Artificial intelligence in anesthesiology: Clinical decision support, challenges, and future directions

The United States healthcare industry has three major simultaneous developments in knowledge management and the use of information technology (IT). The first is in data collection, i.e., the adoption and “meaningful use” of electronic health records (EHRs). Second is data sharing as exemplified by health information exchanges (HIEs). Finally, there is data analysis as seen in enterprise data warehouse (EDW) and clinical decision support system (CDSS) tools.A CDSS supports clinicians in making evidence-based decisions and diagnoses by providing scenario-pertinent information from patient data in the EHR system. A CDSS can aid the physician in asking questions that are specific to a patient's health, helping avoid errors of omission. A CDSS helps to better utilize the data and intelligence in an EHR system. A CDSS that is configured properly can help to avoid adverse events—for example, by predicting possible harmful drug interactions.With the continuing push toward implementing EHR systems, more CDSS use is sure to follow—some say to the ultimate extent in which a patient will be dealing at home with a super-duper CDSS in the form of a holographic doctor. No waiting! Your virtual doctor would possess all the collated experience and knowledge about your health, prescribing the right treatments and medications. Wait. Didn't they do that already on one of the “Star Trek” TV shows? Although I think that the “Star Trek” holographic doctor was confined to a sick bay, it was always ready to serve. Maybe in the future, modern houses will include a sick bay and virtual medical staff. Future child: “I don't feel so good. I should stay home from school today.” Future parent: “Well why don't you go and log into Sick Bay and see what the doctor says?”While we're not there yet, maybe we are on the path to a home sick bay staffed with holograms. An estimated 41% of hospitals that have an EHR system also have a CDSS in place.There are two general types of CDSSs. One is knowledge-based, much like what I've just described. In essence, such a CDSS is a huge scannable database with a clinical case-based reasoning system. The other type is more of a neural network computing effort. Also known as artificial intelligence, this second type of CDSS involves an iterative “trial and error” learning process similar to one of the ways that humans think and learn.A knowledge-based CDSS uses compiled clinical knowledge to provide expert-level consultation to the clinician for diagnosis and medication selection. Such systems also can have many features, from general medical treatment references to precise information for specific conditions. The suggestions from the CDSS can target a patient's unique clinical and physiological data sets.Data mining may be conducted by the CDSS to examine the patient's medical history in conjunction with relevant clinical research—such as in a succession of IFTHEN queries. This kind of evidence-based analysis also can help predict potential events, such as the previously mentioned drug interactions.An example of the non-knowledge-based approach is a CDSS that uses the Archimedes model in which a series of equations analyze the EHR physiological and clinical data. The results are then fed into a computer model that simulates real healthcare processes and human physiology. This type of CDSS also could pull data from places such as a disease registry and then combine it with data from the EHR system to identify at-risk levels and suggest recommended treatments.EHR adoption is driven mainly by Title XIII of the American Recovery and Reinvestment Act (ARRA) and is expected to continue to accelerate. The Centers for Medicare & Medicaid Services (CMS) published its final rule in 2010 for the EHR Incentive Program. The program sets out requirements for the meaningful use of EHRs as a condition of the inventive payments. According to the Federal Register, “The HITECH Act [enacted as part of ARRA] statutorily requires the use of health information technology in improving the quality of care, reducing medical errors, reducing health disparities, increasing prevention, and improving the continuity of care among health settings.”Also adding to the quantity and quality of data will be ICD-10 when it goes into effect in October 2014. ICD-10 is the 10th revision of the International Statistical Classification of Diseases and Related Health Problems. It will increase the number of codes for identifying diagnoses and procedures nearly tenfold from 17,000 to 155,000, allowing for better classifications. ICD-10 will facilitate the matching of diagnoses with symptoms by increasing the data granularity, in turn producing a higher volume of new data for analysis and evaluation by the CDSS. This could lead to better pattern recognition and outcomes.When there are several disconnected databases and data stores, there is a danger of obtaining only some of the pertinent clinical and health information. Without a process to drive standardization and normalization, pulling data from various disconnected systems will not connect all the dots. Humans will need to be employed to scrub, sort, filter, and combine data manually to get to the same level as what could be achieved with a standardized process. Such a process can get time consuming and costly as it proceeds report by report.Big data as a concept has been around in other industries for a long time. In the IT arena, the term describes a very large data set beyond the ability of common software tools to manage and process within a tolerable elapsed time. Such a data set would be in the range of terabytes (1 terabyte = 1000 gigabytes) and petabytes (1 petabyte = 1000 terabytes), and big data is growing. In light of federally mandated and incentivized EHR adoption and expected changes in ICD-10, big data has become a hot topic in healthcare in the past few years.Adding to the flood of health data is the rise of mHealth and the growth of wellness apps. CDSS promises to make use of all that data on the order of $450 billion in reduced healthcare spending according to a April 2013 McKinsey Report—or about 12 to 17% of the current $2.6 trillion in healthcare costs. To say that this is a huge deal is putting it rather mildly.To help consolidate and control your torrents of data, consider an EDW device. An EDW is a server designed for data storage, access, and use. To get an idea of what a EDW looks like, consider the following specifications for a current top-of-line system: a tower with the dimensions of H: 6½′ × W: 2′ × D: 4′ and weighing in at 1,650 pounds, fully loaded. While it needs 6000 watts of power, it can dynamically support online, real-time use of its 60 petabytes of storage. Now we're talking serious data storage! It uses a concept of data temperature in which highly used data is hot data and tends to reside in the faster solid state drive (SSD). Hard disk drives, on the other hand, have access rates that are 16 to 22 times slower and would store cold to warm data as it's not accessed as much. These systems are also highly fault tolerant and include redundant hardware so that hardware or disk failures are managed seamlessly—transparent to the user. Although that may be an extreme example of an EDW, it is one that points to the future.Physicians, nurses, and other healthcare professionals can use a CDSS to prepare and review a diagnosis as a means of improving patient outcomes. A CDSS needs to be the focal point if meaningful use of EHRs is to realize its potential of better healthcare at lower costs. To achieve this goal, a CDSS needs to deliver relevant medical practice information at the point of care. In some cases, the operational costs of a fully implented CDSS and EDW sytem can be a barrier to adoption. One report indicated that some 74% of those with a CDSS said that the financial viability continues to be a struggle. While that represents a costly learning curve, the expected payoff in healthcare efficiencies and better outcomes would make it worthwhile. All leading indicators and current healthcare industry efforts seem to be pointing in the direction of making use of all the health and clinical data we've been collecting via EHRs. Maybe we're not that far away from the home sick bay idea. Future parent: “Doctor, what's wrong with my child?” Dr. Hologram: “Nothing at all ma'am, all bio indicators and CDSS reports indicate a clean bill of health with no current maladies. Send him to school!”

Clinical Decision Support Systems (CDSS) are integral tools in modern healthcare, designed to assist clinicians by providing patient-specific recommendations based on vast medical data and knowledge. The advent of Artificial Intelligence (AI) has significantly enhanced CDSS, enabling sophisticated predictive analytics, early detection of complications, and personalized interventions. AI techniques like machine learning, natural language processing, and deep learning play crucial roles in refining CDSS functionality. However, challenges such as data quality, AI transparency, and clinician trust hinder widespread adoption. Future trends focus on improving AI integration in CDSS through better data representation, automation, and ethical considerations. This paper investigates the fundamental aspects of CDSS, the applications of AI in healthcare, and the challenges and future directions for AI-driven CDSS. Keywords: Clinical Decision Support Systems (CDSS), Artificial Intelligence (AI), Machine Learning, Healthcare Technology, Predictive Analytics.

The brave new world of artificial intelligence: dawn of a new era

Context: Artificial intelligence refers to a set of systems that are capable of performing functions similar to human intelligent functions. Today, artificial intelligence has been successfully incorporated into clinical decision support systems (CDSS). Evidence Acquisition: The current study aimed to briefly present a narrative mini-review on clinical reasoning and artificial intelligence. Data were gathered from Google Scholar, ScienceDirect, and PubMed databases using the "clinical decision support system, artificial intelligence, and clinical reasoning" keywords. Results: Clinical decision support systems are divided into two categories: Knowledge-based and data-driven. The first category is called the rule-based expert system, and the second category is also named the machine-learning system. The usefulness of the mentioned systems and artificial intelligence in interpreting algorithmic and statistical information, where the human element can easily make a mistake, is that they are much more efficient and work with fewer errors. However, when it comes to dealing with a patient and his complaints and symptoms, because of the requirement for clinical judgment, the human element works much better in obtaining a mental image of the patient’s condition. Artificial intelligence is specifically used in scenarios such as the diagnosis of electrolyte disorders, interpreting ECG findings, and recognizing the causes of myocardial hypertrophy. Nonetheless, artificial intelligence has challenges, such as a lack of responsibility for medical decisions and treatment errors. Conclusions: Referring to the above-mentioned benefits and challenges of artificial intelligence, artificial and human intelligence cannot be superior to each other, and both have an irreplaceable role in clinical decision-making. The new view is that the goal of CDSS is to help the physician make better decisions by processing vast pieces of information as a whole entity rather than individually.

Artificial intelligence (AI) plays a crucial role in advancing head-and-neck cancer diagnosis and treatment, significantly impacting patient outcomes and healthcare efficiency. We explore how AI-driven technologies are revolutionizing clinical practices. AI-driven surgical robotics enables highly accurate, minimally invasive procedures by providing real-time intraoperative guidance and analyzing complex imaging data, thus improving surgical success rates and reducing complications. Similarly, AI-driven remote monitoring systems facilitate continuous, non-invasive tracking of disease progression, treatment adherence, and early detection of recurrence, allowing for timely interventions and personalized care adjustments. These innovations enhance diagnostic accuracy, therapeutic precision, patient engagement, and resource utilization, leading to a better quality of life. However, several challenges hinder widespread AI adoption, including concerns over data privacy and security, algorithm bias due to unrepresentative datasets, variability in data quality, and regulatory and ethical issues regarding accountability and transparency. Implementation barriers, such as that in integration with existing workflows, clinician acceptance, and resource limitations, further complicate deployment, especially in low-resource settings. Despite these hurdles, we demonstrate that the potential benefits of AI—improved diagnostic accuracy, personalized treatment, and proactive disease management—are substantial. Addressing these challenges through robust data governance, validation, and ethical frameworks is essential for safe and equitable AI integration. We conclude that ongoing technological and methodological advancements will continue to enhance the efficacy and accessibility of AI in head cancer care. We emphasize the importance of collaborative efforts, regulatory support, and ethical standards to fully realize AI’s transformative potential, ultimately leading to more precise, patient-centered, and effective head-and-neck cancer management.

Artificial intelligence in Glioblastoma Diagnostics: Integrating MRI, histopathology, and molecular profiling.

Introduction Acute stroke is a time‐critical condition where delays in diagnosis and treatment significantly affect outcomes. Artificial intelligence (AI) has shown promise across multiple domains of stroke care, yet its clinical integration remains inconsistent. A comprehensive mapping of current AI applications is needed to understand the scope, trends, gaps, and translational challenges. This scoping review synthesizes peer‐reviewed evidence on AI use in acute stroke care, focusing on imaging, triage, prognostication, rehabilitation, and decision support. Methods Following PRISMA‐ScR guidelines, we systematically searched MEDLINE, Embase, IEEE Xplore, and Cochrane CENTRAL from inception to March 2025. Inclusion criteria comprised original studies involving AI tools for acute stroke management across any clinical setting. Data extraction focused on publication year, study design, AI type, clinical task, validation status, and model performance metrics. Using R and Python, we performed descriptive analytics and visualized distribution by clinical domain. A custom ontology was developed to categorize AI use into six domains: imaging/diagnosis, prognostication, triage/workflow, rehabilitation, clinical decision support (CDS), and implementation/usability. Results Out of 2176 records screened, 133 studies met inclusion criteria. Imaging and diagnosis dominated the landscape (42 studies, 31.6%), particularly in ischemic stroke detection via non‐contrast CT and diffusion‐weighted MRI, with average AUCs exceeding 0.90. Prognostication followed (27 studies, 20.3%), featuring deep learning models predicting 90‐day mRS scores and hemorrhagic transformation with accuracies up to 88%. Workflow and triage AI systems (19 studies) demonstrated strong potential to reduce door‐to‐needle times, yet only 5 were validated in real‐world emergency settings. Rehabilitation‐focused studies (14) applied AI to robotics, motion tracking, and tele‐rehabilitation, but showed wide variability in outcome measures. Clinical decision support tools (22) included integrated CDS in telestroke platforms, though only 8 achieved clinical integration. Implementation and usability studies (9) highlighted concerns around algorithmic bias, regulatory hurdles, and clinician trust. Only 12% of studies were externally validated and just 1.5% were part of interventional trials. Conclusion The AI research landscape in acute stroke management is rapidly expanding, with imaging and prognostication being the most mature domains. However, critical translational gaps exist in clinical validation, regulatory clearance, and human‐centric usability. Rehabilitation and CDS applications remain underexplored and inconsistently evaluated. To transition from innovation to impact, future research must prioritize multi‐center trials, harmonized reporting standards, and ethical integration frameworks. This review offers a structured roadmap for researchers, clinicians, and policymakers to navigate and strengthen AI's role in acute stroke care. image

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 prevailingobstacles 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.

Probabilistic reasoning refers to the construction of the likelihood of conclusions based on one's belief. Contrary to deductive reasoning, which produces either true or false output, probabilistic reasoning requires retrieving prior knowledge from memory and has distinct neurocognitive process.1 Clinical reasoning previously depended on the hypothetico-deductive approach for deriving diagnosis or result interpretation, but uncertainty surrounding clinical scenarios, especially in nephrology ones, may necessitate a probabilistic approach to circumvent errors. Historically, nephrology's development closely intertwines with technological advancements and computer-aided modelling. The interpretation of laboratory data and dialysis prescription heavily rely on process automation and algorithms, fostering a preference for numeric accuracy among nephrologists while instilling apprehension toward clinical ambiguity.3 Artificial intelligence (AI) has transformed medical practice in the contemporary era. A recent article nicely summarizes the utility of AI in dialysis management.2 Emerging studies also examined the applicability of clinical decision support (CDS) systems in aiding drug dosing, acute kidney injury management, allograft rejection prediction, and quality matrix monitoring.3 Despite the gross accuracy observed by researchers, applying CDS output to individual patients often necessitates probability interpretation and a certain degree of ambiguity tolerance. In the forthcoming AI era, nephrologists will be required to make decisions based on probabilities provided by data-driven CDS systems. However, nephrologists often hesitate to communicate prognostic uncertainty to end-stage kidney disease (ESKD) patients. Moreover, maladaptive responses to clinical uncertainty can detrimentally impact the physician-patient relationship and compromise care quality. The complexities and prognostic uncertainties further cause frustrations and contribute to declining interest in nephrology and burnout. Nephrology trainees, lacking a comprehensive background knowledge and emotional preparation, will confront heightened uncertainty in this evolving landscape. The educational gap about uncertainty-coping strategies becomes a lurking concern. To mitigate this challenge, we can reconcile the inherent features of the discipline (difficulty in managing uncertainty) with the inevitable trajectory of AI-assisted clinical practice. We aim to integrate probabilistic reasoning into nephrology training, achieved through approaches such as case-based learning. We propose specific strategies to enhance nephrology trainees' ability to navigate uncertainty (Figure 1). First, we should place emphasis on precisely introducing probabilistic information in undergraduate and postgraduate education. Probability and uncertainty are intrinsic elements of differential diagnosis and clinical decision-making for nephrology patients. The real-time provision of CDS produces probabilities intensifies decision-making urgency and anxiety. Trainees can enhance their probabilistic skills by engaging in repeated exposure to case presentation, including enumeration of indices like pre-test probability, sensitivity/specificity, or predicted risk. Moreover, engaging in peer discussions about uncertainty in risk interpretation can be beneficial. Collaborative efforts can alleviate anxiety, enhance well-being, and reduce uncertainty. Second, many nephrology algorithms are based on assumptions and possess inherent limitations. AI-assisted CDS algorithms are no exception, having their limitations, optimal usage settings, and requiring consistent data input for retraining. Therefore, the focus of training should be on probabilistic reasoning considering both limitations and the applicability of CDS-generated risk stratification and algorithms. Lastly, nephrology trainees should engage in discussions for the best way to refine the algorithm applicability. An example of medical education and training recommendations for probabilistic reasoning can be found elsewhere.4 AI-enabled CDS systems can assist in workflow improvement and optimizing management efficiency in nephrology. The value of CDS to streamline clinical practice is highly augmented by AI technologies. However, how to correctly interpret CDS output by users significantly affects its tremendous clinical potential.5 Without appropriate visualization of results and understanding of the context upon which AI-enabled CDS is built, such system can increase provider dissatisfaction and even resistance to implementation.5 Coping with uncertainty based on probabilistic reasoning can and should be the first step for fully realizing CDS system's potential. In summary, the practice of nephrology is poised to enter a new era with AI assistance, coinciding with escalating clinical uncertainty. We outline three components to enhance trainees' ability of coping with uncertainty and to cultivate their reasoning potential, including the enhancement of probabilistic information understanding, probabilistic reasoning/algorithm training, and case-based practice of applicability. We believe that nephrology education can take proactive steps by highlighting the importance of probabilistic reasoning to aid trainees in effectively grappling with this conundrum. Study design: Chia-Ter Chao. Data analysis: Chia-Ter Chao, Kuan-Yu Hung. Article drafting: Chia-Ter Chao, Kuan-Yu Hung. All authors approved the final version of the manuscript. We are grateful to Ms. Ting-Yu Chen for her kind assistance. Part of the figure content was generated using Microsoft Bing software. The study is financially sponsored by National Taiwan University Hospital (112-N0031 and 112-UN0060) and National Science and Technology Council, Taiwan (NSTC 112-2314-B-002-232-MY3). The authors have no relevant financial or non-financial competing interests to declare in relation to this manuscript. This study did not generate new data or materials.

The role of artificial intelligence in sarcopenia: Advances, applications, and future directions.

Chronic heart failure (CHF) represents a major global health burden. This review explores the potential of artificial intelligence (AI) in improving its diagnosis, treatment, and management. This study conducted a comprehensive literature review to evaluate the current and emerging applications of AI in CHF. Databases, such as PubMed, Scopus, and IEEE Xplore, were searched for peer-reviewed articles published between 2015 and 2025, focusing on AIbased diagnostic tools, predictive modeling, treatment personalization, and remote monitoring systems. Significant advancements were identified in AI-enhanced diagnostics, predictive models for hospital readmissions, personalized treatment optimization, and AI-driven remote monitoring systems. These technologies have demonstrated improvements in diagnostic accuracy, risk stratification, and real-time patient management. AI offers substantial benefits for CHF management by enabling data-driven, individualized care. Nonetheless, challenges remain, including variability in data quality, lack of algorithm transparency, and ethical considerations regarding patient privacy and accountability. AI holds transformative potential for CHF management. Its successful integration can enhance diagnostic precision, personalize treatment, and support proactive patient care- ultimately improving outcomes and reducing the global burden of CHF.

Artificial intelligence (AI) has rapidly emerged as a transformative force in modern dentistry, offering innovative solutions that enhance diagnostic precision, treatment planning, education, patient management, and regenerative medicine. The integration of advanced computational methods – including machine learning, deep learning, convolutional neural networks, and hybrid neuro-fuzzy systems – has enabled automated analysis and clinical decision support with accuracy approaching or even surpassing that of experienced dental specialists. Recent research between 2020 and 2025 demonstrates AI’s growing role across dental specialties such as radiology, orthodontics, endodontics, periodontics, oral pathology, and prosthodontics. These technologies have improved early disease detection, personalized treatment strategies, and workflow efficiency, while also enhancing educational outcomes through simulation and predictive modeling. Despite these advances, challenges remain concerning data quality, algorithm transparency, ethical considerations, and clinical validation. This review synthesizes current evidence from recent literature, highlighting AI’s core technologies, specialty-specific applications, benefits, and limitations. Furthermore, it explores emerging trends such as explainable AI, multimodal learning, and human–AI collaboration, offering insights into the future trajectory of AI-driven innovations in dental research and clinical practice.

Clinical decision-making is a critical process where physicians balance risks and benefits. Clinical Decision Support Systems (CDSSs) are increasingly used to help in this process. The regulatory landscape for CDSSs is evolving significantly, with the new European Medical Device Regulation (MDR) now requiring, CE certification for certain CDSSs. This shift poses challenges for health care providers to develop CDSSs in an effective and useful manner while adhering to regulations. This viewpoint comments on diverse challenges and provides solutions to develop a reliable, well integrated and practical tool for clinical use. Using three tools (the Early Onset Sepsis Calculator, Feverkidstool, and Neonatal Procalcitonin Intervention Study algorithm) as examples, we explore the development of CDSSs across four core characteristics: scientific basis, technical aspects, safety, and sustainability. These characteristics recur across the main development processes; scientific development, regulatory assessment, and implementation in routine practice. Successful integration of CDSSs into clinical practice requires a comprehensive understanding of the interconnections between these processes. For example, decisions on algorithm validation and platform selection in the scientific process influence choices for technical safety during the regulatory process. Developers should consider both regulation requirements and clinical needs, to create CDSSs that are not only compliant but also adaptable to the rapidly changing healthcare landscape. We outline a developer’s checklist, for practical guidance, but also appeal for structural support, including national protocols and dedicated hospital roles, to help developers implement CDSSs successfully.

Artificial intelligence (AI) has the potential to revolutionize critical care medicine by enhancing patient care, improving resource allocation and reducing clinician workload. Despite this promise, many AI applications remain confined to scientific research rather than being integrated into everyday clinical practice. This manuscript aims to help intensivists prepare themselves and their intensive care units (ICUs) for AI implementation. It provides a comprehensive yet practical roadmap, detailing AI methods, applications, responsible AI principles, common roadblocks and implementation strategies. We propose a three-tiered risk-based approach to AI implementation, starting with low-risk low-complexity administrative AI, progressing to logistical AI, and finally integrating medical AI as clinical decision support systems. This ensures a gradual build-up of AI skills, technical AI readiness of the ICU, incremental value demonstration and alignment with evolving regulatory standards. For each AI project, responsible AI principles should be incorporated and adequately addressed throughout the entire AI lifecycle, from development to validation to implementation and scaling. Common roadblocks for AI implementation including technical issues (such as data quality and interoperability issues), organizational challenges (such as lack of a clear vision and strategy), and clinical concerns (such as limited AI literacy among staff), should be addressed proactively. By following this roadmap, ICUs can achieve sustainable AI integration, ultimately improving patient outcomes and clinician experience. The future of critical care lies in the responsible and strategic adoption of AI, with intensivists playing a central role in shaping its implementation.

BackgroundDespite the emerging application of clinical decision support systems (CDSS) in pregnancy care and the proliferation of artificial intelligence (AI) over the last decade, it remains understudied regarding the role of AI in CDSS specialized for pregnancy care.ObjectiveTo identify and synthesize AI-augmented CDSS in pregnancy care, CDSS functionality, AI methodologies, and clinical implementation, we reported a systematic review based on empirical studies that examined AI-augmented CDSS in pregnancy care.MethodsWe retrieved studies that examined AI-augmented CDSS in pregnancy care using database queries involved with titles, abstracts, keywords, and MeSH (Medical Subject Headings) terms. Bibliographic records from their inception to 2022 were retrieved from PubMed/MEDLINE (n=206), Embase (n=101), and ACM Digital Library (n=377), followed by eligibility screening and literature review. The eligibility criteria include empirical studies that (1) developed or tested AI methods, (2) developed or tested CDSS or CDSS components, and (3) focused on pregnancy care. Data of studies used for review and appraisal include title, abstract, keywords, MeSH terms, full text, and supplements. Publications with ancillary information or overlapping outcomes were synthesized as one single study. Reviewers independently reviewed and assessed the quality of selected studies.ResultsWe identified 30 distinct studies of 684 studies from their inception to 2022. Topics of clinical applications covered AI-augmented CDSS from prenatal, early pregnancy, obstetric care, and postpartum care. Topics of CDSS functions include diagnostic support, clinical prediction, therapeutics recommendation, and knowledge base.ConclusionsOur review acknowledged recent advances in CDSS studies including early diagnosis of prenatal abnormalities, cost-effective surveillance, prenatal ultrasound support, and ontology development. To recommend future directions, we also noted key gaps from existing studies, including (1) decision support in current childbirth deliveries without using observational data from consequential fetal or maternal outcomes in future pregnancies; (2) scarcity of studies in identifying several high-profile biases from CDSS, including social determinants of health highlighted by the American College of Obstetricians and Gynecologists; and (3) chasm between internally validated CDSS models, external validity, and clinical implementation.