Andrew Bishara

Associate Professor In Residence

University of California
Country flagUnited States

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (7)

Year:

2026

Purpose of review To synthesize recent advances in intraoperative resuscitation for trauma surgery, including fluid composition, transfusion thresholds, and coagulopathy management, and to identify emerging directions that address persistent gaps in precision. Particular attention is given to prospective evidence, as forward-looking evaluations better capture real-world performance, workflow integration, and clinical impact, culminating in the integration of artificial intelligence and machine learning as the next stage of innovation. Recent findings Major trials over the past 5 years have refined evidence for balanced transfusion ratios, restrictive transfusion thresholds, and the transition from crystalloid to hemostatic and physiology-guided strategies. However, outcome variability underscores the need for individualized, data-driven resuscitation. Early prospective machine learning evaluations – along with the US Food and Drug Administration–cleared point-of-care systems such as APPRAISE-HRI – demonstrate that multimodal physiologic modeling can predict hemorrhage and fluid responsiveness as accurately as expert clinicians, while offering real-time monitoring and guidance. Summary The field is shifting from protocol-based to precision-guided trauma resuscitation. Future progress will rely on randomized-controlled-trial-validated, adaptive, human-in-the-loop artificial intelligence workflows that integrate continuous physiologic data with clinical judgment to enhance the timing, composition, and safety of intraoperative fluid and transfusion therapy.

Year:

2026

Background Chronic low-back pain (LBP) is the largest contributor to disability worldwide, yet many assessments still reduce a complex, spatially distributed condition to a single 0–10 score. Body-map drawings capture location and extent of pain, but manual digitization is too slow and inconsistent for large studies or real-time telehealth. Methods Paper pain drawings from 332 adults in the multicenter COMEBACK study (four University of California sites, March 2021–June 2023) were scanned to PDFs. A Python pipeline automatically (i) rasterized PDF pages with pdf2image v1.17.0; (ii) resized each scan and delineated anterior/posterior regions of interest; (iii) registered patient silhouettes to a canonical high-resolution template using ORB key-points, Brute-Force Hamming matching, RANSAC inlier selection, and 3 × 3 projective homography implemented in OpenCV; (iv) removed template outlines via adaptive Gaussian thresholding, Canny edge detection, and 3 × 3 dilation, leaving only patient-drawn strokes; (v) produced binary masks for pain, numbness, and pins-and-needles, then stacked these across subjects to create pixel-frequency matrices; and (vi) normalized matrices with min–max scaling and rendered heat maps. RGB composites assigned distinct channels to each sensation, enabling intuitive visualization of overlapping symptom distributions and for future data analyses. Results Cohort-level maps replicated classic low-back pain hotspots over lumbar paraspinals, gluteal fold, and posterior thighs, while exposing less-recognized clusters along the lateral hip and lower abdomen. Neuropathic-leaning drawings displayed broader leg involvement than purely nociceptive patterns. Conclusions Our automated workflow converts pen-on-paper pain drawings into machine-readable digitized images and heat maps at the population scale, laying practical groundwork for spatially informed, precision management of chronic LBP.

Year:

2025

Objective This study identifies distinct biobehavioral phenotypes among patients with chronic low back pain (cLBP) using Latent Profile Analysis (LPA). Methods These phenotypes were derived from baseline data from two cohorts within the NIH HEAL BACPAC consortium: BACKHOME, a large nationwide e-cohort (N = 3025) utilized for model training, and COMEBACK as external test set, a deep phenotyping cohort (N = 450) utilized for generalization. The analysis incorporated variables including pain characteristics, psychosocial factors, lifestyle habits, and social determinants of health. Model fit was optimized via 10-fold cross-validation with 100 bootstraps and evaluated using Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and Entropy(uncertainty). Results Four classes were identified: Class 1 (“High Distress and Maladaptive Behaviors”) displayed high levels of anxiety, depression, and fear avoidance. Class 2 (“Resilient and Adaptive Coping”) exhibited low maladaptive behaviors and high pain self-efficacy. Class 3 (“Intermediate Maladaptive Patterns”) represented moderate levels of psychological and behavioral challenges, while Class 4 (“Emotionally Regulated with High Pain Burden”) demonstrated strong emotional regulation despite significant pain burden. Class sizes were 701, 413, 893, and 947 for the train set, and 127, 108, 95, and 68 for the test set, respectively. Fit metrics supported the model’s performance and generalizability (BACKHOME (train set): AIC = 77 792, BIC = 78 338, Entropy = 0.82; COMEBACK(test set): AIC = 72 437, BIC = 73 880, Entropy = 0.81). Statistical analysis revealed significant differences between classes (P < .05) in key variables such as pain self-efficacy, fear avoidance, and emotional awareness, and changes in pain severity and health-related quality of life over time (P ≤ .001), indicating clinical utility. Conclusions Our findings highlight the heterogeneity of cLBP and suggest that tailored treatments targeting these distinct subgroups could improve clinical outcomes. This work advances our understanding of cLBP by providing a robust framework for identifying patient subgroups based on biobehavioral characteristics. Results underscore the value of LPA in uncovering clinically meaningful patterns in complex conditions like cLBP, paving the way for more personalized treatment approaches.

Year:

2025

Year:

2025

Background Unplanned postoperative intensive care unit admissions (UIAs) are rare events that cause significant challenges to perioperative workflow. We describe the development of a machine-learning derived model to predict UIAs using only widely used preoperative variables. Methods This was a 3-year retrospective review of all adult surgeries under the General, Vascular, and Thoracic surgical services with anticipated length of greater than 180 minutes at a single institution. A UIA was defined as any post-operative patient recovering in the post-anesthesia care unit (PACU) requiring direct transfer to the intensive care unit (ICU) for higher level of care. We developed our prediction model with a gradient-boosting decision tree algorithm (XGBoost). The model incorporated sixteen generalizable predictor variables that were derived from the demographics and surgical booking details. Validation and evaluation were performed with 10-fold cross validation, and model performance was evaluated using the area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, and likelihood ratio. Results A total of 4658 patients were included for analysis. The incidence of UIAs was 2.3%. With 10-fold cross validation, the area under the ROC curve was 0.80 (95% CI 0.74–0.86). Two decision thresholds were used, which achieved the best specificity of 94% (95% CI 92–96%), best positive likelihood ratio of 4.22 (95% CI 0.99–8.79), and best sensitivity of 82% (95% CI 58–100%). Conclusions Our machine learning-derived model is a reliable tool for the perioperative clinician to predict a rare outcome in high-risk patients using only preoperative variables. Future studies will include prospective validation of this model at other institutions and real-time incorporation for improvement in perioperative workflow.

Year:

2025

Acute kidney injury (AKI) is a major postoperative complication that lacks established intraoperative predictors. Our objective was to develop a prediction model using preoperative and high-frequency intraoperative data for postoperative AKI. In this retrospective cohort study, we evaluated 77,428 operative cases at a single academic center between 2016 and 2022. A total of 11,212 cases with serum creatinine (sCr) data were included in the analysis. Then, 8519 cases were randomly assigned to the training set and the remainder to the validation set. Fourteen preoperative and twenty intraoperative variables were evaluated using elastic net followed by hierarchical group least absolute shrinkage and selection operator (LASSO) regression. The training set was 56% male and had a median [IQR] age of 62 (51–72) and a 6% AKI rate. Retained model variables were preoperative sCr values, the number of minutes meeting cutoffs for urine output, heart rate, perfusion index intraoperatively, and the total estimated blood loss. The area under the receiver operator characteristic curve was 0.81 (95% CI, 0.77–0.85). At a score threshold of 0.767, specificity was 77% and sensitivity was 74%. A web application that calculates the model score is available online. Our findings demonstrate the utility of intraoperative time series data for prediction problems, including a new potential use of the perfusion index. Further research is needed to evaluate the model in clinical settings.

Year:

2023

Collaborators (8)

Thomas A Peterson

Assistant Professor, BCHSI; Assistant Professor, UCSF Dept. Orthopaedic Surgery

University of California, San Francisco

UNITED STATES
View details

Hillary Braun

Assistant Professor

University of California, San Francisco

UNITED STATES
View details

Jeffrey Lotz

University of California, San Francisco

UNITED STATES
View details

Jean Digitale

University of California, San Francisco

UNITED STATES
View details

Mark J. Pletcher

University of California, San Francisco

UNITED STATES
View details

Adam R Ferguson

Principal Investigator and Research Health Science Specialist

University of California, San Francisco

UNITED STATES
View details

Aaron Fields

Professor

University of California, San Francisco

UNITED STATES
View details

Irina Strigo

University of California, San Francisco

UNITED STATES
View details