Yannick Laurent Tchenadoyo BAYALA

Dr. Yannick Laurent Tchenadoyo BAYALA

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 May 2025 in BMC Rheumatology
Verified
Journal Article
Open access
PDF file
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
WZWendlassida Joelle Stéphanie Zabsonré/Tiendrebeogo
Wendlassida Joelle Stéphanie Zabsonré/Tiendrebeogo
DODieu-Donné Ouedraogo
Dieu-Donné Ouedraogo
FKFulgence Kaboré
Fulgence Kaboré
CSCharles Sougué
Charles Sougué
YZYamyellé Enselme Zongo
Yamyellé Enselme Zongo
Artificial intelligence (AI) tools, particularly Large Language Models (LLMs), are revolutionizing medical practice, including rheumatology. However, their diagnostic capabilities remain underexplored in the African context. To assess the diagnostic accuracy of ChatGPT-4, Gemini, Copilot, and Claude AI in rheumatology within an African population. This was a cross-sectional analytical study with retrospective data collection, conducted at the Rheumatology Department of Bogodogo University Hospital Center (Burkina Faso) from January 1 to June 30, 2024. Standardized clinical and paraclinical data from 103 patients were submitted to the four AI models. The diagnoses proposed by the AIs were compared to expert-confirmed diagnoses established by a panel of senior rheumatologists. Diagnostic accuracy, sensitivity, specificity, and predictive values were calculated for each AI model. Among the patients enrolled in the study period, infectious diseases constituted the most common diagnostic category, representing 47.57% (n = 49). ChatGPT-4 achieved the highest diagnostic accuracy (86.41%), followed by Claude AI (85.44%), Copilot (75.73%), and Gemini (71.84%). The inter-model agreement was moderate, with Cohen’s kappa coefficients ranging from 0.43 to 0.59. ChatGPT-4 and Claude AI demonstrated high sensitivity (> 90%) for most conditions but had lower performance for neoplastic diseases (sensitivity < 67%). Patients under 50 years old had a significantly higher probability of receiving a correct diagnosis with Copilot (OR = 3.36; 95% CI [1.16–9.71]; p = 0.025). LLMs, particularly ChatGPT-4 and Claude AI, show high diagnostic capabilities in rheumatology, despite some limitations in specific disease categories. Not applicable.

9 December 2025 in BMC Cardiovascular Disorders
Verified
Journal Article
Open access
PDF file
MNMartin Wendlassida NACANABO
Martin Wendlassida NACANABO
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
ASAndré Arthur Taryètba Seghda
André Arthur Taryètba Seghda
ATAnna Tall/Thiam
Anna Tall/Thiam
AYAristide Relwendé Yaméogo
Aristide Relwendé Yaméogo
PZPatrice Zabsonré
Patrice Zabsonré
Artificial intelligence, particularly Large Language Models (LLMs), has revolutionized the field of medicine. Their ability to understand and answer medica

29 January 2025 in Osteoarthritis and Cartilage Open
Verified
Journal Article
Open access
CSCharles Sougué
Charles Sougué
MDMalick Diallo
Malick Diallo
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
ITIsmaël Ayouba Tinni
Ismaël Ayouba Tinni
FKFulgence Kaboré
Fulgence Kaboré
DODieu-Donné Ouedraogo
Dieu-Donné Ouedraogo
Our objective was to study the clinical phenotypes of knee osteoarthritis in rheumatology in a black sub-Saharan African population. This study took place from October 1, 2022, to September 30, 2023, in the rheumatology department. It involved adult patients with knee osteoarthritis. The researchers used K-means clustering analysis to identify different phenotypes and logistic regression to determine associated factors. A total of 321 patients were included in the study. The mean age was 58.7 years (ranging from 21 to 92 years), with a sex ratio of 0.23 (M/F). The study identified five clinical phenotypes through clustering: 152 patients (47.3 ​%) exhibited the "osteoporotic" phenotype, 113 patients (35.2 ​%) exhibited the "metabolic" phenotype, 17 patients (5.3 ​%) exhibited the "genetic" phenotype, 24 patients (7.4 ​%) exhibited the "biomechanical" phenotype, and 15 patients (4.6 ​%) exhibited the "post-traumatic" phenotype. The "osteoporotic" phenotype was significantly more frequent in patients aged 60 years or older (OR ​= ​1.13 [1.10; 1.16], p ​< ​0.0001) and in women (OR ​= ​2.44 [1.20; 4.94], p ​< ​0.0001). On the other hand, the "post-traumatic" phenotype was significantly more frequent in patients younger than 60 years (OR ​= ​1.93 [1.91; 1.96], p ​< ​0.0001) and in those with tibiofemoral osteoarthritis (OR ​= ​0.44 [0.21; 0.94], p ​= ​0.034). The osteoporotic and metabolic phenotypes were the most frequently observed. The osteoporotic phenotype was more common in women and patients over 60 years while the post-traumatic phenotype was more prevalent in tibiofemoral osteoarthritis under 60 years.

24 October 2024 in Clinical Case Reports
Verified
Journal Article
Open access
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
IOIssa Ouedraogo
Issa Ouedraogo
HMHervé Eric Mourfou
Hervé Eric Mourfou
BSBakoubassé Aïssata Son
Bakoubassé Aïssata Son
WYWendyam Nadège Yameogo
Wendyam Nadège Yameogo
DODieu‐Donné Ouedraogo
Dieu‐Donné Ouedraogo
Key Clinical Message: Differentiating Adult‐Onset Still's Disease (AOSD) from lymphoma is challenging. A 23‐year‐old female presented with polyarthralgia, fever, rash, lymphadenopathy, and abnormal labs. She met AOSD criteria and was diagnosed with non‐Hodgkin lymphoma. Treatment led to improvement. The differentiation between Adult‐onset Still's Disease (AOSD) and lymphoma remains challenging in our context. The Faustrel score facilitates the simultaneous diagnosis of these conditions. A 23‐year‐old woman presented with chronic polyarthralgia in a febrile context. A physical examination revealed peripheral joint syndrome, a maculopapular rash on the trunk, and peripheral lymphadenopathy. Laboratory tests showed neutrophils leukocytosis, hyperferritinemia, and a glycosylated ferritin fraction of 12%. A lymph node biopsy revealed a malignant non‐Hodgkin lymphoma, and the patient met the diagnostic criteria for AOSD according to Faustrel. She received corticosteroid therapy and four courses of Rituximab. After 6 months, clinical and biological improvements were noted. It is essential to consider the possibility of an association between atypical clinical presentations of lymphoma and AOSD.

29 April 2026 in Health Informatics Journal
Verified
Journal Article
Open access
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
FKFulgence Kaboré
Fulgence Kaboré
CSCharles Sougué
Charles Sougué
AOAboubakar Ouédraogo
Aboubakar Ouédraogo
YZYamyellé Enselme Zongo
Yamyellé Enselme Zongo
DODieu-Donné Ouedraogo
Dieu-Donné Ouedraogo
Background: Large language models (LLMs) have demonstrated promising capabilities in medical diagnostic reasoning, yet their performance in specialized clinical domains such as rheumatology remains incompletely characterized. While diagnostic accuracy has been evaluated, critical dimensions including calibration, reasoning quality, and temporal stability have not been systematically assessed across contemporary models. Objectives: This study aimed to comprehensively evaluate and compare the diagnostic accuracy, certainty expression, reasoning quality, and hallucination rates of four state-of-the-art LLMs ChatGPT-4, Claude 3.5, DeepSeek-V3, and Gemini 1.5 Pro in complex rheumatologic case scenarios. Design: A cross-sectional, analytical, and comparative study was conducted following STARD and TRIPOD guidelines, adapted for LLM evaluation. Nine complex rheumatologic cases from published case reports were evaluated at three time points (Days 1, 5, and 10) between July 1 and September 18,2025. Methods: Standardized clinical vignettes were submitted to each LLM under controlled experimental conditions. Two blinded senior rheumatologists independently assessed diagnostic accuracy, reasoning quality across five analytical dimensions using Likert scales, and hallucination frequency. Certainty expression and temporal stability were quantified using intraclass correlation coefficients. Correlation analyses examined relationships between reasoning quality and confidence expression. Results: All models achieved near-perfect diagnostic accuracy, with ChatGPT, Claude and Gemini correctly identifying the primary diagnosis in 100% of cases and DeepSeek in 88.9%. However, Spearman correlation analysis revealed uniformly weak and non-significant associations between reasoning quality and expressed certainty across all models (ρ range: -0.156 to 0.215, all p>0.05), indicating fundamental miscalibration. ChatGPT demonstrated the highest reasoning score (3.89±0.23) and lowest hallucination rate (7.4%), while Gemini showed the highest hallucination frequency (18.5%). Temporal stability was excellent for ChatGPT (ICC=0.84) and good for DeepSeek (ICC=0.79). Conclusion: Despite exceptional diagnostic accuracy, current LLMs exhibit critical limitations in confidence calibration and variable hallucination rates, representing significant barriers to safe clinical deployment in rheumatology.

18 July 2025 in Health Science Reports
Verified
Journal Article
Open access
ITIsmael Ayouba Tinni
Ismael Ayouba Tinni
WYWendyam Nadège Yameogo
Wendyam Nadège Yameogo
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
BSBakoubassé Aissata Son
Bakoubassé Aissata Son
IOIssa Ouedraogo
Issa Ouedraogo
DODieu‐Doné Ouedraogo
Dieu‐Doné Ouedraogo
Background and Aims: Rheumatoid arthritis is still poorly understood by medical personnel in sub‐Saharan Africa, resulting in significant diagnostic delays. The aim of this study was to assess the knowledge, attitudes and practices of general practitioners and nonrheumatologist specialists regarding rheumatoid arthritis. Methods: This was a descriptive and analytical cross‐sectional study from January 22 to February 22, 2024. Data were collected using an online self‐administered questionnaire from general practitioners and nonrheumatology specialists practicing in Burkina Faso. The association between variables was tested using the chi‐squared test. The significance level was set at 5%. Results: One hundred and forty‐five physicians completed the questionnaire. The mean age of the participants was 32.01 ± 4.066 [25; 47] years. The proportion of men was 62.10% (90). The proportion of general practitioners was 61.40% (89). The mean knowledge score was 12.51 ± 2.741 [4; 18] out of 20. Of the 145 physicians who completed the questionnaire, 22.76% (33) were confronted with rheumatoid arthritis in their practice. The mean attitude score was 9.64 ± 3.389 (3 − 16) out of 20. The mean practice score was 14.76 ± 2.292 (9 − 19) out of 20. Physicians with average/good knowledge had no idea about biotherapy in 72.90% (62) of the cases, compared to 27.10% (23) who had an idea about biotherapy ( p = 0.001). Physicians with average/good knowledge had unfavorable attitudes in 58.30% (14) of cases compared to 41.70% (10) who had favorable attitudes ( p = 0.42). Physicians with average/good knowledge had inadequate practices in 29.20% (7) of cases versus 70.80% (17) with adequate practices ( p = 0.019). Conclusion: The majority of participants had an acceptable level of knowledge, attitude and practice regarding rheumatoid arthritis.