Loading

Annals of Vascular Medicine and Research

Evaluation of The Diagnostic Capabilities of Artficial Intelligence (CHATGPT-4) in The Cardiology Department of Bogodogo University Hospital, Burkina Faso

Short Communication | Open Access | Volume 12 | Issue 1
Article DOI :

  • 1. Department of Cardiology, Bogodogo University Hospital Center, Burkina Faso
  • 2. Department of Cardiology, Yalgado Ouedraogo University Hospital Center, Burkina Faso
  • 3. Department of Rheumatology, Bogodogo University Hospital Center, Burkina Faso
+ Show More - Show Less
Corresponding Authors
Wendlassida Martin NACANABO, Department of Cardiology, Bogodogo University Hospital Center, Burkina Faso
Abstract

Introduction: ChatGPT is an artificial intelligence developed by OpenAI. It can be used to generate positive and differential diagnoses. However, its effectiveness in a cardiology department in Africa has not been studied.

Objectives: To evaluate the diagnostic accuracy of ChatGPT4 in the cardiology department of the Bogodogo University Hospital Center. Patients and Methods: This was a retrospective descriptive study conducted from 1st April to 30 May 2024 in the cardiology department of the Bogodogo University Hospital. Our primary endpoint was whether the main diagnosis of ChatGPT corresponded to the final diagnosis made by the cardiologists.

Results: Out of 50 patients collected, ChatGPT found the diagnosis on the basis of clinical data in 35.19%. In 81.48% of cases, ChatGPT’s diagnosis was one of the cardiologist’s three hypotheses and in 64.81% of cases the diagnosis was found with certainty by ChatGPT. The differential diagnosis listed by ChatGPT was score 5 in 46 patients. All the diagnoses of the aetiological groups were found by ChatGPT in 100% of cases except in the hypertensive and ischaemic cardiomyopathy groups.

Conclusion: ChatGPT demonstrated a variable ability to generate accurate diagnoses, with a significant improvement when paraclinical data was included.

Keywords

• ChatGPT

• Cardiology

• Diagnosis

• Burkina Faso

Citation

NACANABO WM, SEGHDA TAA, BAYALA YLT, MILLOGO G, THIAM A, et al. (2025) Evaluation of The Diagnostic Capabilities of Artficial Intelligence (CHATGPT-4) in The Cardiology Department of Bogodogo University Hospital, Burkina Faso. Ann Vasc Med Res 12(1): 1185.

INTRODUCTION

ChatGPT is an artificial intelligence developed by OpenAI [1]. It is a large language model based on automatic natural language processing, also known as “generative pretrained transform” (GPT) [2]. ChatGPT is capable of generating textual responses that sound human in response to queries written by users [2]. Previous studies have reported that the diagnostic accuracy of differential diagnosis lists generated by ChatGPT for clinical vignettes ranged from 64% to 83% [3]. Extensive research is currently being conducted in a variety of areas, including cardiovascular disease, using ChatGPT [4]. In our African context, the findings of these studies could be beneficial due to the inadequacy of medical equipment and the obvious shortage of medical specialists. However, there is a lack of studies addressing the competence of ChatGPT in the diagnosis of cardiovascular disease, based on clinical and paraclinical data in a black African population. The aim of this study was to assess the diagnostic accuracy of ChatGPT when provided with clinical and paraclinical data and to compare its performance with that of cardiologists in a cardiology department in Burkina Faso.

MATERIALS AND METHODS

Clinical information from 50 consecutive patients admitted to the cardiology department of Bogodogo University Hospital Center between 1er April and 30 May 2024 was reviewed. Patients without a clear and precise diagnosis were excluded. We used the Chat GPT 4 template application (June 14 version; ChatGPT4, OpenAI, LLC). Clinical and paraclinical information was anonymised, transcribed and entered into Chat GPT 4, followed by the question “what is the most likely diagnosis?” and then “what are the possible diagnoses?”. Our predefined primary endpoint was whether the main diagnosis in ChatGPT matched the final diagnosis made by cardiologists. The secondary endpoints were whether the final diagnosis matched by providing clinical data only. Then the presence of the final diagnosis in the possible differential and the differential quality score of the model using a 5-point ordinal scoring system previously published by Bond et al., [5]. This score is based on accuracy and utility (in which a score of 5 is assigned for a differential including the correct diagnosis and a score of 0 is assigned when no diagnosis is close) [5].

The source documents were hospital registers, medical records and reports of paraclinical results.

The data were entered into an Excel database and all the analysis was carried out using SPSS software version 20.0. Missing data were treated as missing data during analysis. We calculated the frequencies of the exact diagnoses found by ChatGPT (clinical data only, then clinical + paraclinical data).

We also calculated the frequencies of the final diagnosis as a function of the differential diagnosis scores. Identifiers were assigned to each patient during the collection process, so that no names are on our database, thus preserving anonymity and confidentiality.

RESULTS

In this study, ChatGPT found the diagnosis solely on the basis of clinical data in 35.19% of cases. In 81.48% of cases, ChatGPT’s diagnosis was one of the three diagnostic hypotheses put forward by the clinicians. After inclusion of the paraclinical data, he reported 64.81% certainty with the physicians’ diagnoses. The main diagnoses such as hypertensive heart disease, ischaemic heart disease, toxic heart disease and valvular heart disease were found in 19.23%, 28.84%, 15.38% and 15.38% respectively. All the diagnoses of the aetiological groups were found by ChatGPT in 100% of cases except in the hypertensive and ischaemic cardiomyopathy groups.

DISCUSSION

Artificial intelligence (AI) occupies a prominent place in contemporary medical practice [3]. The aim of our study was to evaluate the performance of ChatGPT in the context of African cardiology practice. To our knowledge, this is the first study to evaluate the diagnostic capabilities of ChatGPT in a cardiology department in sub-Saharan Africa. Our study in cardiology revealed that ChatGPT correctly identified patients’ diagnoses in 64.81% of cases, a significantly better result than that observed by Stoneham et al. in dermatology, where ChatGPT correctly identified the diagnosis in 56% of cases. [6]. In terms of differential diagnoses, ChatGPT listed the cardiologist’s diagnosis among its hypotheses with a score equal to 5 in 85.18% of cases, compared with 100% in the dermatology study [6]. This disparity can be attributed to several factors.

Firstly, our study used the latest version of ChatGPT, version 4, which benefits from significant improvements in terms of accuracy and analytical capabilities. In contrast, the study by Stoneham et al. used an earlier version of the AI, which could explain the lower performance [6]. In addition, the inherent complexity of dermatological diagnoses often requires a very precise clinical semiological description, a task that may be more difficult for ChatGPT to accomplish without high-quality input data. In cardiology, ChatGPT has the advantage of being able to draw on a multitude of paraclinical examinations, such as electrocardiograms, echocardiograms and laboratory analyses, to refine its diagnoses. This wealth of clinical data enables ChatGPT to produce more accurate and reliable diagnoses. Our superior results in cardiology illustrate not only the technological evolution of ChatGPT, but also the importance of available data in improving its diagnostic capabilities. ChatGPT’s capabilities are proving to be an invaluable asset for the future of medical practice. Indeed, the integration of generative AI such as ChatGPT can offer immediate support to doctors in complex cases, reducing diagnostic errors and improving patient outcomes [4].

In an educational context, ChatGPT could play a crucial role in the training of future cardiologists, in particular by refining clinical reasoning and the acquisition of medical knowledge [4]. Interaction with generative AI exposes learners to a variety of diagnoses, preparing them for complex clinical situations. ChatGPT, is becoming increasingly important in cardiology, as demonstrated by several Western studies. For example, the study by Gunay et al., concluded that ChatGPT outperformed cardiologists on common questions, while its performance closely aligned with that of cardiologists as the complexity of the questions increased [7]. Similarly, the study by Guo et al., found that the application of AI in the diagnosis and treatment of cardiac arrhythmias was superior to that of medical specialists [8].

The use of ChatGPT in the diagnosis of cardiovascular disease presents both risks and challenges. Risks include concerns about confidentiality, ethics, bias and discrimination. ChatGPT can be used intentionally or unintentionally to create false evidence and material, thanks to its impressive ability to produce information with a high degree of plausibility [9]. This includes “hallucinations”, where the content generated is not based on reality, creating entirely fabricated facts [9]. Another major risk is the reproduction of biases present in training data. In the field of health, where precision is crucial, errors or inaccuracies can be catastrophic [9]. To minimise these risks, rigorous human evaluation is essential, as is compliance with standards of accuracy, reliability and interpretability. In addition, security measures must be put in place to protect patient information, including encryption, access control, secure data storage and compliance with confidentiality regulations.

Challenges include the need for ChatGPT to have the medical expertise to understand the complex relationships between conditions and treatments. Being limited to data, it lacks recent medical advances, which may affect its clinical utility [10]. Our study showed that in 81.48% of cases, the diagnosis of ChatGPT matched the cardiologists’ assumptions, highlighting its potential usefulness despite the challenges mentioned. Another challenge is the potential help of ChatGPT for non-cardiologists in the triage and referral of patients, especially in countries such as ours where there is a critical shortage of specialist physicians, but also with the security challenge of not being able to evacuate certain patients. Our study of the diagnostic capabilities of ChatGPT in cardiology has several important limitations. Firstly, as with any retrospective study, it suffers from missing data in some patients, which may affect the representativeness of the results.

Secondly, although the cases studied provide valuable insight into diagnostic scenarios, they may not reflect the full range of clinical presentations, including atypical cases or diagnostic challenges encountered in the cardiology department. In addition, some diagnoses could have been refined if ChatGPT had access to the clinical course of patients, as a clinician would. These limitations must be taken into account when interpreting the results, and underline the need for further studies to fully assess the potential and limitations of ChatGPT in the diagnosis of cardiovascular disease.

CONCLUSION

In conclusion, our study of the diagnostic capabilities of ChatGPT in a cardiology department in Africa reveals promising results. In 64.81% of cases, ChatGPT established a diagnosis concordant with that of the cardiologist, particularly in the nosological groups associated with valvular and hypertensive cardiomyopathies. These results demonstrate the potential of ChatGPT as a diagnostic aid, while underlining the importance of continuing research to refine these results, particularly in developing countries such as ours. The challenges encountered, particularly in relation to the variability of clinical presentations and the lack of longitudinal follow-up of patients, need to be overcome by future studies.

DECLARATIONS

Ethics approval and consent to participate

We have obtained the ‘informed consent’ of the subjects concerned. All measures are taken to preserve the confidentiality of information concerning them. Approval was obtained from the ethics committee of Bogodogo University Hospital. The procedures used in this study adhere to the tenets of the Declaration of Helsinki.

Consent for publication

We have obtained the ‘informed consent’ of the subjects concerned for publication.

Availability of data and materials

The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.

Competing interests

The authors state that they have no conflicts of interest that might have influenced the outcome of this research.

Funding

The lead author Wendlassida Martin NACANABO affirms that this manuscript is an honest, accurate, and transparent account of the study being reported; that no important aspects of the study have been omitted; and that any discrepancies from the study as planned (and, if relevant, registered) have been explained. Author contributions

Wendlassida Martin NACANABO: Conceptualization;methodology; data curation; writing–review and editing; writing–original draft; project administration.

Taryètba André Arthur SEGHDA: project administration; investigation; methodology.

Yannick Laurent Tchenadoyo BAYALA: Conceptualization investigation; data curation, project administration. Georges MILLOGO: Supervision; investigation; Anna THIAM: Supervision; investigation;

Nobila Valentin YAMEOGO: Supervision; investigation; André Kounoaga SAMADOULOUGOU: supervision; validation Patrice ZABSONRE: Supervision Author details (optional) The lead author Wendlassida Martin NACANABO is a resident in cardiology department of Bogodogo university hospital

REFERENCES
  1. Curtis N, ChatGPT. To ChatGPT or not to ChatGPT? The Impact of Artificial Intelligence on Academic Publishing. Pediatr Infect Dis J. 2023; 42: 275.
  2. Kung TH, Cheatham M, Medenilla A, Sillos C, De Leon L, Elepaño C, et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit Health. 2023; 2: e0000198.
  3. Kanjee Z, Crowe B, Rodman A. Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge. JAMA. 2023; 330: 78-80.
  4. Hirosawa T, Kawamura R, Harada Y, Mizuta K, Tokumasu K, Kaji Y, et al. ChatGPT-Generated Differential Diagnosis Lists for Complex Case- Derived Clinical Vignettes: Diagnostic Accuracy Evaluation. JMIR Med Inform. 2023; 11: e48808.
  5. Bond WF, Schwartz LM, Weaver KR, Levick D, Giuliano M, Graber ML. Differential Diagnosis Generators: an Evaluation of Currently Available Computer Programs. J Gen Intern Med. 2012; 27: 213-219.
  6. Stoneham S, Livesey A, Cooper H, Mitchell C. Chat GPT vs Clinician: challenging the diagnostic capabilities of A.I. in dermatology. Clin Exp Dermatol. 2024; 49: 707-710.
  7. Günay S, Öztürk A, Özerol H, Yi?it Y, Erenler AK. Comparison of emergency medicine specialist, cardiologist, and chat-GPT in electrocardiography assessment. Am J Emerg Med. 2024; 80: 51-60.
  8. Guo R-X, Tian X, Bazoukis G, Tse G, Hong S, Chen KY, et al. Application of artificial intelligence in the diagnosis and treatment of cardiac arrhythmia. PACE. 2024; 47: 789-801.
  9. Cascella M, Montomoli J, Bellini V, Bignami E. Evaluating the Feasibility of ChatGPT in Healthcare: An Analysis of Multiple Clinical and Research Scenarios. J Med Syst. 2023; 47: 33.
  10. Vaishya R, Misra A, Vaish A. ChatGPT: Is this version good for healthcare and research? Diabetes Metab Syndr. 202317: 102744.

NACANABO WM, SEGHDA TAA, BAYALA YLT, MILLOGO G, THIAM A, et al. (2025) Evaluation of The Diagnostic Capabilities of Artficial Intelligence (CHATGPT-4) in The Cardiology Department of Bogodogo University Hospital, Burkina Faso. Ann Vasc Med Res 12(1): 1185

Received : 03 Mar 2025
Accepted : 27 Feb 2025
Published : 03 Mar 2025
Journals
Annals of Otolaryngology and Rhinology
ISSN : 2379-948X
Launched : 2014
JSM Schizophrenia
Launched : 2016
Journal of Nausea
Launched : 2020
JSM Internal Medicine
Launched : 2016
JSM Hepatitis
Launched : 2016
JSM Oro Facial Surgeries
ISSN : 2578-3211
Launched : 2016
Journal of Human Nutrition and Food Science
ISSN : 2333-6706
Launched : 2013
JSM Regenerative Medicine and Bioengineering
ISSN : 2379-0490
Launched : 2013
JSM Spine
ISSN : 2578-3181
Launched : 2016
Archives of Palliative Care
ISSN : 2573-1165
Launched : 2016
JSM Nutritional Disorders
ISSN : 2578-3203
Launched : 2017
Annals of Neurodegenerative Disorders
ISSN : 2476-2032
Launched : 2016
Journal of Fever
ISSN : 2641-7782
Launched : 2017
JSM Bone Marrow Research
ISSN : 2578-3351
Launched : 2016
JSM Mathematics and Statistics
ISSN : 2578-3173
Launched : 2014
Journal of Autoimmunity and Research
ISSN : 2573-1173
Launched : 2014
JSM Arthritis
ISSN : 2475-9155
Launched : 2016
JSM Head and Neck Cancer-Cases and Reviews
ISSN : 2573-1610
Launched : 2016
JSM General Surgery Cases and Images
ISSN : 2573-1564
Launched : 2016
JSM Anatomy and Physiology
ISSN : 2573-1262
Launched : 2016
JSM Dental Surgery
ISSN : 2573-1548
Launched : 2016
Annals of Emergency Surgery
ISSN : 2573-1017
Launched : 2016
Annals of Mens Health and Wellness
ISSN : 2641-7707
Launched : 2017
Journal of Preventive Medicine and Health Care
ISSN : 2576-0084
Launched : 2018
Journal of Chronic Diseases and Management
ISSN : 2573-1300
Launched : 2016
Annals of Vaccines and Immunization
ISSN : 2378-9379
Launched : 2014
JSM Heart Surgery Cases and Images
ISSN : 2578-3157
Launched : 2016
Annals of Reproductive Medicine and Treatment
ISSN : 2573-1092
Launched : 2016
JSM Brain Science
ISSN : 2573-1289
Launched : 2016
JSM Biomarkers
ISSN : 2578-3815
Launched : 2014
JSM Biology
ISSN : 2475-9392
Launched : 2016
Archives of Stem Cell and Research
ISSN : 2578-3580
Launched : 2014
Annals of Clinical and Medical Microbiology
ISSN : 2578-3629
Launched : 2014
JSM Pediatric Surgery
ISSN : 2578-3149
Launched : 2017
Journal of Memory Disorder and Rehabilitation
ISSN : 2578-319X
Launched : 2016
JSM Tropical Medicine and Research
ISSN : 2578-3165
Launched : 2016
JSM Head and Face Medicine
ISSN : 2578-3793
Launched : 2016
JSM Cardiothoracic Surgery
ISSN : 2573-1297
Launched : 2016
JSM Bone and Joint Diseases
ISSN : 2578-3351
Launched : 2017
JSM Bioavailability and Bioequivalence
ISSN : 2641-7812
Launched : 2017
JSM Atherosclerosis
ISSN : 2573-1270
Launched : 2016
Journal of Genitourinary Disorders
ISSN : 2641-7790
Launched : 2017
Journal of Fractures and Sprains
ISSN : 2578-3831
Launched : 2016
Journal of Autism and Epilepsy
ISSN : 2641-7774
Launched : 2016
Annals of Marine Biology and Research
ISSN : 2573-105X
Launched : 2014
JSM Health Education & Primary Health Care
ISSN : 2578-3777
Launched : 2016
JSM Communication Disorders
ISSN : 2578-3807
Launched : 2016
Annals of Musculoskeletal Disorders
ISSN : 2578-3599
Launched : 2016
Annals of Virology and Research
ISSN : 2573-1122
Launched : 2014
JSM Renal Medicine
ISSN : 2573-1637
Launched : 2016
Journal of Muscle Health
ISSN : 2578-3823
Launched : 2016
JSM Genetics and Genomics
ISSN : 2334-1823
Launched : 2013
JSM Anxiety and Depression
ISSN : 2475-9139
Launched : 2016
Clinical Journal of Heart Diseases
ISSN : 2641-7766
Launched : 2016
Annals of Medicinal Chemistry and Research
ISSN : 2378-9336
Launched : 2014
JSM Pain and Management
ISSN : 2578-3378
Launched : 2016
JSM Women's Health
ISSN : 2578-3696
Launched : 2016
Clinical Research in HIV or AIDS
ISSN : 2374-0094
Launched : 2013
Journal of Endocrinology, Diabetes and Obesity
ISSN : 2333-6692
Launched : 2013
Journal of Substance Abuse and Alcoholism
ISSN : 2373-9363
Launched : 2013
JSM Neurosurgery and Spine
ISSN : 2373-9479
Launched : 2013
Journal of Liver and Clinical Research
ISSN : 2379-0830
Launched : 2014
Journal of Drug Design and Research
ISSN : 2379-089X
Launched : 2014
JSM Clinical Oncology and Research
ISSN : 2373-938X
Launched : 2013
JSM Bioinformatics, Genomics and Proteomics
ISSN : 2576-1102
Launched : 2014
JSM Chemistry
ISSN : 2334-1831
Launched : 2013
Journal of Trauma and Care
ISSN : 2573-1246
Launched : 2014
JSM Surgical Oncology and Research
ISSN : 2578-3688
Launched : 2016
Annals of Food Processing and Preservation
ISSN : 2573-1033
Launched : 2016
Journal of Radiology and Radiation Therapy
ISSN : 2333-7095
Launched : 2013
JSM Physical Medicine and Rehabilitation
ISSN : 2578-3572
Launched : 2016
Annals of Clinical Pathology
ISSN : 2373-9282
Launched : 2013
Annals of Cardiovascular Diseases
ISSN : 2641-7731
Launched : 2016
Journal of Behavior
ISSN : 2576-0076
Launched : 2016
Annals of Clinical and Experimental Metabolism
ISSN : 2572-2492
Launched : 2016
Clinical Research in Infectious Diseases
ISSN : 2379-0636
Launched : 2013
JSM Microbiology
ISSN : 2333-6455
Launched : 2013
Journal of Urology and Research
ISSN : 2379-951X
Launched : 2014
Journal of Family Medicine and Community Health
ISSN : 2379-0547
Launched : 2013
Annals of Pregnancy and Care
ISSN : 2578-336X
Launched : 2017
JSM Cell and Developmental Biology
ISSN : 2379-061X
Launched : 2013
Annals of Aquaculture and Research
ISSN : 2379-0881
Launched : 2014
Clinical Research in Pulmonology
ISSN : 2333-6625
Launched : 2013
Journal of Immunology and Clinical Research
ISSN : 2333-6714
Launched : 2013
Annals of Forensic Research and Analysis
ISSN : 2378-9476
Launched : 2014
JSM Biochemistry and Molecular Biology
ISSN : 2333-7109
Launched : 2013
Annals of Breast Cancer Research
ISSN : 2641-7685
Launched : 2016
Annals of Gerontology and Geriatric Research
ISSN : 2378-9409
Launched : 2014
Journal of Sleep Medicine and Disorders
ISSN : 2379-0822
Launched : 2014
JSM Burns and Trauma
ISSN : 2475-9406
Launched : 2016
Chemical Engineering and Process Techniques
ISSN : 2333-6633
Launched : 2013
Annals of Clinical Cytology and Pathology
ISSN : 2475-9430
Launched : 2014
JSM Allergy and Asthma
ISSN : 2573-1254
Launched : 2016
Journal of Neurological Disorders and Stroke
ISSN : 2334-2307
Launched : 2013
Annals of Sports Medicine and Research
ISSN : 2379-0571
Launched : 2014
JSM Sexual Medicine
ISSN : 2578-3718
Launched : 2016
JSM Biotechnology and Biomedical Engineering
ISSN : 2333-7117
Launched : 2013
Journal of Hematology and Transfusion
ISSN : 2333-6684
Launched : 2013
JSM Environmental Science and Ecology
ISSN : 2333-7141
Launched : 2013
Journal of Cardiology and Clinical Research
ISSN : 2333-6676
Launched : 2013
JSM Nanotechnology and Nanomedicine
ISSN : 2334-1815
Launched : 2013
Journal of Ear, Nose and Throat Disorders
ISSN : 2475-9473
Launched : 2016
JSM Ophthalmology
ISSN : 2333-6447
Launched : 2013
Journal of Pharmacology and Clinical Toxicology
ISSN : 2333-7079
Launched : 2013
Annals of Psychiatry and Mental Health
ISSN : 2374-0124
Launched : 2013
Medical Journal of Obstetrics and Gynecology
ISSN : 2333-6439
Launched : 2013
Annals of Pediatrics and Child Health
ISSN : 2373-9312
Launched : 2013
JSM Clinical Pharmaceutics
ISSN : 2379-9498
Launched : 2014
JSM Foot and Ankle
ISSN : 2475-9112
Launched : 2016
JSM Alzheimer's Disease and Related Dementia
ISSN : 2378-9565
Launched : 2014
Journal of Addiction Medicine and Therapy
ISSN : 2333-665X
Launched : 2013
Journal of Veterinary Medicine and Research
ISSN : 2378-931X
Launched : 2013
Annals of Public Health and Research
ISSN : 2378-9328
Launched : 2014
Annals of Orthopedics and Rheumatology
ISSN : 2373-9290
Launched : 2013
Journal of Clinical Nephrology and Research
ISSN : 2379-0652
Launched : 2014
Annals of Community Medicine and Practice
ISSN : 2475-9465
Launched : 2014
Annals of Biometrics and Biostatistics
ISSN : 2374-0116
Launched : 2013
JSM Clinical Case Reports
ISSN : 2373-9819
Launched : 2013
Journal of Cancer Biology and Research
ISSN : 2373-9436
Launched : 2013
Journal of Surgery and Transplantation Science
ISSN : 2379-0911
Launched : 2013
Journal of Dermatology and Clinical Research
ISSN : 2373-9371
Launched : 2013
JSM Gastroenterology and Hepatology
ISSN : 2373-9487
Launched : 2013
Annals of Nursing and Practice
ISSN : 2379-9501
Launched : 2014
JSM Dentistry
ISSN : 2333-7133
Launched : 2013
Author Information X