Total knee arthroplasty (TKA) and total hip arthroplasty (THA) improve symptoms in end-stage osteoarthritis, yet long-term objective characterization of perioperative physical activity trajectories remains limited. We conducted a longitudinal observational study within the All of Us Research Program dataset, linking electronic health records with continuous Fitbit-derived step count data over a four-year perioperative window (two years before and two years after arthroplasty). Piecewise linear mixed-effects models characterized preoperative declines and postoperative recovery trajectories, and time-to-recovery was evaluated using Kaplan-Meier curves and Cox proportional hazards models under remote and immediate preoperative physical activity baseline definitions. Among 238 participants (147 TKA; 91 THA), both procedures exhibited progressive preoperative decline with distinct procedure-specific patterns and staged postoperative recovery: rapid improvement during weeks 1-6, decelerating gains through weeks 7-19/20, and subsequent stabilization through week 104. Recovery to remote and immediate baselines differed in timing (median 22 vs 13 weeks) and associated predictors. Higher imm
The intricate nature of modern surgical care necessitates intelligent systems that can synthesize extensive patient records, support collaborative decision-making, and provide transparent, auditable reasoning across the entire perioperative workflow. Although web-based Large Language Models (LLMs) possess advanced reasoning capabilities, they are ill-equipped for surgical applications due to critical limitations: input length constraints, incomplete memory management, and limited traceability. To address this issue, we present SURGENT, a surgical multi-agent assistance system that combines a Tree-of-Thought planner, multi-department collaboration agents, and retrieval-augmented reasoning with clinical guidelines and biomedical literature. SURGENT features a novel memory design that manages both long-term patient histories and short-term working summaries, enabling more complete, contextualized, and consistent reasoning. Experimental evaluations across five key perioperative tasks - case analysis, surgical plan simulation, safety monitoring, complication risk assessment, and rehabilitation guidance - show that SURGENT outperforms baseline LLMs and existing medical multi-agent framew
Noninvasive arterial blood pressure (ABP) monitoring is essential for patient management in critical care and perioperative settings, providing continuous assessment of cardiovascular hemodynamics with minimal risks. Numerous deep learning models have developed to reconstruct ABP waveform from noninvasively acquired physiological signals such as electrocardiogram and photoplethysmogram. However, limited research has addressed the issue of model performance and computational load for deployment on embedded systems. The study introduces a lightweight sInvResUNet, along with a collaborative learning scheme named KDCL_sInvResUNet. With only 0.89 million parameters and a computational load of 0.02 GFLOPS, real-time ABP estimation was successfully achieved on embedded devices with an inference time of just 8.49 milliseconds for a 10-second output. We performed subject-independent validation in a large-scale and heterogeneous perioperative dataset containing 1,257,141 data segments from 2,154 patients, with a wide BP range (41-257 mmHg for SBP, and 31-234 mmHg for DBP). The proposed KDCL_sInvResUNet achieved lightly better performance compared to large models, with a mean absolute error o
Large Language Models (LLMs) are emerging as powerful tools in healthcare, particularly for complex, domain-specific tasks. This study describes the development and evaluation of the PErioperative AI CHatbot (PEACH), a secure LLM-based system integrated with local perioperative guidelines to support preoperative clinical decision-making. PEACH was embedded with 35 institutional perioperative protocols in the secure Claude 3.5 Sonet LLM framework within Pair Chat (developed by Singapore Government) and tested in a silent deployment with real-world data. Accuracy, safety, and usability were assessed. Deviations and hallucinations were categorized based on potential harm, and user feedback was evaluated using the Technology Acceptance Model (TAM). Updates were made after the initial silent deployment to amend one protocol. In 240 real-world clinical iterations, PEACH achieved a first-generation accuracy of 97.5% (78/80) and an overall accuracy of 96.7% (232/240) across three iterations. The updated PEACH demonstrated improved accuracy of 97.9% (235/240), with a statistically significant difference from the null hypothesis of 95% accuracy (p = 0.018, 95% CI: 0.952-0.991). Minimal hallu
We investigate whether general-domain large language models such as GPT-4 Turbo can perform risk stratification and predict post-operative outcome measures using a description of the procedure and a patient's clinical notes derived from the electronic health record. We examine predictive performance on 8 different tasks: prediction of ASA Physical Status Classification, hospital admission, ICU admission, unplanned admission, hospital mortality, PACU Phase 1 duration, hospital duration, and ICU duration. Few-shot and chain-of-thought prompting improves predictive performance for several of the tasks. We achieve F1 scores of 0.50 for ASA Physical Status Classification, 0.81 for ICU admission, and 0.86 for hospital mortality. Performance on duration prediction tasks were universally poor across all prompt strategies. Current generation large language models can assist clinicians in perioperative risk stratification on classification tasks and produce high-quality natural language summaries and explanations.
The association between preoperative cognitive status and surgical outcomes is a critical, yet scarcely explored area of research. Linking intraoperative data with postoperative outcomes is a promising and low-cost way of evaluating long-term impacts of surgical interventions. In this study, we evaluated how preoperative cognitive status as measured by the clock drawing test contributed to predicting length of hospital stay, hospital charges, average pain experienced during follow-up, and 1-year mortality over and above intraoperative variables, demographics, preoperative physical status and comorbidities. We expanded our analysis to 6 specific surgical groups where sufficient data was available for cross-validation. The clock drawing images were represented by 10 constructional features discovered by a semi-supervised deep learning algorithm, previously validated to differentiate between dementia and non-dementia patients. Different machine learning models were trained to classify postoperative outcomes in hold-out test sets. The models were compared to their relative performance, time complexity, and interpretability. Shapley Additive Explanations (SHAP) analysis was used to find
The increasing availability of wearable electrocardiography (ECG) devices enables the continuous monitoring of individual ECG alterations. This could be beneficial for patients suffering from acute ischemia but with non-standard ECG findings that do not fit to the subject-independent and absolute thresholds defined in clinical guidelines. In this work, we evaluate the inter-patient magnitude of individual ECG alterations during ischemia. The freely available STAFF III database provides 12-lead ECG recordings of patients before, during, and after elective percutaneous coronary intervention(PCI), where a coronary vessel is widened with a balloon inflation. We compute individual alterations of ST-interval and T-wave amplitudes w.r.t. QRS amplitude over time for each patient and lead. We demonstrate that determining relative ST-interval/T-wave amplitudes and deriving individual alterations over time is feasible in standard and non-standard ECG recordings. To demonstrate clinical relevance, we use the features for differentiating N=54 STAFF III patients with atherosclerotic plaque in either the right coronary artery (RCA) or left ascending artery (LAD). Results show significant differen
Surgical co-management (SCM) is an evidence-based model in which hospitalists jointly manage medically complex perioperative patients alongside surgical teams. Despite its clinical and financial value, SCM is limited by the need to manually identify eligible patients. To determine whether SCM triage can be automated, we conducted a prospective, unblinded study at Stanford Health Care in which an LLM-based, electronic health record (EHR)-integrated triage tool (SCM Navigator) provided SCM recommendations followed by physician review. Using pre-operative documentation, structured data, and clinical criteria for perioperative morbidity, SCM Navigator categorized patients as appropriate, not appropriate, or possibly appropriate for SCM. Faculty indicated their clinical judgment and provided free-text feedback when they disagreed. Sensitivity, specificity, positive predictive value, and negative predictive value were measured using physician determinations as a reference. Free-text reasons were thematically categorized, and manual chart review was conducted on all false-negative cases and 30 randomly selected cases from the largest false-positive category. Since deployment, 6,193 cases
We present an investigation of the applicability of topological data analysis (TDA) to the study of high-resolution confocal microscopy images of fibrin network structures from patients with oesophageal cancer undergoing intended curative surgery. Investigation of clot structure brings new knowledge about blood coagulation, risk of bleeding, and thrombosis in this group of patients. Images of fibrin network formation in the collected blood samples were captured by confocal microscopy and three-dimensional z-stacks were analysed. Each z-stack was cropped to a centre region for analysis, the validity of which is assessed in detail. Overall, we found no significant differences in fibrin network topology across the perioperative period, and no consistent differences in network structure between the standard and intervention groups.
"Days alive and at home" (DAH) is a recent patient-centered outcome measure for perioperative trials, defined as the number of days a patient spends at home during the follow-up period. DAH typically follows a zero-inflated, left-skewed, bi-modal distribution. Other increasingly used complex endpoints, such as days alive without a ventilator, share these statistical features arising from combining survival with another clinically relevant count outcome into a single, comprehensive measure. A key challenge for DAH and similar endpoints is the lack of a readily identifiable distributional form, which complicates the statistical design of trials using it as the primary endpoint, particularly regarding the robustness of sample size calculations and final analyses where the central limit theorem might not be suitable. Using 200 data points from the interim data of the NOTACS trial (ISRCTN14092678), whose primary endpoint was DAH, we developed a novel 'Divide & Conquer' model that breaks DAH into distinct parts modeled individually. To our knowledge, such a model has not been used before for DAH. We demonstrate that our approach significantly improves model fit compared to existing a
Estimating heterogeneous treatment effects in survival settings is complicated by right censoring as well as the time-varying nature of the estimand. While the conditional average treatment effect (CATE) provides a natural target, most existing approaches focus on a single prespecified time point and do not account for the temporal trajectory, leading to instability in estimation. We propose a deep survival learner (DSL) for estimating heterogeneous treatment effects with right-censored outcomes. The method is based on a doubly robust pseudo-outcome whose conditional expectation identifies time-specific CATEs under standard assumptions. This construction remains unbiased if either the outcome model or the treatment assignment model is correctly specified, when properly accounting for censoring. To estimate CATEs over a clinically relevant time spectrum, DSL employs a multi-output deep neural network with shared representations, enabling joint estimation of treatment effect trajectories. From a theoretical perspective, we derive error bounds for both pointwise and joint estimation over time. We show that joint estimation can leverage temporal structure to control estimation error wi
Data scarcity challenges the development and implementation of innovative healthcare solutions. In geriatrics, fall-related injuries are a major cause of hospitalization, functional decline, and mortality in older adults. Optimizing post-operative discharge planning can mitigate these outcomes, but limited data hinders predictive model development. Here, we explored generative machine learning approaches to augment data from the SURGE-Ahead project (Supporting SURgery with Geriatric Co-Management and AI), an initiative addressing geriatric perioperative care. Data from the German geriatric trauma register (AltersTraumaZentrum; ATZ) were incorporated using two strategies: (i) combining SURGE-Ahead and ATZ register data with imputation (ComImp) and (ii) generating synthetic data from SURGE-Ahead alone or combined SURGE-Ahead and the ATZ register datasets with Adversarial random forests (ARF). Predictive models, including multinomial logistic regression, random forest, and a prior-fitted transformer (TabPFN), were trained and evaluated using standard performance metrics: accuracy, area under the receiver operating characteristic curve (ROC AUC), Brier score, and the logistic loss. Ran
Accurate prediction of postoperative complications can support personalized perioperative care. However, in surgical settings, data collection is often constrained, and identifying which variables to prioritize remains an open question. We analyzed 767 elective bowel surgeries performed under an Enhanced Recovery After Surgery protocol at Medisch Spectrum Twente (Netherlands) between March 2020 and December 2023. Although hundreds of variables were available, most had substantial missingness or near-constant values and were therefore excluded. After data preprocessing, 34 perioperative predictors were selected for further analysis. Surgeries from 2020 to 2022 ($n=580$) formed the development set, and 2023 cases ($n=187$) provided temporal validation. We modeled two binary endpoints: any and serious postoperative complications (Clavien Dindo $\ge$ IIIa). We compared weighted logistic regression, stratified random forests, and Naive Bayes under class imbalance (serious complication rate $\approx$11\%; any complication rate $\approx$35\%). Probabilistic performance was assessed using class-specific Brier scores. We advocate reporting probabilistic risk estimates to guide monitoring ba
Context: Utilization of operating theaters is a major cost driver in hospitals. Optimizing this variable through optimized surgery schedules may significantly lower cost and simultaneously improve medical outcomes. Previous studies proposed various complex models to predict the duration of procedures, the key ingredient to optimal schedules. They did so perusing large amounts of data. Goals: We aspire to create an effective and efficient model to predict operation durations based on only a small amount of data. Ideally, our model is also simpler in structure, and thus easier to use. Methods: We immerse ourselves in the application domain to leverage practitioners expertise. This way, we make the best use of our limited supply of clinical data, and may conduct our data analysis in a theory-guided way. We do a combined factor analysis and develop regression models to predict the duration of the perioperative process. Findings: We found simple methods of central tendency to perform on a par with much more complex methods proposed in the literature. In fact, they sometimes outperform them. We conclude that combining expert knowledge with data analysis may improve both data quality and
Background: Accurate prediction of surgical case duration underpins operating room (OR) scheduling, yet existing models often depend on site- or surgeon-specific inputs and rarely undergo external validation, limiting generalisability. Methods: We undertook a retrospective multicentre study using routinely collected perioperative data from two general hospitals in Japan (development: 1 January 2021-31 December 2023; temporal test: 1 January-31 December 2024). Elective weekday procedures with American Society of Anesthesiologists (ASA) Physical Status 1-4 were included. Pre-specified preoperative predictors comprised surgical context (year, month, weekday, scheduled duration, general anaesthesia indicator, body position) and patient factors (sex, age, body mass index, allergy, infection, comorbidity, ASA). Missing data were addressed by multiple imputation by chained equations. Four learners (elastic-net, generalised additive models, random forest, gradient-boosted trees) were tuned within internal-external cross-validation (IECV; leave-one-cluster-out by centre-year) and combined by stacked generalisation to predict log-transformed duration. Results: We analysed 63,206 procedures (
The operating room (OR) is a complex environment where optimizing workflows is critical to reduce costs and improve patient outcomes. While computer vision approaches for automatic recognition of perioperative events can identify bottlenecks for OR optimization, privacy concerns limit the use of OR videos for automated event detection. We propose a two-stage pipeline for privacy-preserving OR video analysis and event detection. First, we leverage vision foundation models for depth estimation and semantic segmentation to generate de-identified Digital Twins (DT) of the OR from conventional RGB videos. Second, we employ the SafeOR model, a fused two-stream approach that processes segmentation masks and depth maps for OR event detection. Evaluation on an internal dataset of 38 simulated surgical trials with five event classes shows that our DT-based approach achieves performance on par with -- and sometimes better than -- raw RGB video-based models for OR event detection. Digital Twins enable privacy-preserving OR workflow analysis, facilitating the sharing of de-identified data across institutions and potentially enhancing model generalizability by mitigating domain-specific appearan
Traditional methods of surgical decision making heavily rely on human experience and prompt actions, which are variable. A data-driven system generating treatment recommendations based on patient states can be a substantial asset in perioperative decision-making, as in cases of intraoperative hypotension, for which suboptimal management is associated with acute kidney injury (AKI), a common and morbid postoperative complication. We developed a Reinforcement Learning (RL) model to recommend optimum dose of intravenous (IV) fluid and vasopressors during surgery to avoid intraoperative hypotension and postoperative AKI. We retrospectively analyzed 50,021 surgeries from 42,547 adult patients who underwent major surgery at a quaternary care hospital between June 2014 and September 2020. Of these, 34,186 surgeries were used for model training and 15,835 surgeries were reserved for testing. We developed a Deep Q-Networks based RL model using 16 variables including intraoperative physiologic time series, total dose of IV fluid and vasopressors extracted for every 15-minute epoch. The model replicated 69% of physician's decisions for the dosage of vasopressors and proposed higher or lower d
Background: Artificial Intelligence (AI) clinical decision support (CDS) systems have the potential to augment surgical risk assessments, but successful adoption depends on an understanding of end-user needs and current workflows. This study reports the initial co-design of MySurgeryRisk, an AI CDS tool to predict the risk of nine post-operative complications in surgical patients. Methods: Semi-structured focus groups and interviews were held as co-design sessions with perioperative physicians at a tertiary academic hospital in the Southeastern United States. Participants were read a surgical vignette and asked questions to elicit an understanding of their current decision-making practices before being introduced to the MySurgeryRisk prototype web interface. They were asked to provide feedback on the user interface and system features. Session transcripts were qualitatively coded, after which thematic analysis took place. Results: Data saturation was reached after 20 surgeons and anesthesiologists from varying career stages participated across 11 co-design sessions. Thematic analysis resulted in five themes: (1) decision-making cognitive processes, (2) current approach to decision-
Intraoperative hypotension (IOH) is strongly associated with postoperative complications, including postoperative delirium and increased mortality, making its early prediction crucial in perioperative care. While several artificial intelligence-based models have been developed to provide IOH warnings, existing methods face limitations in incorporating both time and frequency domain information, capturing short- and long-term dependencies, and handling noise sensitivity in biosignal data. To address these challenges, we propose a novel Self-Adaptive Frequency Domain Network (SAFDNet). Specifically, SAFDNet integrates an adaptive spectral block, which leverages Fourier analysis to extract frequency-domain features and employs self-adaptive thresholding to mitigate noise. Additionally, an interactive attention block is introduced to capture both long-term and short-term dependencies in the data. Extensive internal and external validations on two large-scale real-world datasets demonstrate that SAFDNet achieves up to 97.3\% AUROC in IOH early warning, outperforming state-of-the-art models. Furthermore, SAFDNet exhibits robust predictive performance and low sensitivity to noise, making
We propose vine copula-based classifiers for probabilistic risk prediction in perioperative settings. We obtain full joint probability models for mixed continuous-ordinal variables by fitting a separate vine copula to each outcome class, capturing nonlinear and tail-asymmetric dependence. In a cohort of 767 elective bowel surgeries (81 serious vs. 686 non-serious complications), posterior probabilities from the fitted vine classification models are used to allocate patients into low-, moderate-, and high-risk groups. Compared to weighted logistic regression and random forests with stratified sampling, the vine copula-based classifiers achieve up to 10% lower class-specific Brier scores and negative log-likelihoods on the out-of-sample. The vine copula-based classifier identifies a large cohort of true low-risk patients potentially eligible for early discharge. Scenario analyses based on the fitted vine copula models provide interpretable risk profiles, including nonlinear relationships between body mass index, surgery duration, and blood loss, which might remain undetected under linear models. These results demonstrate that vine copula-based classifiers offer a reliable and interpr