Citations

Background: Large language models (LLMs) represent a recent advancement in artificial intelligence with medical applications across various healthcare domains. The objective of this review is to highlight how LLMs can be utilized by clinicians and surgeons in their everyday practice. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Six databases were searched to identify relevant articles. Eligibility criteria emphasized articles focused primarily on clinical and surgical applications of LLMs. Results: The literature search yielded 333 results, with 34 meeting eligibility criteria. All articles were from 2023. There were 14 original research articles, four letters, one interview, and 15 review articles. These articles covered a wide variety of medical specialties, including various surgical subspecialties. Conclusions: LLMs have the potential to enhance healthcare delivery. In clinical settings, LLMs can assist in diagnosis, treatment guidance, patient triage, physician knowledge augmentation, and administrative tasks. In surgical settings, LLMs can assist surgeons with documentation, surgical planning, and intraoperative guidance. However, addressing their limitations and concerns, particularly those related to accuracy and biases, is crucial. LLMs should be viewed as tools to complement, not replace, the expertise of healthcare professionals.

Background: The compensatory reserve metric (CRM) provides a novel marker of hemodynamic status in prediction of sudden cardiovascular decompensation during central hypovolemia. The CRM has previously been calculated using arterial waveforms obtained from a photoplethysmographic volume-clamp technique. However, the in-field use of pulse oximetry is becoming more prominent in research and medicine. To improve in-field applicability of the CRM, this project aimed to validate pulse-oximetry derived CRM values relative to physiologic data during simulated hemorrhage through application of lower body negative pressure (LBNP). Methods: Forty-nine healthy adults (25 females) underwent a graded LBNP protocol with the following 5-minute stages: -0, -15, -30, -45, -60, -70, -80, -90, and 100 mmHg, or until the onset of pre-syncopal symptoms (tolerance) was reached. Arterial waveforms were sampled using pulse oximetry (Massimo Radical 7). The CRM was calculated using a validated one-dimensional convolutional neural network. A brachial artery catheter was used to measure intraarterial pressure. A 3-lead ECG was used to measure heart rate. SpO2 was measured using pulse oximetry. Cardiac output and stroke volume were estimated using the photoplethysmographic volume-clamp. Data were binned for the last thirty seconds of each completed stage, and at tolerance. Fixed-effect linear mixed models with repeated measures were used to examine the association between CRM values and physiologic variables. A priori significance was set at P<0.05. Results: The median LBNP stage reached was 70 mmHg (Range: 45-100 mmHg). Relative to baseline, at tolerance there was a 50±12% ( P<0.001) mean reduction in stroke volume, 65±27% ( P<0.001) increase in heart rate, 18±8% ( P<0.001) reduction in mean arterial pressure, 21±7% ( P<0.001) systolic blood pressure, 8±9% ( P<0.001) diastolic blood pressure, and 39±12% ( P<0.001) pulse pressure. The CRM obtained using pulse oximetry was significantly associated with a reduction in stroke volume ( P<0.001), increase in heart rate ( P<0.001), and reductions in systolic ( P=0.033), diastolic ( P=0.036), and pulse pressure ( P=0.002). There was no statistically significant association between CRM and cardiac output ( P=0.421), SpO2 ( P=0.408), or mean arterial pressure ( P=0.214). Conclusion: The CRM obtained using pulse oximetry may be a valid, reliable marker of hemodynamic status with promising in-field applications. Future studies warrant investigation of feasibility and applicability within various contexts ranging from the operating room to the battlefield. The presented work was funded in part by the Congressionally Directed Medical Research Program (Award No. DM180240) and Offce of Naval Research (Awards No. N00014-18-D-7001 and N00014-19-C-2017). This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

This study aims to explore how artificial intelligence can help ease the burden on caregivers, filling a gap in current research and healthcare practices due to the growing challenge of an aging population and increased reliance on informal caregivers. We conducted a search with Google Scholar, PubMed, Scopus, IEEE Xplore, and Web of Science, focusing on AI and caregiving. Our inclusion criteria were studies where AI supports informal caregivers, excluding those solely for data collection. Adhering to PRISMA 2020 guidelines, we eliminated duplicates and screened for relevance. From 947 initially identified articles, 10 met our criteria, focusing on AI’s role in aiding informal caregivers. These studies, conducted between 2012 and 2023, were globally distributed, with 80% employing machine learning. Validation methods varied, with Hold-Out being the most frequent. Metrics across studies revealed accuracies ranging from 71.60% to 99.33%. Specific methods, like SCUT in conjunction with NNs and LibSVM, showcased accuracy between 93.42% and 95.36% as well as F-measures spanning 93.30% to 95.41%. AUC values indicated model performance variability, ranging from 0.50 to 0.85 in select models. Our review highlights AI’s role in aiding informal caregivers, showing promising results despite different approaches. AI tools provide smart, adaptive support, improving caregivers’ effectiveness and well-being.

With abundant information and interconnectedness among people, identifying knowledgeable individuals in specific domains has become crucial for organizations. Artificial intelligence (AI) algorithms have been employed to evaluate the knowledge and locate experts in specific areas, alleviating the manual burden of expert profiling and identification. However, there is a limited body of research exploring the application of AI algorithms for expert finding in the medical and biomedical fields. This study aims to conduct a scoping review of existing literature on utilizing AI algorithms for expert identification in medical domains. We systematically searched five platforms using a customized search string, and 21 studies were identified through other sources. The search spanned studies up to 2023, and study eligibility and selection adhered to the PRISMA 2020 statement. A total of 571 studies were assessed from the search. Out of these, we included six studies conducted between 2014 and 2020 that met our review criteria. Four studies used a machine learning algorithm as their model, while two utilized natural language processing. One study combined both approaches. All six studies demonstrated significant success in expert retrieval compared to baseline algorithms, as measured by various scoring metrics. AI enhances expert finding accuracy and effectiveness. However, more work is needed in intelligent medical expert retrieval.

Introduction: As large language models receive greater attention in medical research, the investigation of ethical considerations is warranted. This review aims to explore surgery literature to identify ethical concerns surrounding these artificial intelligence models and evaluate how autonomy, beneficence, nonmaleficence, and justice are represented within these ethical discussions to provide insights in order to guide further research and practice. Methods: A systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Five electronic databases were searched in October 2023. Eligible studies included surgery-related articles that focused on large language models and contained adequate ethical discussion. Study details, including specialty and ethical concerns, were collected. Results: The literature search yielded 1179 articles, with 53 meeting the inclusion criteria. Plastic surgery, orthopedic surgery, and neurosurgery were the most represented surgical specialties. Autonomy was the most explicitly cited ethical principle. The most frequently discussed ethical concern was accuracy (n = 45, 84.9%), followed by bias, patient confidentiality, and responsibility. Conclusion: The ethical implications of using large language models in surgery are complex and evolving. The integration of these models into surgery necessitates continuous ethical discourse to ensure responsible and ethical use, balancing technological advancement with human dignity and safety.

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.

ABSTRACT Introduction Military transport can induce whole-body vibrations, and combat almost always involves high impact between lower extremities and the ground. Therefore, robust splinting technology is necessary for lower extremity fractures in these settings. Our team compared a novel one-step spray-on foam splint (FastCast) to the current military standard structured aluminum malleable (SAM) splint. Materials and Methods Ten cadaveric specimens were subjected to complete tibia/fibula osteotomy. Specimens were fitted with custom accelerometer and gyroscope sensors superior and inferior to the fracture line. Each specimen underwent fracture and splinting from a standard of care SAM splint and an experimental FastCast spray foam splint in a randomized order. Each specimen was manually transported to an ambulance and then released from a 1 meter height to simulate impact. The custom sensors recorded accelerations and rotations throughout each event. Repeated-measures Friedman tests were used to assess differences between splint method within each event and between sensors within each splint method. Results During splinting, overall summation of change and difference of change between sensors for accelerations and rotations were greater for SAM splints than FastCast across all axes (P ≤ 0.03). During transport, the range of acceleration along the linear superior/inferior axis was greater for SAM splint than FastCast (P = 0.02), as was the range of rotation along the transverse plane (P &lt; 0.01). On impact, the summation of change observed was greater for SAM splint than FastCast with respect to acceleration and rotation on the posterior/anterior and superior/inferior axes (P ≤ 0.03), and the cumulative difference between superior and inferior sensors was greater for SAM than FastCast with respect to anterior-axis rotation (P &lt; 0.05). Conclusion FastCast maintains stabilization of fractured lower extremities during transport and impacts to a significantly greater extent than SAM splints. Therefore, FastCast can potentially reduce the risk of fracture complications following physical stressors associated with combat and extraction.