Aboubakar Ouedraogo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Aboubakar Ouedraogo has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Fulgence Kaboré
Department of Rheumatology, Bogodogo University Hospital Center, Ouagadougou, Burkina Faso
7 shared publications - Wendlassida Joelle Stéphanie Zabsonré/Tiendrebeogo
Department of Rheumatology, Bogodogo University Hospital Center, Ouagadougou, Burkina Faso
7 shared publications - Dieu-Donné Ouédraogo
Department of Rheumatology, Bogodogo University Hospital Center, Ouagadougou, Burkina Faso
6 shared publications - Yamyellé Enselme Zongo
Bogodogo University Hospital Center, Ouagadougou, Burkina Faso
6 shared publications - Yannick Laurent Tchenadoyo Bayala
Department of Rheumatology, Bogodogo University Hospital Center, Ouagadougou, Burkina Faso
6 shared publications - Charles Sougué
Sourou Sanou University Hospital Center
4 shared publications
Latest Publications
- Open Access
- 11 September 2026
- Published by Springer Nature in BMC Rheumatology
Ultrasound reference values for trochlear cartilage in healthy black African subjects: a study of a cohort of 506 participants
- 11 September 2026
- Published by Springer Nature in BMC Rheumatology
Open AccessUltrasound reference values for trochlear cartilage in healthy black African subjects: a study of a cohort of 506 participants
- Open Access
- 14 August 2026
- Published by Springer Nature in BMC Sports Science, Medicine and Rehabilitation
- Vol. 18 (1)
AI-assisted exercise prescription in rheumatology: a comparative evaluation of three large language models for personalized APA prescription
- 14 August 2026
- Published by Springer Nature in BMC Sports Science, Medicine and Rehabilitation
- Vol. 18 (1)
Open AccessAI-assisted exercise prescription in rheumatology: a comparative evaluation of three large language models for personalized APA prescription
- Open Access
- 20 July 2026
- Published by Springer Nature in European Review of Aging and Physical Activity
- Vol. 23 (1)
Quality of AI-generated exercise awareness messages for older adults aligned with the ICFSR consensus: a comparative study of three LLMs
Background: Large Language Models (LLMs) are emerging as potential tools for health communication and patient education. However, their ability to translate complex medical guidelines into accessible, safe, and accurate messages for older adults remains insufficiently evaluated. To assess the capacity of ChatGPT-4, Claude AI, and Deepseek to generate exercise awareness messages for older adults, aligned with international expert consensus. Materials and methods: This was a cross-sectional observational study conducted between April and August 2025. Using the ICFSR 2021 Global Consensus on optimal exercise recommendations as the gold standard, we evaluated messages generated by three LLMs for 13 common chronic conditions in older adults. A standardized prompt was used to generate messages addressing exercise prescription considerations, disease progression, and recommended modalities. Two independent expert evaluators; a geriatrician and a sports medicine physician assessed five dimensions using a 5-point Likert scale; accuracy, clarity, safety, behavioral relevance, and absence of fabrication. Readability was measured using Flesch-Kincaid Grade Level (FKGL), Gunning Fog Index (GFI), and Simple Measure of Gobbledygook (SMOG). Inter-rater agreement was assessed using intraclass correlation coefficient (ICC). Results: Claude achieved the overall scores from both evaluators at 4.63 ± 0.55 and 4.60 ± 0.55, followed by ChatGPT-4 at 4.55 ± 0.50 and 4.48 ± 0.53 and Deepseek at 4.15 ± 0.87 and 4.17 ± 0.86. Inter-rater agreement was moderate was 0.668. Claude demonstrated accuracy scores at 4.58 ± 0.64, while ChatGPT-4 excelled in clarity with 5 ± 0. All models achieved perfect scores for absence of fabrication (5 ± 0). Readability indices revealed high complexity across all LLMs, with median FKGL values ranging from 10.84 to 10.93, corresponding to 10th-11th grade reading level, exceeding recommended levels for older populations. A significant correlation was found between Claude’s accuracy scores and FKGL ( r = 0.599, p = 0.030). Conclusion: LLMs, particularly Claude, ChatGPT-4 and Deepseek demonstrate strong potential for generating accurate, safe, and hallucination-free exercise awareness messages for older adults. However, readability remains above recommended levels, requiring optimization.
- 20 July 2026
- Published by Springer Nature in European Review of Aging and Physical Activity
- Vol. 23 (1)
Open AccessQuality of AI-generated exercise awareness messages for older adults aligned with the ICFSR consensus: a comparative study of three LLMs
Background: Large Language Models (LLMs) are emerging as potential tools for health communication and patient education. However, their ability to translate complex medical guidelines into accessible, safe, and accurate messages for older adults remains insufficiently evaluated. To assess the capacity of ChatGPT-4, Claude AI, and Deepseek to generate exercise awareness messages for older adults, aligned with international expert consensus. Materials and methods: This was a cross-sectional observational study conducted between April and August 2025. Using the ICFSR 2021 Global Consensus on optimal exercise recommendations as the gold standard, we evaluated messages generated by three LLMs for 13 common chronic conditions in older adults. A standardized prompt was used to generate messages addressing exercise prescription considerations, disease progression, and recommended modalities. Two independent expert evaluators; a geriatrician and a sports medicine physician assessed five dimensions using a 5-point Likert scale; accuracy, clarity, safety, behavioral relevance, and absence of fabrication. Readability was measured using Flesch-Kincaid Grade Level (FKGL), Gunning Fog Index (GFI), and Simple Measure of Gobbledygook (SMOG). Inter-rater agreement was assessed using intraclass correlation coefficient (ICC). Results: Claude achieved the overall scores from both evaluators at 4.63 ± 0.55 and 4.60 ± 0.55, followed by ChatGPT-4 at 4.55 ± 0.50 and 4.48 ± 0.53 and Deepseek at 4.15 ± 0.87 and 4.17 ± 0.86. Inter-rater agreement was moderate was 0.668. Claude demonstrated accuracy scores at 4.58 ± 0.64, while ChatGPT-4 excelled in clarity with 5 ± 0. All models achieved perfect scores for absence of fabrication (5 ± 0). Readability indices revealed high complexity across all LLMs, with median FKGL values ranging from 10.84 to 10.93, corresponding to 10th-11th grade reading level, exceeding recommended levels for older populations. A significant correlation was found between Claude’s accuracy scores and FKGL ( r = 0.599, p = 0.030). Conclusion: LLMs, particularly Claude, ChatGPT-4 and Deepseek demonstrate strong potential for generating accurate, safe, and hallucination-free exercise awareness messages for older adults. However, readability remains above recommended levels, requiring optimization.
- Open Access
- 11 June 2026
- Published by Elsevier in Osteoarthritis and Cartilage Open
- Vol. 8 (3)
Frequency and factors associated with neuropathic pain in patients with knee osteoarthritis
- 11 June 2026
- Published by Elsevier in Osteoarthritis and Cartilage Open
- Vol. 8 (3)
Open AccessFrequency and factors associated with neuropathic pain in patients with knee osteoarthritis
- Open Access
- 29 April 2026
- Published by SAGE Publications in Health Informatics Journal
- Vol. 32 (2)
Assessing the clinical reasoning of large language models on complex rheumatology cases: A multidimensional evaluation of four artificial intelligence
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.
- 29 April 2026
- Published by SAGE Publications in Health Informatics Journal
- Vol. 32 (2)
Open AccessAssessing the clinical reasoning of large language models on complex rheumatology cases: A multidimensional evaluation of four artificial intelligence
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.
- Open Access
- 7 November 2025
- Published by Springer Nature in Mycobacteria
- Vol. 1 (1) , 1-13
Tuberculosis of the sternoclavicular joint: a systematic review of the literature
- 7 November 2025
- Published by Springer Nature in Mycobacteria
- Vol. 1 (1) , 1-13
Open AccessTuberculosis of the sternoclavicular joint: a systematic review of the literature
- Open Access
- 16 May 2025
- Published by Springer Nature in BMC Rheumatology
- Vol. 9 (1) , 1-12
Performance of the Large Language Models in African rheumatology: a diagnostic test accuracy study of ChatGPT-4, Gemini, Copilot, and Claude artificial intelligence
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.
- 16 May 2025
- Published by Springer Nature in BMC Rheumatology
- Vol. 9 (1) , 1-12
Open AccessPerformance of the Large Language Models in African rheumatology: a diagnostic test accuracy study of ChatGPT-4, Gemini, Copilot, and Claude artificial intelligence
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.
- Open Access
- 16 September 2024
- Published by Termedia Sp. z.o.o. in Rheumatology
- Vol. 62 (4) , 259-265
Non-spinal cord injury – etiological profile and associated factors: single rheumatological center experience
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.
- 16 September 2024
- Published by Termedia Sp. z.o.o. in Rheumatology
- Vol. 62 (4) , 259-265
Open AccessNon-spinal cord injury – etiological profile and associated factors: single rheumatological center experience
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.
- Open Access
- 1 January 2024
- Published by Pan African Medical Journal in Pan African Medical Journal
- Vol. 47 (12) , 12
Polyarthrite rhumatoïde: la rémission sans biothérapie? L’expérience du Burkina Faso (Afrique de l’Ouest)
INTRODUCTION: l'objectif de cette étude était d'évaluer la réponse thérapeutique des patients traités par les antirhumatismaux modificateurs de la maladie (ARMM) pour une polyarthrite rhumatoïde (PR). MÉTHODES transversale monocentrique descriptive et analytique menée au Burkina Faso de janvier 2019 à décembre 2021 chez des patients atteints d´une PR répondant aux critères American Rheumatism Association/European League Against Rheumatism. La réponse thérapeutique a été évaluée selon les critères de European League Against Rheumatism, le Clinical Disease Activity Index et the Simplified Disease Activity Index après au moins six mois de traitement. RÉSULTATS: cent trois patients dont 85 femmes ont été inclus. La moyenne d´âge des patients était de 50,14 ans ±15,04 ans. Quatre-vingt-sept patients (84,47%) étaient ACPA positif et 50 patients (48,54%) avaient une atteinte radiologique à l´inclusion. Le DAS28-CRP, le CDAI et le SDAI moyen étaient respectivement de 5,17; 32,16 et 35,48 à l´inclusion contre 2,53; 7,83 et 8,76 après au moins six mois de traitement (p
- 1 January 2024
- Published by Pan African Medical Journal in Pan African Medical Journal
- Vol. 47 (12) , 12
Open AccessPolyarthrite rhumatoïde: la rémission sans biothérapie? L’expérience du Burkina Faso (Afrique de l’Ouest)
INTRODUCTION: l'objectif de cette étude était d'évaluer la réponse thérapeutique des patients traités par les antirhumatismaux modificateurs de la maladie (ARMM) pour une polyarthrite rhumatoïde (PR). MÉTHODES transversale monocentrique descriptive et analytique menée au Burkina Faso de janvier 2019 à décembre 2021 chez des patients atteints d´une PR répondant aux critères American Rheumatism Association/European League Against Rheumatism. La réponse thérapeutique a été évaluée selon les critères de European League Against Rheumatism, le Clinical Disease Activity Index et the Simplified Disease Activity Index après au moins six mois de traitement. RÉSULTATS: cent trois patients dont 85 femmes ont été inclus. La moyenne d´âge des patients était de 50,14 ans ±15,04 ans. Quatre-vingt-sept patients (84,47%) étaient ACPA positif et 50 patients (48,54%) avaient une atteinte radiologique à l´inclusion. Le DAS28-CRP, le CDAI et le SDAI moyen étaient respectivement de 5,17; 32,16 et 35,48 à l´inclusion contre 2,53; 7,83 et 8,76 après au moins six mois de traitement (p