Review
Artificial Intelligence in Medical Diagnostics: Foundations,
Clinical Applications, and Future Directions
Dorota Bartusik-Aebisher 1 , Daniel Roshan Justin Raj 2 and David Aebisher 3, *
1 Department of Biochemistry and General Chemistry, Faculty of Medicine, Collegium Medicum, University
of Rzeszów, 35-310 Rzeszów, Poland;
2 English Division Science Club, Faculty of Medicine, Collegium Medicum, University of Rzeszów,
35-310 Rzeszów, Poland;
3 Department of Photomedicine and Physical Chemistry, Faculty of Medicine, Collegium Medicum,
University of Rzeszów, 35-310 Rzeszów, Poland
* Correspondence:
Abstract
Artificial intelligence (AI) is rapidly transforming medical diagnostics by allowing for early,
accurate, and data-driven clinical decision-making. This review provides an overview of
how machine learning (ML), deep learning, and emerging multimodal foundation models
have been used in diagnostic procedures across imaging, pathology, molecular analysis,
physiological monitoring, and electronic health record (EHR)-integrated decision-support
systems. We have discussed the basic computational foundations of supervised, unsuper-
vised, and reinforcement learning and have also shown the importance of data curation,
validation metrics, interpretability methods, and feature engineering. The use of AI in
many different applications has shown that it can find abnormalities and integrate some
features from multi-omics and imaging, which has shown improvements in prognostic
modeling. However, concerns about data heterogeneity, model drift, bias, and strict regu-
latory guidelines still remain and are yet to be addressed in this field. Looking forward,
future advancements in federated learning, generative AI, and low-resource diagnostics
will pave the way for adaptable and globally accessible AI-assisted diagnostics.
Keywords: machine learning in healthcare; medical diagnosis algorithms; healthcare
technology innovation; predictive analytics in medicine; data-driven medical solutions;
artificial intelligence in diagnostics; clinical decision support systems
1. Introduction
Artificial intelligence (AI) is an umbrella term that refers to the machine-based systems
Academic Editors: Giorgio De Nunzio that, when given a certain set of goals set by humans, can make predictions, suggestions,
and Luana Conte or choices and perform tasks that would normally require the intelligence of humans.
Received: 7 December 2025 AI in healthcare includes systems that can assist with or automate clinical tasks such as
Revised: 5 January 2026 diagnosis, prognosis, workflow optimization, recommendation of treatments, and patient
Accepted: 6 January 2026 monitoring [1]. Machine learning (ML), on the other hand, is a well-defined subfield of AI
Published: 10 January 2026
where algorithms, from data examples, learn patterns and can make predictions or decisions
Copyright: © 2026 by the authors.
on new data based on the patterns learned. ML involves supervised, unsupervised, and
Licensee MDPI, Basel, Switzerland.
reinforcement learning, while deep learning, which involves neural networks with many
This article is an open access article
distributed under the terms and layers, is a commonly used ML approach in modern medical imaging and electronic health
conditions of the Creative Commons record (EHR) analysis [2].
Attribution (CC BY) license.
Appl. Sci. 2026, 16, 728 https://doi.org/10.3390/app16020728
,Appl. Sci. 2026, 16, 728 2 of 34
The early implementation of AI in medicine relied on expert systems that were using
predefined “if-then” rules to simulate clinical reasoning. A good example is the MYCIN
program from the 1970s for infectious diseases, showing that computers were able to pro-
vide explainable medical recommendations. However, rule-based systems were limited at
the time by the difficulty of manual knowledge encoding and poor adaptability [3], which
resulted in the MYCIN program never being used in practice. As clinical data increased
between the 1980s and 1990s, AI also shifted towards probabilistic reasoning and statis-
tical learning, including the Bayesian network and pattern-recognition methods. These
systems were learning from data rather than just fixed rules, which marked a transition
towards machine learning in diagnostics [4]. Machine learning-based computer-aided
detection (CAD) systems emerged in radiology between the 1990s and 2000s, especially
in mammography and chest imaging, where algorithms were analyzing medical images
to highlight any abnormalities for radiologists, which showed the first clinical integration
of AI tools [5]. Algorithms such as support vector machines, random forests, and logistic
regression became the standard for diagnostic prediction and biomarker discovery. These
classical ML models from between the 2000s and 2010s relied on engineered features and
were being used in radiomics, genomics, and supporting clinical decisions [6]. The deep
learning revolution between the 2010s and now, with the rise of deep neural networks
(DNNs), has supported AI in medicine by enabling end-to-end learning from raw data.
Convolutional neural networks (CNNs) also achieved specialist-level accuracy in diagnos-
tics that were image-based, such as in skin cancer and retinal disease detection [7]. The
focus on AI research today is mostly on its clinical validation, generalizability, fairness,
and explainability, as all regulatory pathways require precise evaluation before it can be
deployed in patient care [8].
AI tools are able to reduce diagnostic errors through detecting subtle findings and
minimizing possible oversight, mainly during imaging triage and interpretation. How-
ever, issues such as algorithmic bias and over-reliance, such as automation bias, could
produce new errors if the AI models are poorly validated or if they were trained on non-
representative data [9]. Clinical trials have shown that AI is able to improve diagnostic
accuracy and workflow efficiency, but there is limited evidence that shows consistent
benefits in hard outcomes such as survival and morbidity, as most studies have reported
process improvements rather than its direct impact on patients [10]. As such, AI systems
face key barriers like the limited generalizability across populations, lack of explainability,
issues with data privacy, and insufficient regulatory frameworks. The integration of AI into
clinical workflows in a safe way will require transparent validation and prospective tri-
als [11]. The use of AI in healthcare also raises questions about accountability, transparency,
and equity, which further hinder its adoption. Regulatory bodies such as the FDA and
EMA also require robust clinical validation, bias assessment, and post-market surveillance
for AI diagnostic tools before they allow for their clinical adoption [12].
This review addresses the main research question of how modern-day artificial intel-
ligence and machine learning can be systematically integrated into medical diagnostics
across fields such as imaging, molecular and omics data, physiological signals, and clinical
records, as well as the factors that currently limit their safe and effective adoption. The
motivation behind this work comes from the rapid expansion of AI-driven diagnostic tools
and the challenges surrounding generalizability, interpretability, clinical validation, and
implementation in the real world. While there are numerous studies that have reviewed AI
applications with individual diagnostic domains, there remains a limited number of com-
prehensive and cross-domain syntheses that combine computational foundations, clinical
performance, and translational barriers. This review aims to address this gap by giving
a perspective that includes methodological principles with evidence from diverse diag-
https://doi.org/10.3390/app16020728
,Appl. Sci. 2026, 16, 728 3 of 34
nostic modalities [13]. The contribution of this review is its joint discussion of learning
paradigms, model architectures, validation and interpretability frameworks, and regulatory
considerations, while also highlighting the emerging trends such as federated learning,
generative AI, and multimodal foundation models. The remainder or the review is orga-
nized as follows: Section 2 outlines the theoretical and computational foundations of AI in
diagnostics; Section 3 reviews the main AI applications across major diagnostic procedures;
Section 4 examines predictive analytics and clinical decision-support systems; Section 5
discusses the challenges involved with implementation; Section 6 explores the field’s future
directions; and Section 7 concludes the review. To help navigate the diverse literature
included in this review, Table 1 summarizes the key representative studies, which are
organized by diagnostic domain, data modality, and their clinical contribution.
Table 1. Summary of key representative studies included in this review, grouped together by
diagnostic domain, data modality, and clinical contribution.
Representative Included Main Clinical
Diagnostic Domain Data Modality AI Methods Used
Key Studies Contribution
Bajwa et al. (2021) [1], Showed the feasibility
Foundations and Rule-based clinical Shortliffe (MYCIN, 1977) [3], and limits of
Expert systems
Early AI logic Perry (1990) [4], Beam and computer-assisted
Kohane (2018) [14] diagnosis
Habehh and Gohel (2021) [2],
Feature-engineered
Classical ML in Imaging, tabular SVM, RF, Logistic Castellino (2005) [5], Orrù
diagnostic prediction
Diagnostics clinical data Regression et al. (2012) [6], Roy et al.
and early CAD
(2022) [15]
Demonstrated image
Esteva et al. (2017) [7],
classification
Rajpurkar et al. (2018) [16],
performance
Deep Learning in Aggarwal et al. (2021) [13],
X-ray, CT, MRI CNNs comparable to
Medical Imaging Litjens et al. (2017) [17],
specialists in controlled
Lundervold and Lundervold
retrospective
(2019) [18]
evaluations
Zhou et al. (2021) [8], Kelly Shift from task-specific
Radiology and Its
Multimodal imaging CNNs, Transformers et al. (2019) [19], Bian et al. to usable multimodal
Foundation Models
(2025) [20], Najjar (2023) [21], models
Campanella et al. (2019) [22],
Automated cancer
Whole-slide images MIL, Vision Shafi and Parwani (2023)
Digital Pathology detection, grading, and
(WSI) Transformers [23], McGenity et al. (2024)
prognostication
[24], Dolezal et al. (2024) [25]
Reduced operator
Ultrasound Shen et al. (2021) [26], Meng
Real-time imaging CNN–RNN hybrids dependence in clinical
Diagnostics et al. (2019) [27]
settings
Parmar et al. (2024) [28],
Fundus photography, Adaptable retinal
Ophthalmology CNNs Driban et al. (2024) [29], De
OCT disease screening
Fauw et al. (2018) [30]
These systems can
Hannun et al. (2019) [31],
produce performance
ECG Physiological Time-series CNNs, LSTM, Meng et al. (2022) [32], Jaya
that is comparable to
Signals waveforms Transformers Prakash et al. (2025) [33],
cardiologists in
Ribeiro et al. (2020) [34]
arrhythmia detection
Acharya et al. (2018) [35], Seizure and
EEG Physiological
Time-series signals CNNs, DL classifiers Roy et al. (2019) [36], neurodegenerative
Signals
Hussein et al. (2017) [37] disease detection
https://doi.org/10.3390/app16020728
, Appl. Sci. 2026, 16, 728 4 of 34
Table 1. Cont.
Representative Included Main Clinical
Diagnostic Domain Data Modality AI Methods Used
Key Studies Contribution
Choi et al. (Doctor AI, 2016)
[38], Devlin et al. (BERT,
EHR and Clinical Structured and RNNs, NLP Risk prediction and
2019) [39], Altsentzer et al.
Text unstructured data Transformers phenotyping
(ClinicalBERT, 2019) [40],
Acharya et al. (2024) [41]
Johnson et al. (MIMIC-III,
2016) [42], Moody et al.
Predictive Analytics Vitals, labs, RNNs, GRU, Early detection of
(PhysioNet, 2011) [43], Mao
(ICU) waveforms Ensemble ML deterioration
et al. (2018) [44], Kwon et al.
(2018) [45]
Variant interpretation
Athanasopoulou et al. (2025)
Genomics NGS data DL, Transformers and pathogenicity
[46], Baião et al. (2025) [47]
prediction
Mann et al. (2021) [48],
Proteomics Mass spectrometry ML, DL Biomarker discovery
Kitaoka et al. (2025) [49]
Chi et al. (2024) [50], Disease signature
Metabolomics LC–MS profiles ML, VAEs
Gloaguen et al. (2022) [51] detection
Acharya and
Multi-Omics Genomics, Hybrid ML, Precision medicine
Mukhopadhyay (2024) [52],
Integration proteomics, imaging generative models stratification
Lin et al. (2025) [53]
Imaging and Parmar et al. (2015) [54], Wu Outcome and
Radiogenomics CNN + ML fusion
genomics et al. (2016) [55] recurrence prediction
Alkhanbouli et al. (2025) [56],
SHAP, Grad-CAM, Fuhrman et al. (2022) [57], Model transparency
Explainable AI (XAI) All modalities
LIME Saarela and Podgorelec and trust
(2024) [58]
Salimparsa et al. (2025) [59],
Clinical Decision EHR-integrated Workflow-integrated
ML + rules Solomon et al. (2023) [60],
Support (CDS) systems diagnostics
Patterson et al. (2019) [61]
Han et al. (2024) [10], Park
Validation and et al. (2022) [12], Weissman Clinical safety and
Multisite clinical data SaMD frameworks
Regulation (FDA, 2021) [62] Karnik approval pathways
(2014) [63]
Cross et al. (2024) [9], Ueda
Responsible
Bias, Ethics and Demographically et al. (2023) [64], Nasir et al.
Audit frameworks deployment of clinical
Fairness stratified data (2025) [65], Park et al. (2025)
AI systems
[66]
De Fauw et al. (2018) [30],
Real-World Case Imaging, ECG, Transition from lab to
Deployed DL systems Mckinney et al. (2020) [67],
Studies pathology clinic
Attia et al. (2019) [68]
Figure 1 shows a PRISMA workflow diagram showing the methodology for selecting
the articles included in this review.
The methods used for reviewing the literature involved a search of the PubMed and
PubMed Central (PMC) databases, which was conducted in accordance with PRISMA
guidelines, as seen in Figure 1. Peer-reviewed articles published up to 2025 were searched
using keywords related to artificial intelligence, machine learning, and medical diagnostics.
After the removal of duplicates and the automated exclusion of non-medical AI and
retracted publications, titles and abstracts were screened for relevance to the topic. Full-text
articles were assessed using a predefined inclusion criterion that required a clear description
of AI methodology, relevance to clinical or diagnostic applications, and the presence of an
https://doi.org/10.3390/app16020728
Artificial Intelligence in Medical Diagnostics: Foundations,
Clinical Applications, and Future Directions
Dorota Bartusik-Aebisher 1 , Daniel Roshan Justin Raj 2 and David Aebisher 3, *
1 Department of Biochemistry and General Chemistry, Faculty of Medicine, Collegium Medicum, University
of Rzeszów, 35-310 Rzeszów, Poland;
2 English Division Science Club, Faculty of Medicine, Collegium Medicum, University of Rzeszów,
35-310 Rzeszów, Poland;
3 Department of Photomedicine and Physical Chemistry, Faculty of Medicine, Collegium Medicum,
University of Rzeszów, 35-310 Rzeszów, Poland
* Correspondence:
Abstract
Artificial intelligence (AI) is rapidly transforming medical diagnostics by allowing for early,
accurate, and data-driven clinical decision-making. This review provides an overview of
how machine learning (ML), deep learning, and emerging multimodal foundation models
have been used in diagnostic procedures across imaging, pathology, molecular analysis,
physiological monitoring, and electronic health record (EHR)-integrated decision-support
systems. We have discussed the basic computational foundations of supervised, unsuper-
vised, and reinforcement learning and have also shown the importance of data curation,
validation metrics, interpretability methods, and feature engineering. The use of AI in
many different applications has shown that it can find abnormalities and integrate some
features from multi-omics and imaging, which has shown improvements in prognostic
modeling. However, concerns about data heterogeneity, model drift, bias, and strict regu-
latory guidelines still remain and are yet to be addressed in this field. Looking forward,
future advancements in federated learning, generative AI, and low-resource diagnostics
will pave the way for adaptable and globally accessible AI-assisted diagnostics.
Keywords: machine learning in healthcare; medical diagnosis algorithms; healthcare
technology innovation; predictive analytics in medicine; data-driven medical solutions;
artificial intelligence in diagnostics; clinical decision support systems
1. Introduction
Artificial intelligence (AI) is an umbrella term that refers to the machine-based systems
Academic Editors: Giorgio De Nunzio that, when given a certain set of goals set by humans, can make predictions, suggestions,
and Luana Conte or choices and perform tasks that would normally require the intelligence of humans.
Received: 7 December 2025 AI in healthcare includes systems that can assist with or automate clinical tasks such as
Revised: 5 January 2026 diagnosis, prognosis, workflow optimization, recommendation of treatments, and patient
Accepted: 6 January 2026 monitoring [1]. Machine learning (ML), on the other hand, is a well-defined subfield of AI
Published: 10 January 2026
where algorithms, from data examples, learn patterns and can make predictions or decisions
Copyright: © 2026 by the authors.
on new data based on the patterns learned. ML involves supervised, unsupervised, and
Licensee MDPI, Basel, Switzerland.
reinforcement learning, while deep learning, which involves neural networks with many
This article is an open access article
distributed under the terms and layers, is a commonly used ML approach in modern medical imaging and electronic health
conditions of the Creative Commons record (EHR) analysis [2].
Attribution (CC BY) license.
Appl. Sci. 2026, 16, 728 https://doi.org/10.3390/app16020728
,Appl. Sci. 2026, 16, 728 2 of 34
The early implementation of AI in medicine relied on expert systems that were using
predefined “if-then” rules to simulate clinical reasoning. A good example is the MYCIN
program from the 1970s for infectious diseases, showing that computers were able to pro-
vide explainable medical recommendations. However, rule-based systems were limited at
the time by the difficulty of manual knowledge encoding and poor adaptability [3], which
resulted in the MYCIN program never being used in practice. As clinical data increased
between the 1980s and 1990s, AI also shifted towards probabilistic reasoning and statis-
tical learning, including the Bayesian network and pattern-recognition methods. These
systems were learning from data rather than just fixed rules, which marked a transition
towards machine learning in diagnostics [4]. Machine learning-based computer-aided
detection (CAD) systems emerged in radiology between the 1990s and 2000s, especially
in mammography and chest imaging, where algorithms were analyzing medical images
to highlight any abnormalities for radiologists, which showed the first clinical integration
of AI tools [5]. Algorithms such as support vector machines, random forests, and logistic
regression became the standard for diagnostic prediction and biomarker discovery. These
classical ML models from between the 2000s and 2010s relied on engineered features and
were being used in radiomics, genomics, and supporting clinical decisions [6]. The deep
learning revolution between the 2010s and now, with the rise of deep neural networks
(DNNs), has supported AI in medicine by enabling end-to-end learning from raw data.
Convolutional neural networks (CNNs) also achieved specialist-level accuracy in diagnos-
tics that were image-based, such as in skin cancer and retinal disease detection [7]. The
focus on AI research today is mostly on its clinical validation, generalizability, fairness,
and explainability, as all regulatory pathways require precise evaluation before it can be
deployed in patient care [8].
AI tools are able to reduce diagnostic errors through detecting subtle findings and
minimizing possible oversight, mainly during imaging triage and interpretation. How-
ever, issues such as algorithmic bias and over-reliance, such as automation bias, could
produce new errors if the AI models are poorly validated or if they were trained on non-
representative data [9]. Clinical trials have shown that AI is able to improve diagnostic
accuracy and workflow efficiency, but there is limited evidence that shows consistent
benefits in hard outcomes such as survival and morbidity, as most studies have reported
process improvements rather than its direct impact on patients [10]. As such, AI systems
face key barriers like the limited generalizability across populations, lack of explainability,
issues with data privacy, and insufficient regulatory frameworks. The integration of AI into
clinical workflows in a safe way will require transparent validation and prospective tri-
als [11]. The use of AI in healthcare also raises questions about accountability, transparency,
and equity, which further hinder its adoption. Regulatory bodies such as the FDA and
EMA also require robust clinical validation, bias assessment, and post-market surveillance
for AI diagnostic tools before they allow for their clinical adoption [12].
This review addresses the main research question of how modern-day artificial intel-
ligence and machine learning can be systematically integrated into medical diagnostics
across fields such as imaging, molecular and omics data, physiological signals, and clinical
records, as well as the factors that currently limit their safe and effective adoption. The
motivation behind this work comes from the rapid expansion of AI-driven diagnostic tools
and the challenges surrounding generalizability, interpretability, clinical validation, and
implementation in the real world. While there are numerous studies that have reviewed AI
applications with individual diagnostic domains, there remains a limited number of com-
prehensive and cross-domain syntheses that combine computational foundations, clinical
performance, and translational barriers. This review aims to address this gap by giving
a perspective that includes methodological principles with evidence from diverse diag-
https://doi.org/10.3390/app16020728
,Appl. Sci. 2026, 16, 728 3 of 34
nostic modalities [13]. The contribution of this review is its joint discussion of learning
paradigms, model architectures, validation and interpretability frameworks, and regulatory
considerations, while also highlighting the emerging trends such as federated learning,
generative AI, and multimodal foundation models. The remainder or the review is orga-
nized as follows: Section 2 outlines the theoretical and computational foundations of AI in
diagnostics; Section 3 reviews the main AI applications across major diagnostic procedures;
Section 4 examines predictive analytics and clinical decision-support systems; Section 5
discusses the challenges involved with implementation; Section 6 explores the field’s future
directions; and Section 7 concludes the review. To help navigate the diverse literature
included in this review, Table 1 summarizes the key representative studies, which are
organized by diagnostic domain, data modality, and their clinical contribution.
Table 1. Summary of key representative studies included in this review, grouped together by
diagnostic domain, data modality, and clinical contribution.
Representative Included Main Clinical
Diagnostic Domain Data Modality AI Methods Used
Key Studies Contribution
Bajwa et al. (2021) [1], Showed the feasibility
Foundations and Rule-based clinical Shortliffe (MYCIN, 1977) [3], and limits of
Expert systems
Early AI logic Perry (1990) [4], Beam and computer-assisted
Kohane (2018) [14] diagnosis
Habehh and Gohel (2021) [2],
Feature-engineered
Classical ML in Imaging, tabular SVM, RF, Logistic Castellino (2005) [5], Orrù
diagnostic prediction
Diagnostics clinical data Regression et al. (2012) [6], Roy et al.
and early CAD
(2022) [15]
Demonstrated image
Esteva et al. (2017) [7],
classification
Rajpurkar et al. (2018) [16],
performance
Deep Learning in Aggarwal et al. (2021) [13],
X-ray, CT, MRI CNNs comparable to
Medical Imaging Litjens et al. (2017) [17],
specialists in controlled
Lundervold and Lundervold
retrospective
(2019) [18]
evaluations
Zhou et al. (2021) [8], Kelly Shift from task-specific
Radiology and Its
Multimodal imaging CNNs, Transformers et al. (2019) [19], Bian et al. to usable multimodal
Foundation Models
(2025) [20], Najjar (2023) [21], models
Campanella et al. (2019) [22],
Automated cancer
Whole-slide images MIL, Vision Shafi and Parwani (2023)
Digital Pathology detection, grading, and
(WSI) Transformers [23], McGenity et al. (2024)
prognostication
[24], Dolezal et al. (2024) [25]
Reduced operator
Ultrasound Shen et al. (2021) [26], Meng
Real-time imaging CNN–RNN hybrids dependence in clinical
Diagnostics et al. (2019) [27]
settings
Parmar et al. (2024) [28],
Fundus photography, Adaptable retinal
Ophthalmology CNNs Driban et al. (2024) [29], De
OCT disease screening
Fauw et al. (2018) [30]
These systems can
Hannun et al. (2019) [31],
produce performance
ECG Physiological Time-series CNNs, LSTM, Meng et al. (2022) [32], Jaya
that is comparable to
Signals waveforms Transformers Prakash et al. (2025) [33],
cardiologists in
Ribeiro et al. (2020) [34]
arrhythmia detection
Acharya et al. (2018) [35], Seizure and
EEG Physiological
Time-series signals CNNs, DL classifiers Roy et al. (2019) [36], neurodegenerative
Signals
Hussein et al. (2017) [37] disease detection
https://doi.org/10.3390/app16020728
, Appl. Sci. 2026, 16, 728 4 of 34
Table 1. Cont.
Representative Included Main Clinical
Diagnostic Domain Data Modality AI Methods Used
Key Studies Contribution
Choi et al. (Doctor AI, 2016)
[38], Devlin et al. (BERT,
EHR and Clinical Structured and RNNs, NLP Risk prediction and
2019) [39], Altsentzer et al.
Text unstructured data Transformers phenotyping
(ClinicalBERT, 2019) [40],
Acharya et al. (2024) [41]
Johnson et al. (MIMIC-III,
2016) [42], Moody et al.
Predictive Analytics Vitals, labs, RNNs, GRU, Early detection of
(PhysioNet, 2011) [43], Mao
(ICU) waveforms Ensemble ML deterioration
et al. (2018) [44], Kwon et al.
(2018) [45]
Variant interpretation
Athanasopoulou et al. (2025)
Genomics NGS data DL, Transformers and pathogenicity
[46], Baião et al. (2025) [47]
prediction
Mann et al. (2021) [48],
Proteomics Mass spectrometry ML, DL Biomarker discovery
Kitaoka et al. (2025) [49]
Chi et al. (2024) [50], Disease signature
Metabolomics LC–MS profiles ML, VAEs
Gloaguen et al. (2022) [51] detection
Acharya and
Multi-Omics Genomics, Hybrid ML, Precision medicine
Mukhopadhyay (2024) [52],
Integration proteomics, imaging generative models stratification
Lin et al. (2025) [53]
Imaging and Parmar et al. (2015) [54], Wu Outcome and
Radiogenomics CNN + ML fusion
genomics et al. (2016) [55] recurrence prediction
Alkhanbouli et al. (2025) [56],
SHAP, Grad-CAM, Fuhrman et al. (2022) [57], Model transparency
Explainable AI (XAI) All modalities
LIME Saarela and Podgorelec and trust
(2024) [58]
Salimparsa et al. (2025) [59],
Clinical Decision EHR-integrated Workflow-integrated
ML + rules Solomon et al. (2023) [60],
Support (CDS) systems diagnostics
Patterson et al. (2019) [61]
Han et al. (2024) [10], Park
Validation and et al. (2022) [12], Weissman Clinical safety and
Multisite clinical data SaMD frameworks
Regulation (FDA, 2021) [62] Karnik approval pathways
(2014) [63]
Cross et al. (2024) [9], Ueda
Responsible
Bias, Ethics and Demographically et al. (2023) [64], Nasir et al.
Audit frameworks deployment of clinical
Fairness stratified data (2025) [65], Park et al. (2025)
AI systems
[66]
De Fauw et al. (2018) [30],
Real-World Case Imaging, ECG, Transition from lab to
Deployed DL systems Mckinney et al. (2020) [67],
Studies pathology clinic
Attia et al. (2019) [68]
Figure 1 shows a PRISMA workflow diagram showing the methodology for selecting
the articles included in this review.
The methods used for reviewing the literature involved a search of the PubMed and
PubMed Central (PMC) databases, which was conducted in accordance with PRISMA
guidelines, as seen in Figure 1. Peer-reviewed articles published up to 2025 were searched
using keywords related to artificial intelligence, machine learning, and medical diagnostics.
After the removal of duplicates and the automated exclusion of non-medical AI and
retracted publications, titles and abstracts were screened for relevance to the topic. Full-text
articles were assessed using a predefined inclusion criterion that required a clear description
of AI methodology, relevance to clinical or diagnostic applications, and the presence of an
https://doi.org/10.3390/app16020728
