Mesopotamian Journal of Artificial Intelligence in Healthcare

Vol.2023, pp. 45–51

DOI: https://doi.org/10.58496/MJAIH/2023/009; ISSN: 3005-365X
https://mesopotamian.press/journals/index.php/MJAIH

Review Article
Operating Artificial Intelligence to Assist Physicians Diagnose Medical Images: A
Narrative Review
Oluwaseun A. Adelaja1,*, , Hussein Alkattan2,
1 Information Communication and Technology Department, Lagos State University, Lagos, Nigeria
2 Department of System Programming, South Ural State University, Chelyabinsk, Russia

A R TICLE INFO A BS TR ACT

Article History Medical image diagnostics is crucial to healthcare since it aids in the diagnosis and treatment of a variety
Received 23 Jun 2023
of diseases and conditions. However, the process is time-consuming and prone to human error. In recent
Accepted 5 Sep 2023 years, artificial intelligence has been a powerful tool for enhancing medical imaging diagnosis. Using AI
Published 13 Sep 2023 algorithms for medical picture interpretation has the potential to revolutionise the field by improving
accuracy, efficacy, and standardization. These algorithms can quickly sift through enormous amounts of
Keywords
medical imaging, finding anomalies, quantifying features, and providing useful information to help
Artificial Intelligence
medical professional-s make judgments. AI-based systems can be used to track the evolution of diseases,
Medical Images plan treatments, and highlight particular areas of interest in medical pictures. Additionally, AI systems
Healthcare can aid in case triage by classifying cases according to urgency, enabling quick response to life-or-death
Machine Learning situations. Healthcare practitioners can gain from increased diagnostic accuracy and efficiency, improved
Mammography
workflow management, and standardized interpretations by utilizing AI in medical imaging diagnostics.
However, it's crucial to understand that AI complements human expertise rather than replacing it. To
ensure a safe and efficient application in clinical settings as AI technologies continue to evolve and
advance, continuing research and collaboration between AI developers and healthcare practitioners is
essential. Medical image diagnosis is poised to advance significantly with continued AI integration,
ultimately improving patient outcomes and healthcare delivery.

1. INTRODUCTION
In the sphere of healthcare, using artificial intelligence (AI) to improve medical imaging diagnosis has become a ground-
breaking strategy. AI algorithms can analyse the ever-increasing amount of medical pictures, including X-rays, CT scans,
and MRI scans, and offer insightful findings to help medical personnel make a correct and fast diagnosis [1-3]. Diagnostic
interpretation of medical images has traditionally relied significantly on the training and experience of radiologists and other
specialists. However, this procedure can take a while and be prone to mistakes made by humans. On the other hand, AI-
powered systems can process massive amounts of medical imagery and extract vital data to aid clinicians in their decision-
making [4][5]. There are various benefits to incorporating AI into medical image diagnosis. First off, medical images may
be swiftly and precisely scanned for abnormalities or suspected diseases using AI algorithms. They can draw attention to
particular areas of interest, assisting radiologists in concentrating on relevant areas and thus lowering the chance of missing
significant results. Second, AI algorithms can help with the quantification and measurement of medical imaging properties.
This skill is especially helpful for tracking the evolution of an illness over time or assessing the efficacy of treatments [6].
Artificial intelligence-based solutions can offer objective and consistent measures, lowering inter-observer variability and
enhancing the accuracy of diagnosis. AI can also assist in the triage process by ranking cases according to the gravity of the
results. AI can increase workflow efficiency by automatically classifying photos into urgent, less urgent, or typical scenarios,
ensuring that urgent situations are handled right away [7]. It's crucial to remember that AI is intended to complement, not
replace, healthcare personnel. AI systems serve as supporting tools, offering more data and insights to help with diagnosis.
The healthcare expert, who weighs all relevant information, the patient's past, and the clinical setting, ultimately has the last
say.
2. BREAST CANCER DETECTION
Artificial intelligence has mostly been used in the realm of medical imaging for the diagnosis of breast cancer. AI algorithms
have been developed to examine mammograms and increase the precision of diagnoses [8]. Mammography detection for breast
cancer is common [9]. By recognizing and categorizing mammography abnormalities, artificial intelligence-based approaches
*Corresponding author. Email: oluwaseun.adelaja@lasu.edu.ng
46 Adelaja et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 45–51

can help in the early detection of breast cancer. These algorithms can examine a large number of images, and they might be able
to detect small changes in breast tissue that the human eye could miss. AI-powered solutions may lessen inter-observer variability
and steer radiologists to suspicious areas of interest, which can improve diagnosis accuracy. Prioritisation of mammography cases
for additional screening can be improved using artificial intelligence methods [10]. AI-based solutions can aid the triage process
by detecting lesions or anomalies of concern, flagging cases that need further investigation, and helping prioritise patients based
on the potential severity of their condition. Deep learning algorithms contribute to identifying areas where cancer has spread in
the breast [11]. These algorithms can handle and analyse vast amounts of data, including medical images and patient health
information, to build prediction models to assess the risk of developing this severe disease. By considering various risk factors,
including family history, age and breast density, AI-based systems can assist in identifying individuals at high risk of developing
breast cancer, enabling earlier identification and more effective treatments.
3. DIAGNOSIS OF EYE DISEASES
Artificial intelligence (AI) has a lot of potential for use in medical imaging, particularly for the diagnosis of eye problems.
Traditional eye diagnosis techniques frequently call for specialized education, practical expertise, and occasionally invasive
testing. AI-based solutions, on the other hand, can offer a non-invasive and more objective method of diagnosis. To assist in
the diagnosis of many eye disorders, AI algorithms can examine many diagnostic imaging modalities, such as fundus
photography, optical coherence tomography (OCT), and visual field testing [12]. These algorithms analyse the images for
patterns and look for potential anomalies, such as retinal or optic nerve damage, that may be caused by common eye disorders
like glaucoma, age-related macular degeneration, diabetic retinopathy, and others. Diagnoses are more accurate, quicker,
and more precise thanks to AI-based systems that recognize emergent patterns in medical pictures using cutting-edge
machine learning algorithms and deep neural networks [13]. They can process vast numbers of photos more quickly than
humans, enabling earlier abnormality diagnosis than conventional techniques, and allowing for the administration of more
effective illness therapies to patients even before symptoms manifest. Additionally, AI algorithms have the potential to track
the development of diseases over time by observing changes in eye tissue and forecasting results [14]. AI can assist healthcare
providers in creating individualized treatment regimens for individuals by offering a more accurate and reliable technique of
disease monitoring. To diagnose eye problems, artificial intelligence (AI) is also being used in the field of ophthalmology
[27]. AI algorithms can examine patient symptoms, clinical data, and ocular imaging to aid in the spotting and identifying
of a number of eye conditions. Here is some ways AI can help with eye disease diagnosis:
• Analysis of Retinal Imaging [28]: Using methods like fundus photography or optical coherence tomography (OCT), AI
systems may examine retinal images. These algorithms can recognize and categorize several eye disorders, including
glaucoma, age-related macular degeneration, diabetic retinopathy, and retinal detachment. AI can highlight anomalies
or offer numerical data to help in disease diagnosis and tracking the evolution of the condition.
• Assessment of the Optic Nerve [29]: AI can examine clinical and imaging data about the optic nerve to help in the
diagnosis of diseases like glaucoma. AI algorithms can offer insights and help with the early detection and management
of glaucoma by examining several features such as the appearance of the optic nerve head, the thickness of the retinal
nerve fibre layer, and the cup-to-disc ratio.
• Corneal Disorders [30]: AI algorithms can examine data from topography or tomography scans of the cornea to help in
the identification of conditions like keratoconus, corneal dystrophies, or corneal infections.
• Refractive Error Assessments [31]: Using data from autorefractors and retinoscopes as well as other clinical data, AI
algorithms can analyse refractive faults including myopia, hyperopia, and astigmatism to produce more precise readings.
The prescription for eyeglasses or contact lenses may benefit from this.
• Symptom Analysis [32]: Chatbots or virtual assistants powered by AI can gather and examine symptoms and risk factors
reported by patients to make early diagnoses of potential eye disorders. These virtual assistants can aid in patient triage
and recommend suitable next steps for obtaining a diagnosis and therapy.

4. DIAGNOSIS OF NEUROLOGICAL DISEASES

It is a challenging undertaking to diagnose neurological disorders, and it frequently necessitates the expertise of competent
neurologists as well as the synthesis of multiple diagnostic tests and clinical data. Artificial intelligence (AI) has attracted
interest as a potential tool to assist healthcare professionals in more swiftly and accurately diagnosing neurological diseases.
AI algorithms that can analyse various data sources can be used to diagnose neurological diseases. Clinical notes,
electroencephalography (EEG) recordings, magnetic resonance imaging (MRI), computed tomography (CT), and positron
emission tomography (PET) scans are among these sources [15]. One of the primary applications of AI in diagnosing
neurological illnesses is the interpretation of medical imaging data. By identifying patterns and features in imaging data, AI
systems can detect abnormalities connected to specific neurological conditions, such as stroke, brain tumours, multiple
47 Adelaja et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 45–51

sclerosis, and Alzheimer's disease [16]. These techniques can aid radiologists in locating lesions, enhancing diagnostic
accuracy, and reducing interpretation variability. AI can be used to interpret EEG data, which is frequently used to monitor
and diagnose conditions, including epilepsy and sleep issues [17]. By analysing waveforms, spike patterns, and other EEG
characteristics, AI systems can help neurologists diagnose neurological problems by detecting specific practices associated
with certain neurological conditions. Another emerging area is the application of AI algorithms to genetic data analysis to
identify particular neurological conditions with a hereditary component, such as Huntington's disease or specific varieties of
muscular dystrophy [18][19]. AI can help create more precise and individualised diagnoses by identifying relevant genetic
variants and assessing their significance [20][21].

5. DIAGNOSIS OF CARDIOVASCULAR ILLNESS

Artificial intelligence is being used more and more in the healthcare industry, particularly for the diagnosis of cardiovascular
diseases [22]. AI systems can analyse large data sets and find patterns that can be difficult to see in human examination. AI
algorithms can evaluate patient data from sources including medical records, test results, and imaging examinations to
determine a person's risk of developing cardiovascular diseases [23]. Finding high-risk patients who may require additional
evaluation and treatment can be made easier with the help of this. AI algorithms can analyse medical imaging studies like
echocardiograms, CT scans, and MRIs to ascertain the structure and physiology of the heart [24][25]. This may aid in the
early detection of anomalies such as weakened heart muscle, valve problems, or coronary artery plaque accumulation.
Electrocardiogram (ECG) data can be analysed by AI algorithms to look for abnormal heart rhythms, ischemia abnormalities
that indicate decreased heart blood flow, or other cardiac problems [26]. AI can be used for building prediction models that
estimate the likelihood that a patient will encounter a specific cardiovascular condition, or a negative cardiac event based on
patient data. These models can aid in directing preventive measures and specialized treatment regimens. By analysing patient
data and offering suggestions or differential diagnoses based on accepted practices and prior cases, AI-powered decision
support systems can help healthcare providers make precise diagnoses. By enhancing the skills of medical practitioners,
enabling early detection, and guiding individualized treatment decisions, AI has the potential to significantly enhance the
diagnosis of cardiovascular disorders.

6. DIAGNOSIS OF DIGESTIVE SYSTEM DISEASES

The area of gastroenterology is undergoing a revolution thanks to artificial intelligence (AI), which is improving how
digestive system disorders are diagnosed [33]. AI algorithms can make it easier to identify, categorize, and treat a variety of
gastrointestinal diseases through the study of patient data, medical imaging, and clinical records. Outline of how AI enables
the diagnosis of gastrointestinal diseases:
• Image analysis by AI [34]: AI systems are excellent at analysing radiographic and endoscopic images used in medicine.
AI systems can recognize anomalies like polyps, ulcers, tumours, or indications of inflammation in the digestive tract
by utilizing machine learning techniques. This helps doctors establish precise diagnoses and proper treatment regimens.
• Pattern Recognition [35]: AI is capable of identifying patterns in patient data, including symptoms, medical history, test
findings, and genetic data. AI algorithms can offer insightful information into disorders like inflammatory bowel disease,
celiac disease, pancreatitis, or liver diseases by analysing connections within this data, assisting in diagnostic and therapy
choices.
• Gastroenterologists receive intelligent advice from AI-powered decision support systems based on acknowledged norms
and prior situations [36]. To create differential diagnoses or suggest additional diagnostic procedures, these systems
analyse patient data, symptoms, and test results, improving diagnostic speed and accuracy.
• Risk Stratification [37]: AI algorithms may analyse patient information, such as genetic markers and medical history, to
determine an individual's risk of acquiring particular gastrointestinal disorders. Through early interventions or
preventative measures, this risk stratification helps identify those who are at high risk for illnesses like colorectal cancer,
stomach ulcers, or gallstones.
• Predictive Analytics [38]: Using massive datasets, AI algorithms forecast the course of disease and the effectiveness of
treatment. AI can predict patient responses to particular drugs, surgical procedures, or dietary changes by looking for
patterns in patient data. This makes it easier to arrange individualized treatments and enhances patient results.
It is crucial to remember that the application of AI in gastroenterology is an area that is still developing, and different
healthcare settings may use the technology differently [39-41]. To evaluate data generated by AI, apply their clinical
knowledge, and guarantee comprehensive patient care, gastroenterologists and other healthcare professionals play a critical
48 Adelaja et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 45–51

role. AI should be viewed as a supplement to clinical evaluations rather than as a substitute, even though it has enormous
potential to increase diagnostic accuracy and treatment outcomes.

Fig. 1. AI in the fields of gastroenterology and hepatology [42].

7. CONCLUSIONS
If artificial intelligence is applied to enhance medical imaging detection of numerous diseases, there could be a revolution
and significant development in healthcare. Thanks to artificial intelligence algorithms' ability to analyse, interpret, and
diagnose medical images, medical professionals and hospitals can now diagnose patients more quickly. The use of artificial
intelligence to diagnose medical imaging has various benefits. It can improve the speed, accuracy, and efficacy of diagnosis,
allowing for more rapid and precise treatment decisions and shorter patient wait times. AI algorithms can also assist in the
detection of uncommon and anomalous situations and evaluate characteristics in medical imaging, increasing the precision
and dependability of diagnosis. Even though it is still in its early phases, artificial intelligence's usage in diagnosing medical
images has great potential. Further research, validation, and cooperation amongst AI programmers, developers, healthcare
professionals, and supervisors are necessary for this technology to be deployed safely and efficiently in clinical settings.
There is a lot of promise to improve patient care and accuracy by utilising artificial intelligence to enhance medical imaging
diagnostics. As technology advances, incorporating artificial intelligence into hospital and healthcare systems will pave the
way for better, more precise, more efficient healthcare services.
Funding
The authors had no institutional or sponsor backing.
Conflicts Of Interest
The author's disclosure statement confirms the absence of any conflicts of interest.
Acknowledgment
The authors extend appreciation to the institution for their unwavering support and encouragement during the course of
this research.

References
[1] H. Kaheel, A. Hussein, and A. Chehab, “AI-Based Image Processing for COVID-19 Detection in Chest CT Scan
Images,” Frontiers in Communications and Networks, vol.2, no.2021, pp.1-12, August 2021.
https://doi.org/10.3389/frcmn.2021.645040
49 Adelaja et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 45–51

[2] M. M. Mijwil, AH. Al-Mistarehi, M. Abotaleb, E. M. El-kenawy, A. Ibrahim, A. A. Abdelhamid, M. E. Eid, “From
Pixels to Diagnoses: Deep Learning's Impact on Medical Image Processing-A Survey,” Wasit Journal of Computer and
Mathematics Science, vol.2, no.2, pp.8-14, September 2023. https://doi.org/10.31185/wjcms.178
[3] Y. Cui, J. Zhu, Z. Duan, Z. Liao, S. Wang, and W. Liu, “Artificial Intelligence in Spinal Imaging: Current Status and
Future Directions,” International Journal of Environmental Research and Public Health, vol.19, no.18, pp.1-21,
September 2022. https://doi.org/10.3390/ijerph191811708
[4] V. P. Yadav, V.K. Yadav, A. K. Shukla, and B.S. Kshatrya, “Applications of Artificial Intelligence in Biomedical
Fields: An Overview,” International Journal of Newgen Research in Pharmacy & Healthcare, vol.1, no.1, pp.70-75,
June 2023.
[5] F. D’Antoni, F. Russo, L. Ambrosio, L. Bacco, L. Vollero, et al., “Artificial Intelligence and Computer Aided Diagnosis
in Chronic Low Back Pain: A Systematic Review,” International Journal of Environmental Research and Public
Health, vol.19, no.10, pp.1-20, May 2022. https://doi.org/10.3390/ijerph19105971
[6] G. Chassagnon, M. Vakalopoulou, E. Battistella, S. Christodoulidis, T. Hoang-Thi, et al., “AI-driven quantification,
staging and outcome prediction of COVID-19 pneumonia,” Medical Image Analysis, vol.67, pp. 101860, January 2021.
https://doi.org/10.1016/j.media.2020.101860
[7] M. Cellina, M. Cè, G. Irmici, V. Ascenti, E. Caloro, et al., “Artificial Intelligence in Emergency Radiology: Where Are
We Going?,” Diagnostics, vol.12, no.12, pp.1-20, December 2022. https://doi.org/10.3390/diagnostics12123223
[8] S. Agarwal, A. S. Yadav, V. Dinesh, K. S. S. Vatsav, K. S. S. Prakash, and S. Jaiswal, “By artificial intelligence
algorithms and machine learning models to diagnosis cancer,” Materials Today: Proceedings, vol.80, no.3, pp. 2969-
2975, 2023. https://doi.org/10.1016/j.matpr.2021.07.088
[9] G. Meenalochini and S. Ramkumar, “Survey of machine learning algorithms for breast cancer detection using
mammogram images,” Materials Today: Proceedings, vol.37, no.2, pp.2738-2743, 2021.
https://doi.org/10.1016/j.matpr.2020.08.543
[10] T. A. Retson and M. Eghtedari, “Expanding Horizons: The Realities of CAD, the Promise of Artificial Intelligence,
and Machine Learning’s Role in Breast Imaging beyond Screening Mammography,” Diagnostics, vol.13, no.13, pp.1-
12, June 2023. https://doi.org/10.3390/diagnostics13132133
[11] G. Chugh, S. Kumar, and N. Singh, “Survey on Machine Learning and Deep Learning Applications in Breast Cancer
Diagnosis,” Cognitive Computation, vol.13, pp.1451–1470, January 2021. https://doi.org/10.1007/s12559-020-09813-
6
[12] W. S. Lim, H. Ho, H. Ho, Y. Chen, C. Lee, et al., “Use of multimodal dataset in AI for detecting glaucoma based on
fundus photographs assessed with OCT: focus group study on high prevalence of myopia,” BMC Medical Imaging,
vol.20, no.206, pp.1-14, November 2022. https://doi.org/10.1186/s12880-022-00933-z
[13] R. Gupta, S. Kumari, A. Senapati, R. K. Ambasta, and P. Kumar, “New era of artificial intelligence and machine
learning-based detection, diagnosis, and therapeutics in Parkinson’s disease,” Ageing Research Reviews, vol.90,
pp.102013, September 2023. https://doi.org/10.1016/j.arr.2023.102013
[14] X. Du, Z. Chen, Q. Li, S. Yang, L. Jiang, et al., “Organoids revealed: morphological analysis of the profound next
generation in-vitro model with artificial intelligence,” Bio-Design and Manufacturing, vol.6, pp.319–339, January
2023. https://doi.org/10.1007/s42242-022-00226-y
[15] S. Hussain, I. Mubeen, N. Ullah, S. S. U. D. Shah, B. A. Khan, et al., “Modern Diagnostic Imaging Technique
Applications and Risk Factors in the Medical Field: A Review,” BioMed Research International, vol.2022, no.5164970,
pp.1-19, June 2022. https://doi.org/10.1155/2022/5164970
[16] A. Tomitaka, A. Vashist, N. Kolishetti, and M. Nair, “Machine learning assisted-nanomedicine using magnetic
nanoparticles for central nervous system diseases,” Nanoscale Advances, vol.5, no.17, pp.4354-4367, July 2023.
[17] R. Aghoram and S. B. Athira, “EEG Signal Analysis Using Machine Learning and Artificial Intelligence for
Identification of Brain Dysfunction,” In Applied Artificial Intelligence, pp.16, 2023.
[18] S. P. Praveen, T. B. M. Krishnab, C. H. Anuradhac, S. R. Mandalapud, P. Saralae, and S. Sindhura, “A robust
framework for handling health care information based on machine learning and big data engineering techniques,”
International Journal of Healthcare Management, pp.1-18, December 2022.
https://doi.org/10.1080/20479700.2022.2157071
[19] M. Tsuneki, “Deep learning models in medical image analysis,” Journal of Oral Biosciences, vol.64, no.3, pp. 312-
320, September 2022. https://doi.org/10.1016/j.job.2022.03.003
50 Adelaja et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 45–51

[20] G. Ali, M. M. Eid, O. G. Ahmed, M. Abotaleb, A. M. Z. Alaabdin, and B. A. Buruga, “Artificial intelligence in
Corneal Topography: A Short Article in Enhancing Eye Care,” Mesopotamian Journal of Artificial Intelligence in
Healthcare, vol.2023, pp.31–34, June 2023. https://doi.org/10.58496/MJAIH/2023/006
[21] K. C. Santosh, S. Allu, S. Rajaraman, and S. Antani, “Advances in Deep Learning for Tuberculosis Screening using
Chest X-rays: The Last 5 Years Review,” Journal of Medical Systems, vol.46, no.82, pp.1-19, October 2022.
https://doi.org/10.1007/s10916-022-01870-8
[22] S. Romiti, M. Vinciguerra, W. Saade, I. A. Cortajarena, and E. Greco, “Artificial Intelligence (AI) and Cardiovascular
Diseases: An Unexpected Alliance,” Cardiology Research and Practice, vol.2020, no.4972346, pp.1-8, June 2020.
https://doi.org/10.1155/2020/4972346
[23] A. Harry, “Revolutionizing Healthcare: The Transformative Role of Artificial Intelligence in the Health Sector,”
BULLET : Jurnal Multidisiplin Ilmu, vol.2, no.2, pp.326-335, May 2023.
[24] M. Sermesant, H. Delingette, H. Cochet, P. Jaïs, and N. Ayache, “Applications of artificial intelligence in
cardiovascular imaging,” Nature Reviews Cardiology, vol.18, pp.600–609, March 2021.
https://doi.org/10.1038/s41569-021-00527-2
[25] M. M. Mijwil and B. S. Shukur, “A Scoping Review of Machine Learning Techniques and Their Utilisation in
Predicting Heart Diseases,” Ibn AL- Haitham Journal For Pure and Applied Sciences, vol. 35, no.3, pp: 175-189, July
2022. https://doi.org/10.30526/35.3.2813
[26] Z. Bouzid, S. S. Al-Zaiti, R. Bond, and E. Sejdić, “Remote and wearable ECG devices with diagnostic abilities in
adults: A state-of-the-science scoping review,” Heart Rhythm, vol.19, no.7, pp.1192-1201, July 2022.
https://doi.org/10.1016/j.hrthm.2022.02.030
[27] G. W. Armstrong and A. C. Lorch, “A(eye): A Review of Current Applications of Artificial Intelligence and Machine
Learning in Ophthalmology,” International Ophthalmology Clinics, vol.60, no.1, pp.57-71, 2020.
https://doi.org/10.1097/IIO.0000000000000298
[28] R. Liu, Q. Li, F. Xu, S. Wang, J. He, et al., “Application of artificial intelligence-based dual-modality analysis
combining fundus photography and optical coherence tomography in diabetic retinopathy screening in a community
hospital,” BioMedical Engineering OnLine, vol.21, no.47, pp.1-11, July 2022. https://doi.org/10.1186/s12938-022-
01018-2
[29] T. W. Rogers, N. Jaccard, F. Carbonaro, H. G. Lemij, K. A. Vermeer, N. J. Reus, and S. Trikha, “Evaluation of an AI
system for the automated detection of glaucoma from stereoscopic optic disc photographs: the European Optic Disc
Assessment Study,” Eye, vol. 33, pp.1791–1797, July 2019. https://doi.org/10.1038/s41433-019-0510-3
[30] A. K. Morya, S. S. Janti, P. Sisodiya, A. Tejaswini, R. Prasad, K. R. Mali, B. Gurnani, “Everything real about unreal
artificial intelligence in diabetic retinopathy and in ocular pathologies,” World Journal Diabetes, vol.13, no.10, pp.822-
834, October 2022. https://doi.org/10.4239/wjd.v13.i10.822
[31] G. Linde, R. Chalakkal, L. Zhou, J. L. Huang, B. O’Keeffe, et al., “Automatic Refractive Error Estimation Using
Deep Learning-Based Analysis of Red Reflex Images,” Diagnostics, vol.13, no.17, pp.1-16, August 2023.
https://doi.org/10.3390/diagnostics13172810
[32] S. A. Alowais, S. S. Alghamdi, N. Alsuhebany, T. Alqahtani, A. I. Alshaya, et al., “Revolutionizing healthcare: the
role of artificial intelligence in clinical practice,” BMC Medical Education, vol.23, no.689, pp.1-15, September 2023.
https://doi.org/10.1186/s12909-023-04698-z
[33] F. Belabbes, S. Ibork, and F. Rouibaa, “Artificial Intelligence and Digestive Endoscopy: A Revolution for
Gastroenterology,” SAS Journal of Medicine, vol.11, pp.836-838, November 2011.
https://doi.org/10.36347/sasjm.2022.v08i11.012
[34] H. Chen and J. J. Y. Sung, “Potentials of AI in medical image analysis in Gastroenterology and Hepatology,” Journal
of Gastroenterology and Hepatology, vol.36, no.1, pp.31-38, January 2021. https://doi.org/10.1111/jgh.15327
[35] A. S. H. George, A. Shahul, and A. S. George, “Artificial Intelligence in Medicine: A New Way to Diagnose and
Treat Disease,” Partners Universal International Research Journal, vol.2, no.3, pp.246-259, September 2023.
https://doi.org/10.5281/zenodo.8374066
[36] R. T. Sutton, D. Pincock, D. C. Baumgart, D. C. Sadowski, R. N. Fedorak, and K. I. Kroeker, “An overview of clinical
decision support systems: benefits, risks, and strategies for success,” npj Digital Medicine, vol.3, no.17, pp.1-10,
February 2020. https://doi.org/10.1038/s41746-020-0221-y
51 Adelaja et al, Mesopotamian Journal of Artificial Intelligence in Healthcare Vol.2023, 45–51

[37] L. Gedefaw, C. Liu, R. K. L. Ip, H. Tse, M. H. Y. Yeung, S. P. Yip, and C. Huang, “Artificial Intelligence-Assisted
Diagnostic Cytology and Genomic Testing for Hematologic Disorders,” Cells, vol.12, no.13, pp.1-28, June 2023.
https://doi.org/10.3390/cells12131755
[38] R. Sawhney, A. Malik, S. Sharma, and V. Narayan, “A comparative assessment of artificial intelligence models used
for early prediction and evaluation of chronic kidney disease,” Decision Analytics Journal, vol.6, pp.100169, March
2023. https://doi.org/10.1016/j.dajour.2023.100169
[39] C. Hassan, A. Repici, and P. Sharma, “Incorporating Artificial Intelligence Into Gastroenterology Practices,” Clinical
Gastroenterology and Hepatology, vol.21, no.7, pp.1687-1689, July 2023. https://doi.org/10.1016/j.cgh.2023.02.008
[40] A. Lahat, E. Shachar, B. Avidan, Z. Shatz, B. S. Glicksberg, and E. Klang, “Evaluating the use of large language
model in identifying top research questions in gastroenterology,” Scientific Reports, vol.13, no.4164, pp.1-6, March
2023. https://doi.org/10.1038/s41598-023-31412-2
[41] T. Bjørsum-Meyer, A. Koulaouzidis, and G. Baatrup, “Artificial intelligence in gastroenterology: A state-of-the-art
review,” World Journal Gastroenterol, vol.28, no.16, pp.1722-1724, April 2022.
https://doi.org/10.3748/wjg.v28.i16.1722
[42] J. Cao, Z. Lu, M. Chen, B. Zhang, S. Juengpanich, J. Hu, S. Li, W. Topatana, X. Zhou, X. Feng, J. Shen, Y. Liu, and
X. Cai, “Artificial intelligence in gastroenterology and hepatology: Status and challenges,” World Journal
Gastroenterol, vol.27, no.16, pp.1664-1690, April 2021. https://doi.org/10.3748/wjg.v27.i16.1664