The research team, led by investigators at the University of Hong Kong and Ningbo Hospital of Integrated Traditional Chinese and Western Medicine in China, took a deliberately modular approach. Rather than asking an AI to produce an end-to-end diagnosis from an image, they split the problem into two separate modules. The first tested whether a large multimodal model could transcribe and interpret pure-tone audiometry and tympanometry images. The second tested whether AI workflows could calculate twenty-five prespecified clinical fields and draft professional and patient-facing reports in Chinese, given already-verified structured data. This separation matters because a single end-to-end score can hide whether errors come from reading the image, applying specialty rules, or communicating the result.

The study drew on 158 outpatient audiology encounters collected between December 2024 and March 2025, of which 155 records representing 151 unique patients and 302 ears were eligible. Reference standards were built painstakingly: two trained transcribers independently entered every threshold while masked to each other, and two audiologists with 13 and 16 years of clinical experience classified tympanogram curves, agreeing on 296 of 300 dually classified ears, a Cohen’s kappa of 0.979. Air-bone gaps, hearing-loss degrees, and loss types were derived under prespecified rules, including a local convention that a meaningful air-bone gap required at least two comparable frequencies with gaps of 15 dB or more.

The heart of the first module was the audiologist skill: a carefully engineered prompt, not a fine-tuned model, that encoded audiological practice. Early development errors were revealing. The model initially produced thresholds not on the standard 5-dB grid, misapplied degree boundaries, overcalled conductive components, treated insufficient bone-conduction evidence as a negative air-bone gap, and read cancelled 95-dB acoustic-reflex marks as present responses. The refined skill imposed a fixed sequence: verify the image and ear, inspect axes and legends, assign symbols, transcribe before calculating, preserve no-response entries, then derive and cross-check. When masking could not be assigned unambiguously, the prompt instructed the model to abstain rather than guess.

The results of the locked test were striking. In 50 development records, the skill raised hearing-loss-type agreement from 85.0 to 94.0 percent and acoustic-reflex agreement from 70.4 to 98.4 percent compared with a schema-only prompt. In the held-out evaluation of 101 independent patients using a Codex GPT5.5 agentic workflow, the system achieved 1809 of 1820 exact numeric thresholds, 99.4 percent, and 91 of 101 patients met every numeric and no-response criterion. Degree was correct in all 101 patients, hearing-loss type in 100, and tympanometry measurements in all 578 entries. Yet the Achilles’ heel persisted: only 9 of 15 no-response entries were correct, and 18 of 19 air-bone-gap mismatches occurred because the model forced a negative label when the evidence supported an indeterminate one.

A post hoc robustness analysis using DeepSeek-V4-Flash-Vision-Exp on the same patients showed how much performance depends on the implementation. With the same locked skill, hearing-loss-type agreement rose from 37.6 to 70.3 percent, a dramatic improvement, but exact numeric-threshold agreement reached only 72.1 percent, reflex agreement hovered near 69 percent, and no-response agreement was zero. The authors are careful to note this was a descriptive cross-model comparison, not a matched foundation-model experiment, since the execution environments differed. The lesson, however, is clear: specialty guidance can substantially improve rule-dependent interpretation, but raw visual accuracy remains tied to the underlying model and workflow.

The second module addressed reporting. Here the AI received adjudicated structured values rather than its own image predictions, calculated twenty-five prespecified fields, and drafted separate Chinese professional and patient-facing reports. After two audiologists reviewed 60 initial cases and identified overreliance on the speech-frequency average, omission of high-frequency losses, and weak integration of history with results, the prompts were refined and locked. In the formal evaluation of 91 independent patients, all twenty-five rule-derived fields were correct in 91 of 91 Codex-workflow cases and 87 of 91 DeepSeek-workflow cases. Both audiologists rated every single report from both workflows as accurate or basically accurate; no report received a rating of clear error or potentially misleading.

An exploratory lay evaluation added a human dimension. Five lay raters compared pre-refinement patient-facing reports from the two workflows in 48 patients. DeepSeek reports were preferred for explanations in 44 of 48 patients and for next steps in 30, but they were also significantly longer, with a median of 392 versus 235 Chinese characters. Overall preference and perceived ease did not differ significantly. The authors emphasize that preference and readability proxies do not establish comprehension, and that no lay evaluation of the refined reports was conducted. This matters because hearing-health materials often exceed recommended reading levels, and limited health literacy can coexist with hearing loss in older adults.

The study’s limitations are candidly enumerated. It came from a single hospital with two devices over four months. Only 15 no-response entries existed, from just three validation patients. The two audiologists who rated the final reports were the same ones who had refined the prompts, raising the possibility of incorporation bias. Even with zero unfavorable ratings among 91 patients, the statistical upper bound on the unfavorable-report rate remains roughly 4.1 percent. Reproducibility was constrained by reliance on proprietary services: the exact Codex snapshot and sampling settings were unavailable, and provider data retention could not be excluded. No end-to-end test connected the two modules, so error propagation from image to report was never measured.

What the study ultimately offers is an architecture rather than a product. The authors envision a safety-conscious pipeline in which image transcription, deterministic validation and calculation, report drafting, uncertainty flags, and clinician approval remain visible, auditable handoff points. This aligns with what Chinese audiologists themselves have said in qualitative work: AI may absorb repetitive technical work, but communication, judgment, and responsibility should remain clinician-led. The findings support prospective evaluation of modular, clinician-supervised assistance, not autonomous diagnosis. The next step, the authors argue, is a silent prospective deployment that connects the modules while preserving intermediate outputs, measuring abstention, correction burden, review time, patient comprehension, and downstream clinical decisions. Until then, the audiogram-reading AI remains a promising apprentice, one that can transcribe nearly every threshold perfectly yet still needs its audiologist to teach it what silence means.

Subject of Research: Audiologist-guided multimodal AI for interpreting pure-tone audiometry and tympanometry and generating clinical reports

Article Title: Audiologist-Guided Multimodal AI for Pure-Tone Audiometry and Tympanometry Interpretation and Reporting

Article References: Wu, X., Shen, X., Mo, C., Shao, S., Wang, J., & Wang, S. (2026). Audiologist-Guided Multimodal AI for Pure-Tone Audiometry and Tympanometry Interpretation and Reporting. Journal of Medical Systems, 50(1), Article 140. https://doi.org/10.1007/s10916-026-02463-5

Image Credits: AI Generated

DOI: 10.1007/s10916-026-02463-5

Keywords: artificial intelligence, audiology, pure-tone audiometry, tympanometry, large language models, multimodal AI, clinical decision support, hearing loss, medical imaging AI, patient communication, prompt engineering, Journal of Medical Systems

The study focused on the Objective Structured Clinical Examination, or OSCE, a cornerstone of medical training in which trainees rotate through stations and interact with standardized patients — trained actors portraying realistic clinical scenarios. In this case, 126 first-year internal medicine residents at NYU completed six communication-focused OSCE cases between 2019 and 2023, with 82 assessed in person and 54 assessed virtually. In each case, the standardized patients rated resident performance across three core communication domains: information gathering, relationship development, and patient education. Crucially, the ratings used a behaviorally anchored scale — “not done,” “partially done,” or “well done” — meaning each rating level corresponded to observable clinical behaviors rather than a vague global impression. This design choice mattered enormously for the analysis that followed.

Most studies comparing virtual and in-person OSCEs have stopped at overall performance scores, concluding broadly that the two formats produce similar results. The NYU team, led by Christine P. Beltran and Colleen Gillespie, argued that such aggregate comparisons can mask important differences. Two exams might yield identical average scores while individual checklist items behave differently across formats — for example, if a particular behavior is easier to demonstrate, or easier to notice, over video. To detect these hidden discrepancies, the researchers turned to the graded response model, a form of item response theory that estimates what they call item-level thresholds. Each threshold represents the amount of underlying communication proficiency a resident needs to move from one rating category to the next — from “not done” to “partially done,” or from “partially done” to “well done.” If a threshold is lower in one modality, that means residents need less actual skill to earn the same rating there.

The technical machinery is worth unpacking, because it represents a meaningful methodological advance for medical education assessment. In a graded response model, every checklist item is characterized by a discrimination parameter, describing how well the item distinguishes between residents of different ability levels, and a set of threshold parameters, marking the points on the latent proficiency continuum where the probability of achieving each successive rating crosses 50 percent. By fitting the model separately to virtual and in-person data and then comparing threshold estimates with Wald tests — a standard statistical procedure for testing whether estimated parameters differ significantly — the researchers could ask, item by item, whether “partially done” or “well done” meant the same thing in both settings. This stands in contrast to traditional approaches that compare mean scores, which assume that identical numbers imply identical underlying constructs.

The headline results were, in most respects, reassuring. Most residents demonstrated sufficient skill to receive “partially done” or “well done” ratings on the majority of communication items, regardless of format, and overall communication performance appeared broadly similar across modalities. For program directors worried that the pandemic-era pivot to virtual assessment diluted their exams, the message is largely encouraging: the global picture of resident communication competence looks comparable whether the encounter happens in an exam room or on a screen. But the item-level analysis told a subtler story. One specific behavior — “using words the patient understood and explaining jargon” — showed a statistically significant difference between modalities. Residents required a lower level of underlying proficiency to receive a “partially done” rating on that item in virtual encounters compared with in-person ones, with a Wald test statistic of z = 3.92 and an adjusted p-value of 0.001.

Why would explaining medical jargon in plain language be easier to credit over video? The authors are careful to lay out several non-exclusive explanations. It may reflect genuine modality-related variation in the skill itself: residents might consciously simplify their language when they cannot rely on physical props, printed materials, or the full repertoire of in-person cues, making plain speech more prevalent on screen. Alternatively, the difference may lie in rater scoring — standardized patients evaluating a video encounter may attend differently to language, or may be more generous when communication is constrained by technology. Both mechanisms could produce the same statistical signature, and the study design cannot fully disentangle them. What the finding does establish, however, is that at least one checklist item does not function equivalently across formats, which means raw scores from virtual and in-person exams are not perfectly interchangeable, even when their averages look the same.

The broader context makes the study timely. Telehealth has evolved from a pandemic stopgap into a permanent fixture of American medicine, and organizations such as the Association of American Medical Colleges have published telehealth competency frameworks urging training programs to teach and assess virtual care skills deliberately. Previous studies of virtual OSCEs — spanning physical medicine and rehabilitation residencies, pediatric high-stakes exams, dental education, and systematic reviews of implementation across the health professions — have generally reported acceptable feasibility and comparable overall performance, but few have probed whether individual rating categories mean the same thing across formats. Earlier psychometric work had already applied item response theory to OSCE data to explore rater effects and item discrimination, and researchers had documented differences in how satisfied patients feel about physician communication during telemedicine visits. The NYU study ties these threads together, using threshold analysis as a diagnostic for format comparability.

For the assessment community, the practical implications are concrete. Programs running mixed-modality OSCEs — increasingly common as telehealth training becomes standard — can use graded response modeling as a routine quality-assurance step, flagging items whose thresholds drift between formats before those items contaminate pass-fail decisions. The one flagged behavior in this study, avoiding jargon, is itself a natural candidate for targeted curriculum revision: if residents earn partial credit for plain language more easily online, virtual encounters may need explicit prompts or rubric anchors that distinguish genuine skill from modality-driven simplification. The authors also note that their sample, drawn from a single internal medicine program across six cases, limits generalizability, and that the modest virtual cohort of 54 residents constrains statistical power. The project, funded through the AAMC Competency-Based Education in Telehealth Challenge Grant, was reviewed by NYU’s institutional process and classified as educational quality improvement using fully anonymized, de-identified data, with the informed consent requirement waived accordingly. The work was previously presented as a poster at the 2025 Society of General Internal Medicine Annual Conference.

Perhaps the most durable contribution of the study is conceptual: it reframes what “equivalence” means in clinical skills assessment. Averages alone, the authors argue, can lull educators into false confidence, because two formats can converge on the same totals while individual behaviors are weighted differently by raters or expressed differently by trainees. Threshold analysis offers a way to interrogate whether an observed rating reflects the same level of underlying communication proficiency across settings — essentially asking not just whether residents score the same, but whether the same score certifies the same competence. As telemedicine cements its place in routine care, ensuring that the exams certifying tomorrow’s physicians measure what they claim, in every modality, is no longer a technical nicety. It is a patient-safety question, and this study provides a template for answering it one checklist item at a time.

Subject of Research: Item response theory analysis of internal medicine residents' OSCE communication skill ratings in virtual versus in-person examinations

Article Title: When “Well-Done” Is Not the Same: Item Response Theory Analysis of Medicine Residents’ OSCE Communication Ratings Across Modalities

Article References: Beltran, C. P., Nallamaddi, S., Wilhite, J. A., Hardowar, K., Hanley, K., Altshuler, L., Zabar, S. R., & Gillespie, C. (2026). When “Well-Done” Is Not the Same: Item Response Theory Analysis of Medicine Residents’ OSCE Communication Ratings Across Modalities. Journal of General Internal Medicine. https://doi.org/10.1007/s11606-026-10798-5

Image Credits: AI Generated

DOI: 10.1007/s11606-026-10798-5

Keywords: OSCE, item response theory, communication skills, medical residents, telehealth, virtual assessment, standardized patients, internal medicine, graded response model, medical education, assessment comparability, patient communication

The study, published in Public Health in Practice, was conducted through a cross-sectional online survey administered between April and June 2021. Experts from healthcare, academic and governmental institutions, and patient associations were recruited through a purposive, network-based sampling strategy in which national ENABLE representatives identified colleagues with clinical, policy, or research expertise in adherence. The survey was piloted among 12 experts from five countries before deployment, and open-ended responses were analyzed using the qualitative framework method, in which pairs of researchers independently coded each response before reconciling their decisions through team consensus. The resulting codes were then quantified at the respondent level and compared across Western, Central, and Eastern European regions defined by the Global Burden of Disease classification.

The professional landscape of adherence support proved to be dominated by three groups. Physicians, including general practitioners, specialists, and clinical pharmacologists, were named by 90.7 percent of respondents as being involved in medication adherence management in their country. Pharmacists followed at 70.7 percent, and nurses at 55.7 percent. Beyond this core trio, involvement dropped sharply: other professionals such as medical technicians, physiotherapists, midwives, and social services were cited by just 10 percent, psychologists by 7.1 percent, and national health insurance institutes by 5 percent. Regional patterns varied, with nurses far more likely to be cited in Western Europe, where 72.1 percent of respondents mentioned them, compared with 41.3 percent in Central Europe, suggesting that the structure of national health systems shapes who takes responsibility for keeping patients on treatment.

When experts described what happens once a patient is identified as non-adherent, communication and education emerged as the most frequently reported intervention category in every region, cited by 83.6 percent of Western, 87.3 percent of Central, and 68.8 percent of Eastern European respondents. This category encompassed direct patient communication, patient education, peer support groups, self-care training programs, shared decision-making, motivational interviewing, and longer consultations. Follow-up and monitoring was the second most common category, reported by 60.7 percent of Western, 49.2 percent of Central, and 43.8 percent of Eastern European experts, and included closer follow-up visits, regimen simplification, dose-dispensing by pharmacies, and structured medication reviews.

The two remaining categories revealed a more fragmented picture. Collaborative and multidisciplinary approaches, such as involving other healthcare professionals, home care staff, or family caregivers, and technological solutions, including mobile apps, reminders, and pill organizers, were reported significantly less often by Central and Eastern European respondents than by their Western counterparts. Exploratory statistical testing using the Fisher–Freeman–Halton exact test, with p-values adjusted by the Benjamini–Hochberg procedure, found regional differences for both categories, each with an adjusted p-value of 0.046 and a Cramér’s V of roughly 0.24, indicating a modest but measurable association between region and intervention type. Western Europe’s more frequent use of collaborative models may reflect better-resourced systems, but the authors caution that professional boundaries and time constraints can limit multidisciplinary working even where infrastructure exists.

Perhaps the most consequential finding concerns which interventions experts actually believe work. Direct patient communication, encompassing motivational interviewing, shared decision-making, longer consultations, peer support, and patient training, was the single intervention most frequently perceived as successful, identified by 35 percent of all respondents. At the category level, communication and education again led in every region, cited as successful by 36.1 percent of Western, 46.0 percent of Central, and 50 percent of Eastern European experts. Collaborative approaches were seen as successful by 34.4 percent of Western respondents but only 20.6 percent of Central and 6.3 percent of Eastern respondents, while follow-up and monitoring was named by 19.7, 23.8, and 6.3 percent respectively. Notably, after adjustment for multiple comparisons, none of these regional differences in perceived success reached statistical significance, leaving the descriptive patterns suggestive rather than definitive.

The gap between availability and perceived effectiveness is itself revealing. Roughly eight in ten experts said direct patient communication was available in their country, yet only slightly more than a third judged it successful. The authors point out that communication is not inherently beneficial: a clinician who blames or reprimands a patient for missing doses is also communicating directly, and likely counterproductively, since patients who feel judged may disengage further. Limited consultation time, heavy workloads, variable communication skills, health literacy gaps, language barriers, and the compounding complexity of multimorbidity and polypharmacy all constrain how well conversations about medicines can translate into sustained behavior change. The finding echoes a broader evidence base showing that physician communication quality is one of the strongest modifiable predictors of adherence.

Technology, often heralded as the future of adherence support, played a surprisingly marginal role. Fewer than a third of experts reported technological solutions as available, and they were perceived as successful even less often. The authors attribute this limited uptake to practical barriers documented in prior research: uncertain reimbursement, poor integration with electronic health records and pharmacy systems, data privacy concerns, and uneven digital literacy and access among older or multimorbid patients, precisely the populations most likely to need adherence support. This aligns with systematic reviews that have found digital adherence tools to be only moderately effective on average, suggesting that apps and reminders are best understood as complements to, rather than substitutes for, human interaction.

The COVID-19 pandemic provided an unplanned stress test of how adherence support adapts under disruption, and the results were sobering. Some 40.7 percent of experts reported no specific medication adherence initiatives in their countries during the pandemic, although the authors urge caution since responses were retrospective and depended on respondents’ awareness of national or local programs. Among the adaptations that were reported, telemedicine, including e-prescriptions, led at 15.7 percent, followed by easier access to medicines through pharmacist services and home delivery at 7.9 percent, and informative campaigns, lectures, and webinars at 6.4 percent. Respondents from Central Europe described the widest range of initiatives, including vaccination-related actions and educational programs for healthcare professionals. The heterogeneity underscores, the authors argue, the need to build resilient and accessible adherence support that can withstand major healthcare disruptions rather than being improvised mid-crisis.

The study’s implications reach beyond academic classification. Because the analysis maps what is actually practiced rather than what trials recommend, it identifies concrete candidates for future implementation research: structured adherence checks embedded in routine visits, documentation in electronic records, monitored adherence indicators, and multidisciplinary teams that combine communication, behavioral, digital, and system-level approaches. The authors are candid about limitations, including possible selection bias from network-based recruitment, an Eastern European subsample of only 16 respondents from four countries, reliance on expert perception rather than objective effectiveness data, and the absence of probing possible in a self-administered survey. Yet the scale of the exercise, spanning 35 countries and coordinated through the COST Action ENABLE network, makes it an unusually comprehensive snapshot. Its central message is likely to resonate with clinicians and policymakers alike: before Europe invests in the next generation of adherence technology, it should first ensure that the oldest intervention, a trusted conversation between patient and professional, is done well, consistently, and everywhere.

Subject of Research: Expert-reported mapping of medication adherence interventions across 35 European countries

Article Title: Mapping medication adherence interventions across Europe: Expert perspectives from 35 countries

Article References: Mucherino, S., Aarnio, E., Qvarnström, M., Hafez, G., Kamusheva, M., Potočnjak, I., Trečiokiene, I., Mihajlović, J., Ekenberg, M., van Boven, J., & Leiva-Fernandez, F. (2026). Mapping medication adherence interventions across Europe: Expert perspectives from 35 countries. Public Health in Practice, 12, Article 100850. https://doi.org/10.1016/j.puhip.2026.100850

Image Credits: AI Generated

DOI: 10.1016/j.puhip.2026.100850

Keywords: medication adherence, Europe, ENABLE, patient communication, healthcare professionals, technological solutions, multidisciplinary care, COVID-19, survey research, public health, pharmacists, health systems