Aboubakar Ouédraogo

Dr. Aboubakar Ouédraogo

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.

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.

16 September 2024 in Rheumatology
Verified
Journal Article
Open access
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
ITIsmael Ayouba Tinni
Ismael Ayouba Tinni
FKFulgence Kabore
Fulgence Kabore
AOAboubakar Ouédraogo
Aboubakar Ouédraogo
EZEnselme Yamyéllé Zongo
Enselme Yamyéllé Zongo
DODieu-Donné Ouedraogo
Dieu-Donné Ouedraogo
Introduction: Non-traumatic spinal cord injury (NTSCI) represents a medical-surgical emergency. In Burkina Faso, limited data exist on the etiological profiles of this syndrome in rheumatology. This study aimed to describe the etiological profile of NTSCI in the Rheumatology Department of the University Hospital Center of Bogodogo (CHU-B).Material and methods: This was a cross-sectional, retrospective study with descriptive and analyti­cal aims, conducted from March 1, 2017, to December 31, 2023, in the Rheumatology Department of CHU-B. Patients diagnosed with non-traumatic spinal cord compression syndrome during hospitalization were included.Results: The frequency in the Rheumatology Department of NTSCI was 2.94%, accounting for 104 patients. There were 68 men (65.38%), with a sex ratio of 1.88. The average age of the population was 57.91 years. All patients experienced back pain, with a lumbar location in 77 patients (74.04%). The average duration of the motor deficit was 2.97 months. A total of 3,532 patients were admitted to the conventional hospitalization unit of the Rheumatology Department at the CHU-B from March 1, 2017, to December 31, 2023. Among these, 104 patients had NTSCI, yielding a frequency of 2.94%. Spinal MRI was performed in 58 patients (55.77%), and the compression was extradural in 76.92% of cases (n = 80). The etiologies identified were Pott’s disease in 32 patients (30.77%), followed by spinal metastases in 22 patients (21.15%). Twenty-nine patients (27.89%) experienced complications related to prolonged bed rest. No factor was significantly associated with the reco­very of the motor deficit.Conclusions: Non-traumatic spinal cord injury is relatively rare in rheumatological practice in Ouagadougou. The etiology is predominantly Pott’s disease, which confirms the geographical distribution of NTSCI causes.

14 August 2026 in BMC Sports Science, Medicine and Rehabilitation
Verified
Journal Article
Open access
PDF file
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
ACAbdoul Rahamane Cissé
Abdoul Rahamane Cissé
TLTelarpoa Isabelle Lompo
Telarpoa Isabelle Lompo
FNFlorent Brice Nikiema
Florent Brice Nikiema
YTYirozounlomian Tiaho
Yirozounlomian Tiaho
DODieu-Donné Ouedraogo
Dieu-Donné Ouedraogo
Adapted physical activity (APA) is a cornerstone of the management of musculoskeletal and rheumatological conditions, yet its individualized prescription r

7 November 2025 in Mycobacteria
Verified
Journal Article
Open access
PDF file
YBYannick Laurent Tchenadoyo BAYALA
Yannick Laurent Tchenadoyo BAYALA
FKFulgence Kaboré
Fulgence Kaboré
CSCharles Sougué
Charles Sougué
CSCamille Sompougdou
Camille Sompougdou
AOAboubakar Ouédraogo
Aboubakar Ouédraogo
DODieu-Donné Ouédraogo
Dieu-Donné Ouédraogo
Sternoclavicular joint tuberculosis representing less than 1% of osteoarticular tuberculous cases. Due to its rarity, this tuberculous localization is often unrecognized and underdiagnosed, leading to delayed management and potentially severe complications. This study aimed to systematically review of sternoclavicular tuberculosis cases reported worldwide. This systematic review was conducted according PRISMA guidelines. Electronic searches were conducted in databases including Medline via PubMed, Embase, Scopus, CINAHL, Web of Science, Google Scholar, DOAJ, and regional databases up to March 2025 in English language. Studies reporting confirmed sternoclavicular tuberculosis cases with clinical, diagnostic, therapeutic, or evolutionary data were included. Two reviewers independently screened articles, completed the data extraction and assessment of risk of bias. Due to significant heterogeneity and paucity of data, we were unable to carry out a meta-analysis. The Joanna Briggs Institute (JBI) critical appraisal tools were used for quality assessment. The protocol for this review was registered on the International Prospective Register of Systematic Reviews. We identified 495 records and a total of 48 studies documenting 117 patients were included, published between 1955 and 2024, with 77.08% (n = 37) published after 2010. Case reports dominated with 70.83% (n = 34), followed by case series 22.91% (n = 11) and observational studies 6.25% (n = 3). The mean patient age was 42.4 years (SD 17.16) with male predominance 63.8% (n = 74). India accounted for 77.8% (n = 91) of cases. Only 34.2% (n = 40) of patients had identifiable risk factors, with HIV and diabetes being most common at 5.1% (n = 6) each. Clinical presentation included localized pain 79.5% (n = 93), swelling 88.9% (n = 104), and mean symptom duration of 5.17 months before diagnosis. Right-sided involvement predominated with 60.7% (n = 65). Associated extrapulmonary tuberculosis was present in 22.2% (n = 26) of cases. Treatment duration averaged 12.59 months, with standard 7–12-month treatment in 41.5% (n = 34) and prolonged 13–18-month treatment in 40.2% (n = 33). Surgical intervention was required in 20.5% (n = 24) of cases. Clinical evolution was favorable in 55.5% (n = 65) of documented cases. Sternoclavicular tuberculosis remains a rare but likely underdiagnosed condition characterized by atypical presentation leading to diagnostic delays. This review highlights the need for increased clinical suspicion, standardized diagnostic approaches, and prospective multicenter studies to establish evidence-based recommendations for optimal treatment duration and surgical indications.

11 June 2026 in Osteoarthritis and Cartilage Open
Verified
Journal Article
Open access
FKFulgence Kaboré
Fulgence Kaboré
AAAbdoul Aziz
Abdoul Aziz
ITIsmael Ayouba Tinni
Ismael Ayouba Tinni
CSCharles Sougué
Charles Sougué
CSCamille Sompougdou
Camille Sompougdou
DODieu-Donné Ouédraogo
Dieu-Donné Ouédraogo
To determine the frequency and factors associated with neuropathic pain in patients with knee osteoarthritis seen during rheumatology consultations. This was a descriptive and analytical cross-sectional study of patients with knee osteoarthritis who met the ACR criteria and who were seen in rheumatology consultations at a referral university hospital. A DN4 score greater than or equal to 4 was used to classify the pain as like neuropathic. Multivariable logistic regression analysis was used to determine adjusted ORs and 95% CI. Three hundred and twenty-five patients with knee osteoarthritis were included in the study. The mean age of the patients was 57.85 ± 11.89 years. Neuropathic-like pain (DN4 ≥4) was identified in 32% of participants. Among DN4-positive individuals, the mean DN4 score was 6.51 ± 1.60 (range 4–10). The mean global WOMAC score was 30.98 ± 10.98. The mean score for pain under load according to the visual analog scale was 3.35 ± 1.376. After multivariable analysis, the associated factors with neuropathic-like pain were a history of knee trauma (OR = 4.525; 95%CI [1.497–13.678]; p = 0.007). Psychological history (OR = 9.941; 95%CI [3.066–32.235]; p < 0.001). Kellgren–Lawrence grades 3 and 4 (OR = 7.599; 95%CI [2.372–24.432]; p = 0.001) and WOMAC global score (OR = 1.093; 95%CI [1.053–1.134]; p < 0.001). A significant proportion of patients suffering from osteoarthritis of the knee experienced neuropathic-like pain, requiring the implementation of prevention and treatment strategies.