kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Medical reasoning in LLMs: an in-depth analysis of DeepSeek R1
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.ORCID iD: 0000-0002-6529-1211
Karolinska Inst, Dept Clin Sci Intervent & Technol, Div Speech & Language Pathol, Stockholm, Sweden; Karolinska Univ Hosp, Sect Speech & Language Pathol, Theme Womens Hlth & Allied Hlth Profess, Stockholm, Sweden.
Stockholm Hlth Care Serv, Stockholm, Sweden.
2025 (English)In: Frontiers in Artificial Intelligence, E-ISSN 2624-8212, Vol. 8, article id 1616145Article in journal (Refereed) Published
Abstract [en]

Introduction The integration of large language models (LLMs) into healthcare holds immense promise, but also raises critical challenges, particularly regarding the interpretability and reliability of their reasoning processes. While models like DeepSeek R1-which incorporates explicit reasoning steps-show promise in enhancing performance and explainability, their alignment with domain-specific expert reasoning remains understudied.Methods This paper evaluates the medical reasoning capabilities of DeepSeek R1, comparing its outputs to the reasoning patterns of medical domain experts.Results Through qualitative and quantitative analyses of 100 diverse clinical cases from the MedQA dataset, we demonstrate that DeepSeek R1 achieves 93% diagnostic accuracy and shows patterns of medical reasoning. Analysis of the seven error cases revealed several recurring errors: anchoring bias, difficulty integrating conflicting data, limited consideration of alternative diagnoses, overthinking, incomplete knowledge, and prioritizing definitive treatment over crucial intermediate steps.Discussion These findings highlight areas for improvement in LLM reasoning for medical applications. Notably the length of reasoning was important with longer responses having a higher probability for error. The marked disparity in reasoning length suggests that extended explanations may signal uncertainty or reflect attempts to rationalize incorrect conclusions. Shorter responses (e.g., under 5,000 characters) were strongly associated with accuracy, providing a practical threshold for assessing confidence in model-generated answers. Beyond observed reasoning errors, the LLM demonstrated sound clinical judgment by systematically evaluating patient information, forming a differential diagnosis, and selecting appropriate treatment based on established guidelines, drug efficacy, resistance patterns, and patient-specific factors. This ability to integrate complex information and apply clinical knowledge highlights the potential of LLMs for supporting medical decision-making through artificial medical reasoning.

Place, publisher, year, edition, pages
Frontiers Media SA , 2025. Vol. 8, article id 1616145
Keywords [en]
LLM, medical reasoning, DeepSeek R1, AI in medicine, reasoning models, medical benchmarking
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-371001DOI: 10.3389/frai.2025.1616145ISI: 001521129800001PubMedID: 40607450Scopus ID: 2-s2.0-105009608977OAI: oai:DiVA.org:kth-371001DiVA, id: diva2:2003347
Note

QC 20251003

Available from: 2025-10-03 Created: 2025-10-03 Last updated: 2025-10-17Bibliographically approved
In thesis
1. Evaluation of Artificial Intelligence in the Medical Domain: Speech, Language and Applications
Open this publication in new window or tab >>Evaluation of Artificial Intelligence in the Medical Domain: Speech, Language and Applications
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This doctoral thesis investigates the potential of advanced speech and languagetechnologies, driven by deep learning, to improve clinical diagnostics and patientcare, primarily within the Swedish healthcare context. The research encompasseseight key papers, which are presented across three main sections:(1) Data Capture and Machine Learning for Speech: This section explores the use ofmultimodal data and advanced speech processing techniques for clinical applications.It includes research on utilizing multimodal data capture (speech, gaze, and digitalpen input) from clinical interviews to identify potential digital biomarkers for theearly detection and differentiation of dementia (Paper A). It also develops anautomated deep learning system to evaluate the oral diadochokinesis test for motorspeech disorders, which demonstrates higher accuracy than human raters andproposes a human-in-the-loop clinical interface (Paper B). Furthermore, this sectionevaluates the performance of Automatic Speech Recognition (ASR) systems,comparing word error rates between native (L1) and non-native (L2) Swedishspeakers (Paper C), and investigates data augmentation techniques to improve ASRaccuracy for individuals with aphasia, demonstrating a path towards more inclusivetechnology (Paper D).(2) Evaluation of LLMs in the Medical Domain: This section focuses on establishingrobust methods for assessing Large Language Models (LLMs) within a medicalcontext. It details the development of a specialized Swedish Medical LLM Benchmark,comprising over 2600 questions across various medical domains, designed to assessLLM performance in a clinically relevant, language-specific manner (Paper E).Additionally, the medical reasoning capabilities of LLMs, such as DeepSeek R1, arerigorously assessed, focusing on their capacity for general medical diagnosticreasoning (Paper F).(3) Application and Best Practice for Working with AI in Healthcare: This sectionaddresses the practical, ethical, and user experience (UX) considerations forvimplementing AI in healthcare. It proposes a novel user interface paradigm throughan AI-powered journaling application designed for personal health management,illustrating a low-risk, user-centric approach to AI integration (Paper G).Complementing this, it develops harm reduction strategies for the thoughtful use ofLLMs in the medical domain, providing perspectives for both patients and cliniciansto maximize utility while mitigating risks, thereby establishing best practices forresponsible AI engagement (Paper H).Collectively, this work advances the field by providing new tools and methodologiesfor early disease detection using speech and multimodal data, establishing robustevaluation methods for ASR and LLMs in the medical domain, and offering pathwaysand frameworks for responsible, user-centered, and effective AI implementation inhealthcare.

Abstract [sv]

Denna doktorsavhandling undersöker potentialen hos avancerade tal- ochspråkteknologier, drivna av djupinlärning, för att förbättra klinisk diagnostik ochpatientvård, främst inom svensk hälso- och sjukvård. Forskningen omfattar åttacentrala artiklar, vilka presenteras inom tre huvudsakliga avsnitt:(1) Datainsamling och maskininlärning för tal: Detta avsnitt utforskar användningenav multimodal data och avancerade talbearbetningstekniker för kliniskatillämpningar. Det inkluderar forskning om användning av multimodaldatainsamling från kliniska intervjuer för att identifiera digitala biomarkörer fördemens (Artikel A). Vidare utvecklas ett automatiserat system med djupinlärning föratt utvärdera oral diadochokinesis-testet vid motoriska talrubbningar, vilket visarhögre noggrannhet än mänskliga bedömare och föreslår ett kliniskt gränssnitt medmänniska-i-loopen (Artikel B). Avsnittet utvärderar även prestandan hos system förautomatisk taligenkänning (ASR) genom att jämföra felkvoter mellan talare medsvenska som modersmål respektive andraspråk (Artikel C) och undersökerdataaugmenteringstekniker för att förbättra ASR-noggrannheten för personer medafasi (Artikel D).(2) Utvärdering av stora språkmodeller (LLM:er) inom det medicinska området:Detta avsnitt fokuserar på att etablera robusta metoder för att bedöma storaspråkmodeller (LLM:er) i en medicinsk kontext. Det beskriver utvecklingen av ettspecialiserat svenskt medicinskt LLM-benchmark, bestående av över 2600 frågorinom olika medicinska domäner, avsett att utvärdera LLM:ers prestanda på ettkliniskt relevant och språkspecifikt sätt (Artikel E). Därtill bedöms den medicinskaresonemangsförmågan hos LLM:er, såsom DeepSeek R1, noggrant, med fokus påderas kapacitet för generell medicinsk diagnostiskt resonerande (Artikel F).(3) Applikationer och bästa praxis för AI inom hälso- och sjukvård: Detta avsnittbehandlar praktiska, etiska och användarupplevelsemässiga (UX) överväganden vidimplementering av AI inom hälso- och sjukvården. Ett nyttviianvändargränssnittsparadigm föreslås genom en AI-driven applikation för att föra enpersonlig hälsodagbok. Den är utformad för personlig hälsohantering och illustreraren lågrisk, användarcentrerad strategi för AI-integration (Artikel G). Somkomplement utvecklas strategier för harm reduction för genomtänkt användning avLLM:er inom det medicinska området. Dessa strategier erbjuder perspektiv för bådepatienter och kliniker för att maximera nyttan och samtidigt minimera riskerna, ochetablerar därmed bästa praxis för ansvarsfullt AI-engagemang (Artikel H).Sammantaget bidrar detta arbete till forskningsfältet genom att tillhandahålla nyaverktyg och metoder för tidig sjukdomsdetektion med hjälp av tal- och multimodaldata, etablera robusta utvärderingsmetoder för ASR och LLM:er inom det medicinskaområdet, samt erbjuda vägledning och ramverk för en ansvarsfull, användarcentreradoch effektiv implementering av AI inom hälso- och sjukvården.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2025. p. xxi, 82
Series
TRITA-EECS-AVL ; 2025:83
Keywords
Large Language Models (LLMs), Automatic Speech Recognition (ASR), Neurodegenerative Disorders, Swedish Language, Clinical Diagnostics, AI Ethics, Medical Reasoning, Multimodal Data, Tal- och språkteknologi, maskininlärning, djupinlärning, automatisk taligenkänning (ASR), stora språkmodeller (LLM), medicinsk diagnostik, digitala biomarkörer, afasi, demens, hälso- och sjukvård, användarupplevelse (UX), harm reduction, AI-integration
National Category
Artificial Intelligence
Research subject
Speech and Music Communication
Identifiers
urn:nbn:se:kth:diva-371738 (URN)978-91-8106-404-9 (ISBN)
Public defence
2025-12-12, https://kth-se.zoom.us/j/69936124469, Kollegiesalen, Brinellvägen 8, Stockholm, 13:00 (English)
Opponent
Supervisors
Note

QC 20251022

Available from: 2025-10-22 Created: 2025-10-17 Last updated: 2025-11-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Moell, Birger

Search in DiVA

By author/editor
Moell, Birger
By organisation
Speech, Music and Hearing, TMH
In the same journal
Frontiers in Artificial Intelligence
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 155 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf