AI-Driven Clinical Decision Support Systems: An Ongoing Pursuit of Potential
Open accessAbstract
Clinical Decision Support Systems (CDSS) are essential tools in contemporary healthcare, enhancing clinicians' decisions and patient outcomes. The integration of artificial intelligence (AI) is now revolutionizing CDSS even further. This review delves into AI technologies transforming CDSS, their applications in healthcare decision-making, associated challenges, and the potential trajectory toward fully realizing AI-CDSS's potential. The review begins by laying the groundwork with a definition of CDSS and its function within the healthcare field. It then highlights the increasingly significant role that AI is playing in enhancing CDSS effectiveness and efficiency, underlining its evolving prominence in shaping healthcare practices. It examines the integration of AI technologies into CDSS, including machine learning algorithms like neural networks and decision trees, natural language processing, and deep learning. It also addresses the challenges associated with AI integration, such as interpretability and bias. We then shift to AI applications within CDSS, with real-life examples of AI-driven diagnostics, personalized treatment recommendations, risk prediction, early intervention, and AI-assisted clinical documentation. The review emphasizes user-centered design in AI-CDSS integration, addressing usability, trust, workflow, and ethical and legal considerations. It acknowledges prevailing obstacles and suggests strategies for successful AI-CDSS adoption, highlighting the need for workflow alignment and interdisciplinary collaboration. The review concludes by summarizing key findings, underscoring AI's transformative potential in CDSS, and advocating for continued research and innovation. It emphasizes the need for collaborative efforts to realize a future where AI-powered CDSS optimizes healthcare delivery and improves patient outcomes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Models that may perform well during development can degrade in real-world settings due to dataset drift across diverse sites, devices, and populations.
“Models that may perform well during development can degrade in real-world settings due to dataset drift across diverse sites, devices, and populations15–18.”
From What the AI era doctor should know: a scoping review of proposed artificial intelligence competencies for medical education (2026) · cites this paper as [16]
The Review (page unavailable) identifies challenges in maintaining model robustness across patient populations, clinical settings, and data modalities, and says unrepresentative training data may lead to performance disparities. It does not specifically describe dataset drift across devices or a decline from development performance to real-world performance. (LLM, conf=0.84)
Experimental — accuracy not yet measuredIf only certain populations are included in the dataset, some AI-driven CDSS may be trained with biased data and generate unrepresentative outcomes that can further exacerbate health inequities.
“If only certain populations are included in the dataset, some systems may be trained with biased data and generate unrepresentative outcomes that can further exacerbate health inequities [228,229].”
From Toward Safer Diagnoses: A SEIPS-Based Narrative Review of Diagnostic Errors (2026) · cites this paper as [229]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 29 · Cited by 301
Research works printed but not linked: 24
- [3]Deep EHR: A survey of recent advances in deep learning techniques for electronic health record (EHR) analysis IEEE J Biomed Health Inform Shickel B Tighe PJ Bihorac A Rashidi P 1589 1604 22 2018 29989977 PMC6043423
- [4]Machine learning in medicine N Engl J Med Rajkomar A Dean J Kohane I 1347 1358 380 2019 30943338
- [5]A survey on deep learning in medical image analysis Med Image Anal Litjens G Kooi T Bejnordi BE 60 88 42 2017 28778026
- [7]A systematic review of technologies and standards used in the development of rule-based clinical decision support systems Springer Nature Papadopoulos P Soflano M Chaudy Y 713 727 12 2022
- [8]Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: a systematic review Front Med (Lausanne) Moazemi S Vahdati S Li J 1109411 10 2023 37064042 PMC10102653
- [9]Natural language processing (almost) from scratch J Machine Learn Res Collobert R Weston J Bottou L 2493 2537 12 2011 https://www.jmlr.org/papers/volume12/collobert11a/collobert11a.pdf
- [10]Deep learning for healthcare: review, opportunities and challenges Brief Bioinform Miotto R Wang F Wang S Jiang X Dudley JT 1236 1246 19 2018 28481991 PMC6455466
- [11]Doctor Ai: Predicting clinical events via recurrent neural networks JMLR Workshop Conf Proc Choi E Bahadori MT Schuetz A 301 318 56 2016 https://arxiv.org/abs/1511.05942 28286600 PMC5341604 · arXiv
- [15]Extracting cancer concepts from clinical notes using natural language processing: a systematic review BMC Bioinformatics Gholipour M Khajouei R Amiri P Hajesmaeel Gohari S Ahmadian L 405 24 2023 37898795 PMC10613366
- [16]The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care Nat Med Komorowski M Celi LA Badawi O Gordon AC Faisal AA 1716 1720 24 2018 30349085
- [17]A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography Sci Rep Ryu G Lee K Park D Park SH Sagong M 23024 11 2021 34837030 PMC8626435
- [18]Natural language processing of MIMIC-III clinical notes for identifying diagnosis and procedures with neural networks 12 2019 Nuthakki S Neela S Gichoya JW 2019 https://arxiv.org/abs/1912.12397 · arXiv
- [19]Human-centred design in global health: a scoping review of applications and contexts PLoS One Bazzano AN Martin J Hicks E Faughnan M Murphy L 0 12 2017 PMC5665524 29091935
- [20]Human-centered design and evaluation of AI-empowered clinical decision support systems: a systematic review Frontiers Comput Sci Wang L Zhang Z Wang D 5 2023
- [21]The ethics of machine learning-based clinical decision support: an analysis through the lens of professionalisation theory BMC Med Ethics Heyen NB Salloch S 112 22 2021 34412649 PMC8375118
- [22]Artificial intelligence and clinical decision support: clinicians' perspectives on trust, trustworthiness, and liability Med Law Rev Jones C Thornton J Wyatt JC 501 520 31 2023 37218368 PMC10681355
- [23]The strange case of Dr Watson: liability implications of AI evidence-based decision support systems in health care Eur J Legal Stud Lagioia F Contissa G 245 289 12 2020 https://hdl.handle.net/1814/68757
- [24]Promoting ethical deployment of artificial intelligence and machine learning in healthcare Am J Bioeth Spector-Bagdady K Rahimzadeh V Jaffe K Moreno J 4 7 22 2022 PMC9805364 35499568
- [26]Clinicians and AI use: where is the professional guidance? J Med Ethics Smith H Downer J Ives J 2023 PMC11228205 37607805
- [27]Collaborative strategies for deploying AI-based physician decision support systems: challenges and deployment approaches NPJ Digit Med Mittermaier M Raza M Kvedar JC 137 6 2023 37543707 PMC10404285
- [28]Fairness and bias in artificial intelligence: a brief survey of sources, impacts, and mitigation strategies SSRN 10 2023 Ferrara E 27 2023 https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4615421
- [29]Clinicians’ perceptions of artificial intelligence: focus on workload, risk, trust, clinical decision making, and clinical integration Healthcare (Basel) Shamszare H Choudhury A 2308 11 2023 37628506 PMC10454426
- [30]The impact of artificial intelligence on clinical education: perceptions of postgraduate trainee doctors in London (UK) and recommendations for trainers BMC Med Educ Banerjee M Chiew D Patel KT 429 21 2021 34391424 PMC8364021
- [31]Pilot testing of a tool to standardize the assessment of the quality of health information generated by artificial intelligence-based models Cureus Sallam M Barakat M Sallam M 0 15 2023 PMC10674084 38024074
- Authors
- Elhaddad, M., & Hamam, S.
- Affiliations
- Hospital for Sick Children (CA)
- Corresponding author
- Elhaddad, Malek
- ORCID
- Elhaddad, Malek
- Venue
- Cureus
- Published
- 2024-04-06
- Volume
- 16
- Issue
- 4
- Pages
- e57728-e57728
- ISSN
- 2168-8184 (ISSN-L)
- PMC
- PMC11073764
- OpenAlex
- W4394009485
- Cited by
- 301
- References
- 29
- Citations by year
- 2026: 132 · 2025: 143 · 2024: 25 · 2022: 1
- FWCI
- 6.84
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Cureus (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- clinical decision support systems, artificial intelligence in healthcare, machine learning, natural language processing, deep learning, model interpretability, algorithmic bias, AI-assisted diagnosis, personalized treatment recommendations, risk prediction, early intervention, clinical documentation, user-centered design, trust in AI, AI adoption barriers, legal and ethical considerations, workflow integration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
