Borna, Sahar

Primary Care Physicians (PCPs) are the first point of contact in healthcare. Because PCPs face the challenge of managing diverse patient populations while maintaining up-to-date medical knowledge and updated health records, this study explores the current outcomes and effectiveness of implementing Artificial Intelligence-based Clinical Decision Support Systems (AI-CDSSs) in Primary Healthcare (PHC). Following the PRISMA-ScR guidelines, we systematically searched five databases, PubMed, Scopus, CINAHL, IEEE, and Google Scholar, and manually searched related articles. Only CDSSs powered by AI targeted to physicians and tested in real clinical PHC settings were included. From a total of 421 articles, 6 met our criteria. We found AI-CDSSs from the US, Netherlands, Spain, and China whose primary tasks included diagnosis support, management and treatment recommendations, and complication prediction. Secondary objectives included lessening physician work burden and reducing healthcare costs. While promising, the outcomes were hindered by physicians’ perceptions and cultural settings. This study underscores the potential of AI-CDSSs in improving clinical management, patient satisfaction, and safety while reducing physician workload. However, further work is needed to explore the broad spectrum of applications that the new AI-CDSSs have in several PHC real clinical settings and measure their clinical outcomes.

Background: Despite numerous measures used to prevent pressure ulcers, their growing prevalence in recent years is expected to continue as the population ages. This review aims to report the outcomes of the regenerative potential of MSCs in treating pressure ulcers, assessing the effectiveness of MSCs in treating pressure ulcers. Methods: A computerized search for articles on animal models that use MSCs as primary therapy to treat pressure ulcers, published from conception to present, was conducted using PubMed, MEDLINE, Embase, and CINAHL. Our search yielded 52 articles, narrowed to 44 after excluding duplicates. Results: Out of 52 articles collected from four databases, 11 met the inclusion criteria. A total of 11 articles published between 2008 and 2020 met the inclusion criteria. Eight studies were observational descriptive papers in animal models, and three were prospective. Six studies used autologous MSCs, while five used allogenic MSCs. Three studies were conducted in humans, and the remaining eight were conducted in animals. The most common method of cell delivery was an intradermal injection in the margins of the ulcer. All studies reported positive results, including improved wound healing, reduced inflammation, and improved tissue regeneration. Conclusions: MSCs have shown promising results in treating pressure ulcers in animal and clinical trials. The combination of MSCs and scaffold materials has also been studied and found to be effective in wound healing. A standardized human wound model has been proposed further to investigate the efficacy of cell-based therapies for chronic wounds. However, more research is needed to determine the best quantity of cells to apply for pressure ulcers and to ensure the safety and efficacy of these treatments in clinical settings.

(1) Background: Telemetry units allow the continuous monitoring of vital signs and ECG of patients. Such physiological indicators work as the digital signatures and biomarkers of disease that can aid in detecting abnormalities that appear before cardiac arrests (CAs). This review aims to identify the vital sign abnormalities measured by telemetry systems that most accurately predict CAs. (2) Methods: We conducted a systematic review using PubMed, Embase, Web of Science, and MEDLINE to search studies evaluating telemetry-detected vital signs that preceded in-hospital CAs (IHCAs). (3) Results and Discussion: Out of 45 studies, 9 met the eligibility criteria. Seven studies were case series, and 2 were case controls. Four studies evaluated ECG parameters, and 5 evaluated other physiological indicators such as blood pressure, heart rate, respiratory rate, oxygen saturation, and temperature. Vital sign changes were highly frequent among participants and reached statistical significance compared to control subjects. There was no single vital sign change pattern found in all patients. ECG alarm thresholds may be adjustable to reduce alarm fatigue. Our review was limited by the significant dissimilarities of the studies on methodology and objectives. (4) Conclusions: Evidence confirms that changes in vital signs have the potential for predicting IHCAs. There is no consensus on how to best analyze these digital biomarkers. More rigorous and larger-scale prospective studies are needed to determine the predictive value of telemetry-detected vital signs for IHCAs.

Electronic health record (EHR) systems collate patient data, and the integration and standardization of documents through Health Information Exchange (HIE) play a pivotal role in refining patient management. Although the clinical implications of AI in EHR systems have been extensively analyzed, its application in HIE as a crucial source of patient data is less explored. Addressing this gap, our systematic review delves into utilizing AI models in HIE, gauging their predictive prowess and potential limitations. Employing databases such as Scopus, CINAHL, Google Scholar, PubMed/Medline, and Web of Science and adhering to the PRISMA guidelines, we unearthed 1021 publications. Of these, 11 were shortlisted for the final analysis. A noticeable preference for machine learning models in prognosticating clinical results, notably in oncology and cardiac failures, was evident. The metrics displayed AUC values ranging between 61% and 99.91%. Sensitivity metrics spanned from 12% to 96.50%, specificity from 76.30% to 98.80%, positive predictive values varied from 83.70% to 94.10%, and negative predictive values between 94.10% and 99.10%. Despite variations in specific metrics, AI models drawing on HIE data unfailingly showcased commendable predictive proficiency in clinical verdicts, emphasizing the transformative potential of melding AI with HIE. However, variations in sensitivity highlight underlying challenges. As healthcare’s path becomes more enmeshed with AI, a well-rounded, enlightened approach is pivotal to guarantee the delivery of trustworthy and effective AI-augmented healthcare solutions.

Background: The use of bone morphogenic protein and mesenchymal stem cells has shown promise in promoting bone regeneration in calvarial defects. However, a systematic review of the available literature is needed to evaluate the efficacy of this approach. Methods: We comprehensively searched electronic databases using MeSH terms related to skull defects, bone marrow mesenchymal stem cells, and bone morphogenic proteins. Eligible studies included animal studies that used BMP therapy and mesenchymal stem cells to promote bone regeneration in calvarial defects. Reviews, conference articles, book chapters, and non-English language studies were excluded. Two independent investigators conducted the search and data extraction. Results: Twenty-three studies published between 2010 and 2022 met our inclusion criteria after a full-text review of the forty-five records found in the search. Eight of the 23 studies used mice as models, while 15 used rats. The most common mesenchymal stem cell was bone marrow-derived, followed by adipose-derived. BMP-2 was the most popular. Stem cells were embedded in Scaffold (13), Transduction (7), and Transfection (3), and they were delivered BMP to cells. Each treatment used 2 × 104–1 × 107 mesenchymal stem cells, averaging 2.26 × 106. Most BMP-transduced MSC studies used lentivirus. Conclusions: This systematic review examined BMP and MSC synergy in biomaterial scaffolds or alone. BMP therapy and mesenchymal stem cells in calvarial defects, alone, or with a scaffold regenerated bone. This method treats skull defects in clinical trials. The best scaffold material, therapeutic dosage, administration method, and long-term side effects need further study.

Pain assessment is a complex task largely dependent on the patient’s self-report. Artificial intelligence (AI) has emerged as a promising tool for automating and objectifying pain assessment through the identification of pain-related facial expressions. However, the capabilities and potential of AI in clinical settings are still largely unknown to many medical professionals. In this literature review, we present a conceptual understanding of the application of AI to detect pain through facial expressions. We provide an overview of the current state of the art as well as the technical foundations of AI/ML techniques used in pain detection. We highlight the ethical challenges and the limitations associated with the use of AI in pain detection, such as the scarcity of databases, confounding factors, and medical conditions that affect the shape and mobility of the face. The review also highlights the potential impact of AI on pain assessment in clinical practice and lays the groundwork for further study in this area.

Pain is a complex and subjective experience, and traditional methods of pain assessment can be limited by factors such as self-report bias and observer variability. Voice is frequently used to evaluate pain, occasionally in conjunction with other behaviors such as facial gestures. Compared to facial emotions, there is less available evidence linking pain with voice. This literature review synthesizes the current state of research on the use of voice recognition and voice analysis for pain detection in adults, with a specific focus on the role of artificial intelligence (AI) and machine learning (ML) techniques. We describe the previous works on pain recognition using voice and highlight the different approaches to voice as a tool for pain detection, such as a human effect or biosignal. Overall, studies have shown that AI-based voice analysis can be an effective tool for pain detection in adult patients with various types of pain, including chronic and acute pain. We highlight the high accuracy of the ML-based approaches used in studies and their limitations in terms of generalizability due to factors such as the nature of the pain and patient population characteristics. However, there are still potential challenges, such as the need for large datasets and the risk of bias in training models, which warrant further research.