, while other qualitative methods require a significant investment of time and resources for each interview.

After we have sent out our study, our QC process culminates with our team of trained data validators. Two or more validators may evaluate each response to ensure consistent data quality within and across projects. The end result is a dataset that comprises only on-target, detail-rich responses that our analysts can draw the most useful insights from. Before we begin our analysis, though, we listen to each and every recording in order to assess the quality of the answers and of the audio.

Our validators begin by assessing answer quality. We score responses to each question on a scale from 1-5, with 5 being “excellent,” 3 “acceptable,” and 1 “poor.” These comprehensive scores take into account the following criteria:

1. COMPLETENESS: Does the participant answer the main question? Do they answer each of the follow-up questions?

2. RELEVANCE: Does the participant provide relevant information? Do they talk about what we want them to talk about?

3. RICHNESS: What level of detail does the participant delve into? How nuanced is their response?

4. EMOTIONALITY: To what extent does the participant demonstrate emotion? How personal is their response?

High-scoring responses demonstrate high compliance, relevance, richness, and emotionality, while those that score low exhibit poor quality or lack of usability. Instead of accepting low-scoring responses, we send participants invitations to re-record that contain broad instructions on how to improve the quality of their answers (e.g., “Please provide more detail on the decision-making process you discussed in Question 2.”).

When all responses have been scored for a participant, the average score across responses makes up their “overall rating.” This rating serves as a benchmark for final screening decisions, when validators use it to sort participants into one of 3 buckets: “good,” “border,” and “poor.” Good responses enter the final data set, while poor responses are filtered out. Border responses, which meet our baseline of acceptability but do not exceed it, are filed away as a backup. Our team only includes them in the final data set if we are unable to fill our quota entirely with “goods” after undertaking every possible effort to do so.

We perform audio quality checks to make sure that our analysts can clearly hear all of the voice data. (After all, this is the cornerstone of what we do!) We want to make sure that the audio has high fidelity so that our Speech Emotion Recognition software will produce accurate analyses. Too much background noise can throw off its careful acoustic measurements.

There are several criteria that each response must meet to pass audio screening:

No distortion or other audio interference

Responses that do not meet the above criteria are marked accordingly and withheld from our final data set. However, rather than throwing them away, we give participants the chance to re-record. If they choose to do so, their responses once again undergo the same QC procedures. 

Having successfully passed through every check in our QC process, the final set of responses are published to our platform. Using our interactive project dashboards, clients and analysts are able to engage with the high-quality data that results from our rigorous data validation process.

At inVibe, we always operate with our client’s end goal in mind. This means that we are not only a team of language experts, but also a team of innovators, modernizing traditional qualitative methodologies to maximize client research outcomes. Baking QC measures into every step of our research process is only 

 of the many ways that we do this. Innovations like these—client-centered and science-driven—are what enable us to remain at the forefront of research. 

How inVibe collects top data for deeper insights 

Imagine: Ensuring Only the Highest Quality Voice Responses

inVibe turns traditional qualitative research on its ear through our easy and accessible Listening Platform. Our platform provides a solution for participants to share their stories in their own time, on their own terms, and without fear of judgment by eliminating the need for a moderator.

inVibe has created a convenient, efficient, and systematic platform to collect these important participant stories. We capture narratives that address our clients’ objectives with our thoughtful and intentional study design, focused on the participant experience and leveraging our team’s expertise.

, one of our Senior Analysts, shared in a 

 that the goal of our Voice Response Studies is to prompt respondents to answer a series of questions thoughtfully and thoroughly. We specifically craft our prompts to be thought-provoking and to encourage respondents to pull from personal experience in their unbiased and authentic voice. Starting with the inVibe Prompt Library, which contains thousands of carefully crafted prompts we’ve asked over the years and measured to determine which delivered the most robust response, we design each prompt to meet the objective of our clients.


An example prompt might be something like the following: “Please describe how your condition impacts your day-to-day life. What frustrations or challenges do you experience? And what have you done to adjust to these challenges?” We phrase the prompts as a series of questions to be linear, easy-to-understand, and reflective of how respondents have approached similar questions in prior studies in order to solicit a complete narrative around a central theme.

We collect data in a way familiar to participants: it’s just like leaving a voicemail. Our studies use a real human voice to read the prompts aloud, like the recording in a voicemail box. Participants respond, often with a goal in mind of what to say, but then they may start to ramble. This shift to stream-of-consciousness may result in a “confessional” way of talking. ‘The Confessional Effect’ allows the participant  to speak more openly and authentically, touching on the questions in the original prompt before expanding in a less-prepared, more-improvisational manner. This stream of consciousness is also free from judgment as respondents are more able to quasi-monologue their stories.

Listen to how this caregiver feels as they reflect on the naturalness and ease of using our automated voice response study:

“[When] I did an automated interview for the first time, I was actually surprised how natural it felt to answer a question with an automated response. So, while the moderated response was very normal and typical and natural, I think that then trying the automated response, I was pleasantly surprised to how easy it was to answer questions and then hit accept. Because I think with new technology now, and even just with leaving voicemails, it was easy to answer a question and leave a message kind of idea, how you can leave people voice messages. It was not out of the ordinary to do an automated response with the automated interview. While the moderator was natural, I was pleasantly surprised at how natural it was to do the automated response as well.”

One of the unique aspects of 'inVibing’ research is that it is, by default, carefully controlled for consistency since the questions are pre-programmed. This highly structured way of conducting qualitative research  allows for responses between participants to be directly compared. It gives our analysts a quantitative element along with the rich qualitative data to draw actionable insights from including less obvious themes that are as notable for their absence as for their presence.

To get a better sense of our methodology, 

 to how a patient answers the question “If your experience living with this condition were a book, what would its title be and why? And what would you name the chapter you are currently in?” Notice how she elaborates on why she’s called the book “The Journey to the Summit,” explaining the metaphor for her journey with rheumatoid arthritis, but also rationalizing the decision for her titles as she goes into detail. You can hear how she not only answers the prompt but gives in-depth descriptions.

To demonstrate how much of her answer is devoted to answering and expanding, we’ve highlighted direct answers in 

so I would say I would call this "The Journey to the Summit," the summit of the mountain being like having a great life, and living the best life you can.

 You know, when you're climbing and hiking there are parts of it where you're like, "I feel amazing. I'm killing this hike, I'm doing it." And you feel great. Then there are some parts of the hike where you're down, you're tired, you're hungry, you're not sure if you're going to make it to the top. 

I think that that very much symbolizes arthritis, because there are days when I forget I have it, and I do everything I've ever wanted. And then there are days, or weeks, that go by where you're just debilitated. You can't move, you can't do what you want to be, and you're wondering if it's always going to be like that

. So, I think it is an up and down, but at the end of the day, when you get to the top at the end of your great life, you'll realize that you made it, you could do it, and you had a great journey. And so, I think that that's kind of what I would call it. 

I would say the chapter I'm in now is like "A Restart of the Ascent" because I'm still going up, but the last two years have been really tough.

 I've had a lot of RA flares, I couldn't get it under control. I had to take a ton of Prednisone, had some other medical issues come into it, and so it's just been a really rough two to two-and-a-half years. And so, I finally just found this Humira that's working for me. I'm finally off Prednisone, which is amazing, so I feel like I'm starting to feel more normal and forget that I have arthritis every day. So, I'm starting that climb back up, where I'm feeling great, and I've got this. And I'm going to crush it.”

Patients are not the only ones who go into great detail. Listen

to this caregiver answer the question, “Imagine if you could travel back in time and meet the person you were when you or your loved one were first diagnosed. What advice would you give them? How would you describe to that person how you feel now?” Here, her emotions come out as she reflects on a touchy subject and grapples with some of the decisions she’s made and the realities she’s faced as the parent of a child with epilepsy.

Once again, we’ve highlighted direct answers in 

I would just tell myself that to just keep searching, to keep fighting, to keep learning, and doing what's best for my daughter. 

I feel we have done so. I would advise myself to... I guess I would just maybe give what medications we're on now because the journey has been difficult because she wasn't seizure-free if you will. And now, because of the combination of medication that she's on after years of searching, now we're in a good place. 

So maybe I would just tell myself, try these medications at this dosage, because this is what works for her. I would also tell myself to be patient when it comes to friends that are outgrowing her and she doesn't communicate with the same way anymore because she can't keep up with them.

They're at a different level. That's been hard, I think on me. She has a very good circle of friends, but kids are kids and they notice the differences and she's just different and they know. And so I would say, be patient with that. But other than that, I mean, it's been a difficult journey, but we've always just done what's best for our daughter and we've always just taken on the next challenge fully and done very well with it, I feel. 

So maybe just the medication part would be the only thing that would be really heavy for me to say to myself.

In both instances of patient and caregiver, we hear so much more detail and have so much more clarity. They describe significantly more than just what the prompt asks, which helps our researchers understand the full story and tease out linguistic nuances more effectively.

Through inVibe’s proprietary technology and  methodology, we are able to 

 by providing participants the opportunity to tell their story in their own words without fear of judgment or without worry of expectation. In so doing, we challenge the norms of traditional qualitative research. You can hear participants’ experiences and feel their emotions, and that is exactly what we strive for at inVibe: to listen with empathy.

 and we will show you how it works and why it can give your insights an edge.

'inVibing' research to get richer in-depth participant insights

How inVibe Collects the Authentic, Unscripted, Confessional Participant Story

Imagine getting a ton of great insights from just a few questions. Imagine figuring out how to ask a patient or a doctor a question that will really get them talking. This is the main goal of voice response design at inVibe, and the process we undertake to achieve that goal needs to account for how people interact with each other and how they will interact with us.

There are two main “whys” of inVibe’s design process - why do we limit the number of questions we ask in a single study, and why do we use linguists to compose those questions?

When looking at inVibe’s voice response offerings, one question that likely springs to mind is “wait, why do we ask so few questions?” Indeed, when looking at a set of eight questions relative to the tens of questions that are common in most quantitative studies, it seems like there’s less opportunity to ‘go broad’ and cover all of the ground there is to cover in a given market research topic. Eight questions seems more like a probe or a follow-up rather than a useful first step.

This perspective is certainly understandable, however it couldn’t be further from the reality of the data those eight questions retrieve. The content we gain from our voice response platform, in addition to providing a great depth of insights on a single topic, can easily capture stakeholder opinions on several different parts of a treatment landscape or patient journey. This has everything to do with the fact that, fundamentally, we are not asking respondents closed-ended questions. We’re asking them what (and, often, how) they think.

This seemingly simple shift in approach, giving respondents control over the boundaries of the conversation, allows them to talk as much as they want. While the devil’s advocate view would be that people would give an extremely brief response and get on with their day, that simply does not match our years experience.

In 2021, the average respondent talked for about five and a half minutes. This is not the length of the entire engagement; it does not count them listening to questions. It is five and a half straight minutes of speech – voices of patients, caregivers, and doctors telling us what they think. This translates to hours of perspectives – enough to get immersed in, and certainly enough to derive powerful insights from. It is also in comparison to hours of in-depth interviews where less insight is gained.

Of course, there is a natural follow-up question: “if eight questions provide this much good insight, why not go for more?” The simple answer to this comes down to practicality. While a respondent tends to give a good deal of useful information with only eight prompts to focus on, there is a drop-off in response quality past that point, where people become fatigued, inattentive, and terse. Once we reach that threshold of when a respondent is starting to check the time, we lose thoroughness and depth. Frequently, we see respondents start to frame responses as repetitive, “like I said previously.” Those speech markers are a good sign that the respondent has lost their patience and that we would gain deeper insights by sticking with our methodology of eight questions.

How can we get respondents talking without making them feel like they’re being forced to talk, while using as few prompts as possible? Easier said than done. This is where it is important to have a good working knowledge of how interactions work and why we utilize the expertise of our trained linguists who both compose and analyze our voice response questions. We combine this theoretical background with experience in research design. With backgrounds in conversation analysis and discourse studies, our linguists have a sophisticated understanding of how people talk, which we can then match to the client’s goals to understand what kind of speech we want to draw out of stakeholders.

For example, if we want to understand more about HCP/patient interactions, we can prompt one or both of those audiences to reconstruct what a normal conversation at the doctor’s office sounds like. If we want to test claims that depend on disruptive new clinical data, we can ask a polarizing question that will prompt strong, honest opinions from experts.

In essence, our linguists have access to a large toolbox, in addition to the field experience to know what tool is right for the job. With these resources at our fingertips, the goal of getting respondents talking becomes much less daunting. This way, we can literally shape the discussions respondents have – not by introducing bias, but by giving them a loose structure through which they can speak their mind and provide valuable insights.

And once that part is taken care of, all we need to do is listen. When you are ready to listen, reach out to 

The why’s behind inVibe’s voice response collection process

Imagine: Gaining Deep and Meaningful Insights from just a Few Questions

As published in Drug Development and Delivery on April 5, 2022

Fabio Gratton began his career as a Hollywood scriptwriter. There, he learned that storytelling is difficult, but can be made easier by listening to people to discover their innermost needs and desires. And when he co-founded his first healthcare marketing company about 15 years ago, he quickly realized that pharma had an enormous unmet need — listening to patients and their impassioned stories about illness, treatment, and recovery.

Fast forward to inVibe, a voice research company founded in 2013 (and as of January 2022 has become a division of THREAD), where Gratton, as CEO, has applied this same empathy to market research. Somewhere between traditional quantitative (e.g., online surveys) and qualitative (e.g., focus groups and in-depth interviews) research was a gap where patients were not being sufficiently heard. He realized that innovative uses of digital technology could be adapted to collect, analyze, and deliver these stories back to clients.

 recently spoke with Gratton about patient-focused drug development (PFDD), inVibe’s language model, and the value this technology brings to a patient’s treatment journey.

Q: What progress has been made in patient-focused drug development and what are the continued challenges?

 The good news is that numerous governmental and industry-based initiatives have spawned a new era in patient-focused drug development. Although just getting started, PFDD has documented approaches to data collection, identified best practices and benefits/risk tradeoffs, and analyzed input on patient communications preferences

These efforts tap into the reality that patients are willing and oftentimes enthusiastic to share their feelings about the disease burden and their treatment journey with experts, and actively assist with the generation of evidence and actionable data. Unfortunately, company culture, limited cross-functional collaboration, and leadership hesitancy can create barriers for organizations. But even if those challenges are circumvented, the listening process itself is difficult and demands a new approach.

Human communication is messy. At inVibe, we realized early on that even after we got patients to share their deepest thoughts and feelings, we had another problem: How to extract key insights we could then report back to clients in a way that offers a chance to ask more questions, and provide actionable recommendations.

Q: What is GPT-3 technology and how is it extracting those key insights?

 Our solution is a combination of human expertise and next-gen technology. Trained linguists sort through the data and help organize it; and the latest machine learning algorithms, such as Generative Pre-trained Transformer 3 (GPT-3) enable unprecedented semantic analysis and search capabilities. Our clients benefit from a more thorough analysis and dynamic reporting, fulfilling our mission for clients to actually hear from patients and listen to them, rather than merely process and regurgitate data.

GPT-3 technology was created by OpenAI and is the most expansive machine learning model of its kind. Without exaggeration, the tech literally scans nearly the entire Internet to contextualize and extract meaning from our voice data inputs. The richness of qualitative data is also what can make organizing and processing that data such a challenge. With GPT-3, we are able to design algorithms for specific tasks that reduce busy work and allow analysts to quickly get to meaningful insights.

 By integrating GPT-3 technology, we have developed an algorithm to identify and extract patient concerns from open-ended questions that lead to increasingly specific and nuanced answers — often revealing concerns never before considered. With our machine learning capabilities and human-powered linguistic analysis, the industry has an unprecedented opportunity to listen to and extract key insights from patients throughout the drug development process. This mitigates potential downstream setbacks, and proactively enables study designers to focus on the needs and concerns of patients before drugs even hit the market.

To cite a specific use case, we recently applied the firepower of GPT-3 to the lupus clinical trial landscape, seeking to reveal patients’ preferences for study design and endpoints, and comprehension of patient-facing study materials. By offloading these tasks to a powerful language model, we were able to reveal rich qualitative insights in a much more streamlined fashion. Our technology worked like this: Patients were recruited and screened directly from their own smartphones; they viewed stimuli; listened to automated open-ended questions; responded by simply speaking; then their voice responses were analyzed using a combination of sophisticated software and human expertise. The results were shared with the client through dynamic dashboards that revealed key insights, and suggested actionable recommendations for the brand team.

Q: How are pharma and patients responding to this drug development approach?

 Clients have embraced the concept, and inVibe quickly demonstrated value across disease states ranging from diabetes to oncology. By empowering patients to record their candid feelings directly into smartphones and then analyzing it with a hybrid of human linguistic expertise and advanced machine learning technology, we have changed the game in research.

With proven success across the post-launch life cycle of pharma brands, we also soon realized the importance of applying this novel approach to the drug development process. Our hunch that providing a platform where patients could share their perspectives without friction was correct — and so was our belief that regulators would see it the same way, eventually proven by the FDA Patient Focused Drug Development (PFDD) guidance, and Congress recently passing the Cares Act that created new guidance to ensure patient voices are heard early in clinical trials.

Not only are the government and advocacy groups standing behind technology and linguistic integration into the drug development process, but patients appreciate their voices finally being heard. The end result is empowered healthcare stakeholders — and improved therapeutics. Because key decisions at the development phase have a cascading effect throughout the life cycle of a drug, companies can save considerable money and time — and provide better treatments — by accurately understanding the needs and expectations of their end users: the patients.

That excitement and rationale have also been instrumental in our decision to become a division of THREAD, a technology platform helping to decentralize clinical trials. Together, we’re best positioned to infuse the drug development phase with the power of the patient voice.

Q: What will this mean for the future of patient-focused drug development and personalized medicine?

 I have a Pollyanna outlook on life that permeates all the work that I do in healthcare. Despite the ongoing challenges to listening and understanding patients, I’m confident that the industry will evolve, and along with it so too will our capacity to improve the patient experience to the point where we’re not simply better at managing disease, but preventing it.

The key to accomplishing that goal is to embrace technology so that we empower our humanity. Researchers too often consider what they do, and how they do it, a pure numbers game, mistaking map with territory. In contrast, everything we do is ultimately designed to improve and extend human life. Technology is a means to that noble end. That’s why at inVibe we always start with the problems to be solved on our way to better listening to, and understanding, patients. As we tackle obstacles to data collection, analysis, and reporting, we also keep our minds and hearts on the vision of what an idealized future could and should be like for a healthy society. The future of patient-focused drug development is inspirational.

By better understanding end-users through patient-reported outcomes measures, researchers are already able to integrate these critical insights directly into their processes, methodologies, and even their study designs. The end result is to create more patient-centric trials with increased participation and retention, better study designs, and clinical results that precipitate more effective and safer treatments for all. By combining their dedication to patients and embracing the next-gen in market research capabilities, pharma is poised to catch up to the tech firms paving the way for the ideal consumer experience.

Drug development is only one of many opportunities for personalized medicine to come into its own. The patient experience must be integrated across every touchpoint and milestone in the patient journey. Thanks to this already proven combination of innovative technology and human-powered analytical expertise, those voices are not only being heard, but listened to, allowing for better understanding. Identifying differences between patients and heightening sensitivity to their needs, we are able to create a more personalized experience that improves the entire healthcare system.

Given how healthcare is often a matter of life and death, no initiative is more significant than improving public health. Patients are speaking, and pharma is, with the help of innovative market research, listening more.

An interview with Fabio Gratton

inVibe: Changing the Research Game With Voice

Patient-Focused Drug Development: Methods to Identify What Is Important to Patients

” as the second in a series of four guidance documents that describe how patients, researchers, medical product developers, and others can collect and submit patient experience data and other relevant information from patients and caregivers to be used for medical product development and regulatory decision-making.

The new guidance covers the various approaches to identifying what is most important to patients related to their experience with the burden of disease/condition and treatment. Essentially, the document covers a few core qualitative and quantitative research methodologies, with a focus on their respective strengths and limitations. Particularly compelling is the government’s focus on the importance of infusing drug development with patient voices.

The specific goals of the new guidance are to elicit what is important to patients, which may in turn help inform understanding of disease/condition and clinical trial design. The guidance also hopes to help the generation and use of patient experience data, including clinical outcome assessments and patient preference information, and also inform benefit-risk assessment. Let’s take a look, and discover how inVibe can help fill in some of the blanks.

Limitations of Qualitative Market Research: Cost, Comfort, and Computing

The new guidance breaks down qualitative research modalities into one-on-one interviews and focus groups delivered in-person, through telephone, and online/virtual meetings. In terms of strengths, in-person experiences empower researchers with the greatest flexibility, including the collection of verbal and non-verbal responses. But these sessions tend to be expensive, and inconvenient for patients who may have to commute, or during work hours, etc.

SImilarly, telephone interviews offer the benefits of lower costs and heightened convenience compared to in-person sessions, but are often fraught with technical difficulties and data collection challenges. Virtual meetings have become increasingly common thanks to the pandemic, yet are also compromised by tech and access issues, particularly for disadvantaged patient communities. Patient comfort is also a factor, as clinical settings can prove intimidating.

Limitations of Quantitative Market Research: Anonymity, Applicability, and Analysis

Quantitative research has the distinct advantage of scalability, speed, and cost, and typically comes in the form of surveys that ask closed- and open-ended questions. The former consists of a picklist that patients select from; the latter encourages subjects to submit their own written answers. Response options include yes/no, ratings, rankings, and visual scales. Surveys can be distributed in hardcopy or online, and processed singly or in batches.

Although relatively easy to administer, surveys not only lack the dimensionality and nuance of qual methods, but impose additional limitations on test subjects and market researchers. These include patient challenges with language, interpretation, and the sheer anonymity and depersonalization of the approach. Devoid of feedback or human interaction, results can be incomplete, compromised, or inaccurate – especially for underserved populations.


Supplementing Qual & Quant with inVibe: Voice, Value, and Virtue

The new guidance encourages patient-focused drug development through its broad overview of market research techniques, and implicit encouragement of the industry to infuse every aspect of clinical development with patient insights. By better understanding patient needs throughout, clinical trial design, recruitment, and retention can be heightened, ultimately cascading through the development trajectory to maximize public health benefits.


The inVibe voice-response platform empowers patients from all socio-economic backgrounds to candidly answer questions on their own devices, at their own pace, own their own time, and without the implicit bias of a moderator. Voice responses are collected and analyzed through a combination of machine learning algorithms and human linguistic expertise. Reports are dynamically presented and insights-driven, precipitating actionable recommendations for clinicians to improve processes throughout the development drug development lifecycle. It’s a simple, systematic, and scalable solution for the industry to collect, analyze, and understand the true voice of the patient.


“The new PFDD guidance from the FDA is an expression of the government continuing to encourage our industry to take a more patient-centric approach,” insists inVibe’s co-founder and CEO, 

. “Both quantitative and qualitative market research methods are proven effective, and inVibe was created to apply the latest technology and human expertise to overcome the limitations of each by bringing clinicians the depth and nuance of qual, with the efficiency and scalability of quant.”


All of us at inVibe are thrilled by the ongoing PFDD initiative and are eager to continue partnering with sponsors to ensure their patients are heard and understood throughout the process. Nothing is more natural to people than talking, and no device is more ubiquitous and easy to use than a phone. By encouraging patients from all walks of life and backgrounds to speak, pharma is finally listening at the critical points in the life cycle their voices are needed the most.

How inVibe Supports and Enhances the new FDA Guidance on Patient-Focused Drug Development

As humans, we have natural instincts about how to interpret speech. For instance, when we suggest to our friend we should pick up sushi for dinner and they say “…Sure?”, that long pause and questioning intonation might make us feel like they aren’t that excited about the proposition. We’d probably feel better about ordering sushi for dinner if they said “Sure!” with complete enthusiasm and without a moment of hesitation. In both cases, we’re tuned in to their contextualization cues, or features like pitch, tone, and pauses that help convey the intent behind someone’s words.

The inVibe Listening team is comprised of sociolinguists who are particularly trained to listen “between the lines” for these acoustic nuances. While we’ve all got good ears for this kind of deep listening, technology thankfully exists to reinforce our intuitions in the form of an established, rigorously tested speech emotion recognition (SER) algorithm. In the analysis phase of our work, we turn to this algorithm which tracks the physiological changes – those contextualization cues – in voice that are prompted by stimuli and reactions. These vocal fluctuations are then “translated” into the approximate emotions behind a response by scoring valence (level of positivity or negativity), activation (level of interest and/or excitement), and dominance (confidence and control). Finally, for each prompt, we can illustrate all respondents’ scores on a graph, visualizing the response distribution on a per-question basis. This feature is a valuable asset in the inVibe tool belt, as it allows us to “show” what we as linguists are picking up on.

This graph represents multiple HCP respondents in terms of their dominance (x-axis) and activation (y-axis) for one prompt. Most responses are falling to the right side of the x-axis, indicating respondents’ confidence in their answers.

Acoustics in Practice: The Analysis Phase

While our projects always consider acoustic metrics, we find them to be especially illuminating in concept and message testing studies to help us better understand respondents’ attitudes and reactions. One recent concept testing project that benefitted from acoustic analysis was for an eye care treatment already on the market. The client was looking to reposition this existing treatment and wanted to evaluate how three potential concepts fared with eye care providers (ECPs). To answer these questions, we designed a mixed methods quantitative and voice response study aimed at uncovering concept reactions and perceptions to best position the treatment moving forward.

In the analysis phase, the quantitative findings came in first and laid out a vague framework for us to build on. Concept A scored the highest for resonating with ECPs and motivating them to prescribe the treatment, with Concept B and Concept C resulting in the middle and lowest scores, respectively. These results gave us a sense of ‘what’ ECPs’ general attitudes were but not ‘why’ that was the case, so we then turned to the voice responses, where we had probed participants to explain why they found each concept un(relatable) or un(motivational). Through these responses, we heard ECPs praise and criticize various aspects of the visuals and messaging, which helped us make sense of their quant scores.

Perhaps sharing ‘what’ ECP attitudes were and ‘why’ they felt that way would have been sufficient, but we wanted to go one step further and show ‘how’ the ECPs sounded to fully substantiate and ensure client confidence in our analysis. We used our SER technology to plot ECPs’ answers about each concept’s relatability and motivation on the axes of activation (excitement/boredom) and valence (positivity/negativity). These two parameters are typical in our concept testing measurements, as they best depict participant reactions and feelings. From the following graphs, we see that what they said neatly corresponds with how they said it, justifying the quant rankings that we started with.

Concept A had the highest levels of acoustic activation and valence, indicating that it was positively received and attention-grabbing.

While still positively received, Concept B responses had lower levels of acoustic activation, suggesting less enthusiasm.

Concept C responses were most acoustically negative, which could be due to the more negative reception of language and imagery.

Here we see how valuable visual representation of participants’ emotions were for adding color to our qualitative findings. By reinforcing our linguistic intuitions with AI-powered acoustic metrics, we painted an even clearer, more definitive picture of ECP reactions for our clients.

Listening is at the heart of the inVibe approach, no matter the project. Starting with our awesome team of linguists and layering on technology like our SER software, we derive deep, nuanced insights grounded in human behavior. Whether you’re looking to test visual aids for an upcoming launch or want to better understand the patient journey in your disease state, inVibe’s suite of analytic capabilities can help you make smarter decisions that you feel confident about. Interested in hearing – and seeing – for yourself? 

Listening Between the Lines with Acoustics and Speech Emotion Recognition

Imagine: Seeing What We Hear

The era of the “Blockbuster” pharmaceutical brand that treats tens of millions of patients for diseases like diabetes and high blood pressure has evolved into precisely targeted therapeutics addressing increasingly nuanced conditions and populations. Stunning advances in drug development research, coupled with the ascendance of digital technologies, have created a perfect storm putting the patient front and center of the healthcare system, where they belong.

At the heart of this patient-centric revolution is the acknowledgement that every human being is unique, necessitating a hyper-individualized approach to healthcare. Facilitated and encouraged by heavy investment in customized therapeutics and the rise of on-demand digital services, the treatment of rare diseases exemplifies the challenges and opportunities facing the life sciences industry today. Success is contingent on utilizing once unimaginable levels of personalization.


The convergence of digital health, drug development, and commercialization is also reverberating through the market research industry, where listening to the patient voice is now more important than ever before, especially for rare diseases. By empowering marginalized and disenfranchised patients to candidly share their opinions and feelings directly through their own phones, hurdles are overcome and opportunities created for everyone’s voice to be heard.


“Talking is the most natural thing people do,” insists Fabio Gratton, co-founder and CEO of inVibe, now a division of THREAD. “So if the right questions are asked, in the right way, then most people openly and honestly  answer. I started inVibe with that premise in mind, realizing early on that the whole point of market research is to reveal the hearts and minds of patients eager to express themselves through their own voices – if they’re willing to talk, and the industry listen.”


But talking about their own health is difficult  for most people, especially the disenfranchised. Few people are enthusiastic about discussing their debilitating and sometimes  embarrassing diseases, made worse for marginalized communities accustomed to neglect, inequality, language hurdles, and limited access to technology – all made exponentially worse by the global pandemic. These compounding factors silence those communities that need to be heard the most.

“The paradox is that diverse populations are especially eager to have their voices heard,” continues Gratton, “but not in the way traditional market research is structured. Quantitative surveys feel anonymous and mechanical, while qualitative focus groups can be biased  and intimidating. So how can we expect particularly vulnerable minority populations to bare their souls in emotionally sterile settings that make them feel like we feel they’re sick and stupid?”

Feeling ignored at best, judged at worst, the underserved who suffer from rare diseases are finally being respected and heard: By asking them direct questions through their own phones, barriers of entry are removed and the democratization of healthcare can proceed with the help of creativity, innovation, and the sincere willingness to listen. Rare diseases, often populated by marginalized and hard-to-find patient populations, benefit from renewed insights and action.


Thanks to inVibe’s voice response platform, such unprecedented access to rare disease patient insights is spread along the entire pharma brand life cycle. Voice data collection, natural language processing and human linguistic analysis, and dynamic reporting convey actionable recommendations to clients starved for evidence-based decision making.


“From clinical trial designs to pharma marketing campaigns, once silenced voices are finally being heard,” beams Gratton.


Pharma is increasingly motivated to treat and support rare disease communities, yet is strapped by layers of logistical, regulatory, and bureaucratic hurdles. These obstacles exacerbate the hesitancy of diverse, disenfranchised, and marginalized patient populations to share invaluable clinical trial and post-launch market research insights. By inVibing your trial designs, communication assets, and support programs, you can finally listen and act on their needs.


Thankfully much of the same technology used to personalize the services offered by Big Tech are now in the hands of savvy market researchers poised to energize the treatment of rare diseases. While taking privacy and confidentiality very seriously, inVibe has empowered thousands of patients across hundreds of disease states with the power of their own voice. Stop speculating about what your audience thinks, feels, and does, and start inVibing your brand. 

Listening Closely: Hearing the Voices of the Marginalized in Rare Disease

Imagine decoding the human voice to gain a deeper understanding of what is said, how it’s said, how it sounds, and why it matters. As experts in sociolinguistics – the study of language as a window into human behavior – this is exactly what inVibe’s analysts do every day. 

 to the human voice in market research? Aren’t the words themselves all that we really need? At first, it might seem that way. The truth is, however, trying to determine what someone means based on words alone cannot be done without potential misunderstandings (and if there’s one thing companies want to avoid when talking with valued stakeholders, it’s misunderstandings). 

To illustrate this using a classic example from the study of linguistics, consider how a guest who tells their host: “It’s cold in here” may be disappointed when the host simply agrees instead of offering to close the nearby window. In this situation, the host succeeds in grasping the 

(i.e., a statement of fact), but fails in grasping their 

(i.e., a request to alleviate discomfort).

This scenario demonstrates that when we communicate, our words are just a piece of the puzzle. The reality is that when we speak, there are many factors accompanying our words that contribute to what we want to convey. To put it simply, it’s not just what we say that matters – it’s also how we say it and how it sounds. Using another example, the simple phrase — “You look great today” can be a genuine compliment if spoken in earnest, but also a sarcastic or derisive remark if spoken with a hint of a snicker. Alternatively, placing emphasis on ‘You’ (i.e., “

 look great today“) implies that while perhaps the recipient looks great, someone else present looks to be in comparatively rough shape.

While these examples are extremely simplified, they provide evidence that listening for and interpreting cues beyond words is a natural process that we all engage in, as well as a critical process for truly understanding where people are coming from and what they really need.

None of this is to suggest that words themselves – or “

” cues – can’t still convey a great deal about how someone is feeling. It’s simply that if we ignore the voice, we lose other communicative cues that can further inform meaning. These types of cues are sometimes referred to as “

” and include things like tone, pitch, and even pauses in speech. These features allow us to better understand the emotion and intent behind words. As a final example, consider how even the words in a declarative statement like “It’s Monday” can convey palpable uncertainty and confusion when the speaker adds a pause and an upward inflection (i.e., “It’s… Monday?”).

In our research, inVibe’s focus on the voice means we simultaneously analyze both the linguistic and paralinguistic aspects of a respondent’s speech – with the end result being a complete, high-res picture of what they’re trying to tell us. In a way, providing equal weight to what is said, how it’s said, and how it sounds is like seeing in color, while examining words alone is like seeing in black and white.

Healthcare market research often touches on areas that are complicated, high-stakes, and stressful for stakeholders, and the constant question being asked is: “Why should we focus so much on listening to voice?” However, realizing the extra dimension that voice adds to our data, the real question should be: “Why aren’t we listening more?”

Of course, the first step in analyzing voice data is to collect voice responses. Even at this early stage in the research process, inVibe’s practices are informed by fundamental understandings of how people communicate. In the field of sociolinguistics, it’s well established that participants in a conversation are influenced by their “

” – meaning that they change the way they speak based on who they’re talking to.

Let’s consider the traditional qualitative research approach of using an in-person moderator and the effects it can have on data. From the perspective of the research participant, the moderator is usually a complete stranger, making it likely for many participants to become nervous, uncomfortable, or unable to speak as they would under normal circumstances. They might even feel pressure to change their answers based on what they think the moderator wants to hear. On the other end, the moderator can also be biased or inconsistent with their inquiries, in some cases even “leading” participants to certain preferred answers.

By inVibing the process, participants call in at their convenience and engage in our research from wherever they feel the most comfortable. Since our prompts are pre-recorded, each participant is asked the same question, the same way, every time, allowing us to control the experimental variable and eliminate the potential for interviewer bias. This unique methodology elicits responses that are open and uninhibited, free from the influences of pressure or judgment that may be more typically present in a face-to-face scenario. This is a huge benefit for any type of research but is particularly helpful in healthcare where patients, caregivers, and HCPs alike are more likely to hold back when discussing delicate, personal aspects of their lives and professions.

While it’s important to have good data, that’s truly only the starting point. The next step is to make sure the analysts working with the data have the expertise necessary to get the most out of it. Voice data is a rich resource, brimming with potential for valuable insight, but without specialized knowledge in the way language works, it’s likely that a good deal of that resource would go untapped. That’s why inVibe’s research team is built out with sociolinguists, who by trade are highly skilled in both research and the critical analysis of language data. Armed with inVibe’s powerful proprietary platform, our analysts are empowered to identify and track key themes and attitudes as they listen to all types of stakeholders shed light on the areas where they need the most help.

we translate what we hear into actionable insights. But we don’t simply report findings and expect our clients to take our word for it. We bring the voice of our participants into the spotlight, providing concrete examples of where it drives our intuitions and the scientific framework for why those intuitions are valid. In other words, we highlight not only what we find in the data, but how we arrived there and why it matters.

"Talking is the most natural thing we do. It’s one of the most engrained skills we have as human beings. The most effective form of communication. We should be using that enabled skill to let people express themselves naturally,

At the end of the day, inVibe makes listening a standard by providing confidence and clarity to the decision-making process across the industry. See our 

 for examples of how we’ve helped companies gain deeper insight through the power of voice, and reach out to learn more about how our capabilities can best serve your needs. And of course, if you already have some ideas about how your company might benefit from harnessing the power of voice, get in touch – we’ll be more than happy to listen.

Imagine decoding the human voice to gain a deeper understanding of what is said, how it’s said, how it sounds, and why it matters. As experts in sociolinguistics – the study of language as a window into human behavior – this is exactly what inVibe’s analysts do every day. But why should we prioritize listening to the human voice?

What is said, how it's said, how it sounds, and why it matters

Imagine: Decoding the Human Voice

, a leading technology and service provider enabling electronic clinical outcome assessments (eCOA) and decentralized clinical trials (DCTs), today announced that it has acquired 

, the leading voice-powered research and insights technology solution for the life sciences and health care industry. THREAD’s addition of inVibe’s voice research technology and consulting services to its comprehensive decentralized research platform follows the company’s 

As clinical trials and real-world research have grown more complex, experts have challenged the industry to bring the patient voice into research studies in one platform. THREAD's new offering addresses these needs by providing actionable intelligence for customers focused on real-world patient experience. This also proactively keeps THREAD customers in compliance as regulators are now requiring patient insights and feedback to be incorporated into clinical research.

“inVibe adds capabilities to the THREAD platform that allow us to integrate the power of voice into clinical research. This will help us as we seek to create the best possible trial experiences for participants and all other study stakeholders. The ability to analyze and integrate data from listening technology is currently missing from other top players in the industry. We are moving the needle when it comes to delivering adaptive, patient-centered research experiences,” said John Reites, CEO of THREAD.

“The inVibe solution supports multiple research phases and stakeholders, keeping patients and health care professionals as our top priority at all times,” said Fabio Gratton, CEO of inVibe. “Joining THREAD will expedite the delivery of primary research with direct participant listening research via automated survey and voice data capture, and will alter the outcomes of new drugs in the marketplace.”

Acquisition of inVibe adds an innovative, voice-powered research method to THREAD’s technology platform bolstering its mission to modernize clinical research 

New Data Intelligence: An ear to the future

imagine

A tech-enhanced, human-led analytical approach

imagine

Ensuring Only the Highest Quality Voice Responses

How inVibe Collects the Authentic, Unscripted, Confessional Participant Story

imagine

Gaining Deep and Meaningful Insights from just a Few Questions

/voice

/product

/resources

/use-cases

/company

@social