Open research questions in Clinical Reasoning and Diagnostic Skills
248 unresolved questions extracted from the limitations and future-work sections of 1,193 Clinical Reasoning and Diagnostic Skills papers in our library. Each links back to the study that raised it.
What the literature leaves open
The challenge of providing accurate and up-to-date answers to complex clinical questions. The need to avoid fabricated citations and ensure evidence-based responses. The challenge of evaluating the performance of conversational AI systems in medicine.
OpenEvidence clinical question-answering platform: systematic review of early evaluations · 2026 · DOIThe current evidence base for OpenEvidence remains sparse, - Findings are inherently limited by being snapshots taken at specific moments, - Benchmarking at single time points constrains the generalizability and comparability of results, - OpenEvidence continuously evolves in its underlying model, retrieval mechanisms, and content sources
OpenEvidence clinical question-answering platform: systematic review of early evaluations · 2026 · DOIResearch on the implications of generative artificial intelligence chatbots in mental healthcare - Investigation of how artificial intelligence influences patients' self-understanding and help-seeking
When patients consult artificial intelligence before clinicians: restoring clinical prioritisation in mental health care · 2026 · DOIThe paper identifies a gap in understanding how AI has shaped the patient's narrative and its impact on clinical prioritisation. It highlights the need for clinicians to address AI-driven mental health discourse in clinical practice. The paper notes that prior work has focused on the benefits of AI in mental health care, but has neglected the potential risks.
When patients consult artificial intelligence before clinicians: restoring clinical prioritisation in mental health care · 2026 · DOIFuture research could explore how scaffolded reflection prompts, specifically triggered by AI counterarguments, enhance diagnostic calibration and reduce cognitive biases more effectively than disclaimers alone, - A learning module could require students to articulate their reasoning both before and after encountering AI disagreement, followed by guided comparison
Beyond warnings: Leveraging AI disagreement as a catalyst for reflective clinical reasoning · 2026 · DOIThe limitations of using AI diagnostic advice with warnings. The need for a new approach to integrate AI tools into clinical training. The potential of using AI-generated feedback as a catalyst for reflective clinical reasoning.
Beyond warnings: Leveraging AI disagreement as a catalyst for reflective clinical reasoning · 2026 · DOITraditional evaluation methods for physician-patient interactions are time-intensive and subject to inter-rater variability. There is a need for more efficient and consistent assessment methods that can provide accurate and useful feedback.
Large language model evaluation and feedback of transcribed simulated physician-patient verbal interactions · 2026 · DOIThe study was restricted to a Zoom videoconferencing platform due to the Covid-19 pandemic, - The sample size was limited to 31 undergraduate optometry students, - The study only examined the use of cues in a diagram completion task
Exploring the use of metacognitive monitoring cues following a diagram completion intervention · 2024 · DOIFurther research could examine the use of cues in different learning tasks, - Research could investigate the effectiveness of interventions to improve monitoring accuracy
Exploring the use of metacognitive monitoring cues following a diagram completion intervention · 2024 · DOIThe limitations of this study include constraints of resources and time: the number of disease categories covered by the developed cases remains limited and the empirical evaluation sample size is relatively small.
Application of Computer-Simulation-Based Clinical Case Training for General Practice Clinical Reasoning in Standardized Residency Training: A Digital Health Communication Perspective · 2026 · DOIThe finding that o3 showed no language gap on the overall score, while all other models did, warrants attention.
Prompting language influences diagnostic reasoning and accuracy of large language models · 2026Diagnostic error case conferences are used as educational interventions, but their impact on sustained learning behaviors remains unclear.
“Learning bystander activation”: resident-led diagnostic error case conferences and sustained reflective engagement among junior residents · 2026 · DOIWhile traditional diagnostic decision support systems (DDSS) have seen limited adoption because of high input burden and low perceived value, large language models (LLMs) now offer genuine dialogue and reduced effort, with rapidly improving diagnostic performance, yet empirical evidence on their real-world effectiveness and educational impact is still scarce.
Large language models enhance diagnostic reasoning of medical students in rheumatology: a randomized controlled trial · 2026 · DOITop-1 point estimates favored AI assistance but were inconclusive: Adjusted accuracy was 47.
Real-Time Artificial Intelligence Diagnostic Copilot in Simulated Primary Care Consultations: Randomized Simulation Study · 2026 · DOIHowever, research on the associations between UT and RA and students’ individual characteristics, such as age and gender, remains limited, and existing findings are inconsistent.
Given the high proportion of female students, these differences may warrant further investigation and consideration in curriculum development to promote equitable opportunities and optimally prepare all students for clinical practice.
CONCLUSIONS: While we do not consider ChatGPT in its current version capable of generating a realistic blueprint for a VP collection, we believe that the process of prompting, combined with iterative discussions and refinements after each step, is promising and warrants further exploration.
Applying ChatGPT to plan and create a realistic collection of virtual patients for clinical reasoning training · 2025 · DOIFuture research should explore students' perspectives of the value of the Framework to inform their clinical reasoning.
Entry to practice physiotherapy students’ use of the international IFOMPT cervical framework to inform clinical reasoning: a qualitative case study design · 2025 · DOIThe overall impact of the COVID-19 pandemic on undergraduate medical clinical practice remains unknown, in particular whether this context disproportionately affected lower-income regions, as was the case analysed in this study.
Using the OSCE to assess medical students’ communication and clinical reasoning during five years of restricted clinical practice · 2025 · DOIThis study investigated an under-researched source of measurement error in high-stakes examinations, namely mistakes in examination papers (e.
‘If you have a question that doesn’t work, then it’s clearly going to upset candidates’: what gives rise to errors in examination papers? · 2024 · DOIAlthough this tolerance appears to be related to burnout and work engagement, few studies have examined this association among physicians.
Associations of clinical context-specific ambiguity tolerance with burnout and work engagement among Japanese physicians: a nationwide cross-sectional study · 2024 · DOIBACKGROUND: The consensus that clinical reasoning should be explicitly addressed throughout medical training is increasing; however, studies on specific teaching methods, particularly, for preclinical students, are lacking.
Fostering clinical reasoning ability in preclinical students through an illness script worksheet approach in flipped learning: a quasi-experimental study · 2024 · DOIAppraised throughout health education literature, SCTs are cognitive assessments of clinical reasoning, though their use in Doctor of Physical Therapy (DPT) entry-level education has not been investigated.
Evaluating clinical reasoning in first year DPT students using a script concordance test · 2024 · DOIFuture research could investigate the effects of CR curricula on desired outcomes, such as patient care.
Current status and ongoing needs for the teaching and assessment of clinical reasoning – an international mixed-methods study from the students` and teachers` perspective · 2024 · DOIFuture research is required to explore use of the Framework to inform clinical reasoning processes in learners at different levels.
Use of the International IFOMPT Cervical Framework to inform clinical reasoning in postgraduate level physiotherapy students: a qualitative study using think aloud methodology · 2024 · DOI
Most-cited papers in Clinical Reasoning and Diagnostic Skills
- The Structured Clinical Interview for DSM-III-R (SCID) · Archives of General Psychiatry · 1992 · 3,181 citations
- Diagnostic Error in Internal Medicine · Archives of Internal Medicine · 2005 · 1,210 citations
- Mindful Practice · JAMA · 1999 · 962 citations
- Research in clinical reasoning: past history and current trends · Medical Education · 2005 · 724 citations
- What every teacher needs to know about clinical reasoning · Medical Education · 2004 · 715 citations
- Diagnostic reasoning based on structure and behavior · Artificial Intelligence · 1984 · 642 citations
- Large Language Model Influence on Diagnostic Reasoning · JAMA Network Open · 2024 · 562 citations
- Diagnostic Error in Medicine · Archives of Internal Medicine · 2009 · 535 citations
- Virtual patients: a critical literature review and proposed next steps · Medical Education · 2009 · 489 citations
- The paramorphic representation of clinical judgment. · Psychological Bulletin · 1960 · 478 citations
Most recent work
- Performance of a large language model on the reasoning tasks of a physician · Science · 2026
- Why Medical Education Without Artificial Intelligence Still Matters: A Neuroscience-Informed Perspective · JMIR Medical Education · 2026
- The effectiveness of large language models in dental specialty questions: a comparative study in the field of prosthodontics · BMC Medical Education · 2026
- Large language models enhance diagnostic reasoning of medical students in rheumatology: a randomized controlled trial · BMC Medical Education · 2026
- Towards accurate and interpretable competency-based assessment: enhancing clinical competency assessment through multimodal AI and anomaly detection · npj Digital Medicine · 2026
- The value of doubt: training LLMs to consider diagnostic uncertainty may improve clinical utility · npj Digital Medicine · 2026
- Innovating diagnostic learning: How generative AI explanation styles influence cognitive load and confidence calibration in medical students · Computers & Education · 2026
- Error-based learning in health professions education: AMEE Guide No. 191 · Medical Teacher · 2026
- Standardized patient gender influences diagnostic accuracy in undergraduate medical students’ cardiac OSCE interviews · Medical Teacher · 2026
- Using the Nominal Group Technique to explore the contemporary relevance of the Clinical Reasoning Cycle as a pedagogical model for nursing education · Nurse Education Today · 2026
Find a gap in your own Clinical Reasoning and Diagnostic Skills sub-topic
This page shows what the Clinical Reasoning and Diagnostic Skills literature already flags as unresolved. To narrow it to your specific question, run the guided finder — it searches the gap library on demand and checks candidates against 250M+ OpenAlex works.
Open the Research Gap Finder →