Longitudinal clinical decision support for assessing decisions over time: State-of-the-art and future directions.

Objective: Patients and clinicians rarely experience healthcare decisions as snapshots in time, but clinical decision support (CDS) systems often represent decisions as snapshots. This scoping review systematically maps challenges and facilitators to longitudinal CDS that are applied at two or more timepoints for the same decision made by the same patient or clinician. Methods: We searched Embase, PubMed, and Medline databases for articles describing development, validation, or implementation of patient- or clinician-facing longitudinal CDS. Validated quality assessment tools were used for article selection. Challenges and facilitators to longitudinal CDS are reported according to PRISMA-ScR guidelines. Results: Eight articles met inclusion criteria; each article described a unique CDS. None used entirely automated data entry, none used living guidelines for updating the evidence base or knowledge engine as new evidence emerged during the longitudinal study, and one included formal readiness for change assessments. Seven of eight CDS were implemented and evaluated prospectively. Challenges were primarily related to suboptimal study design (with unique challenges for each study) or user interface. Facilitators included use of randomized trial designs for prospective enrollment, increased CDS uptake during longitudinal exposure, and machine-learning applications that are tailored to the CDS use case. Conclusions: Despite the intuitive advantages of representing healthcare decisions longitudinally, peer-reviewed literature on longitudinal CDS is sparse. Existing reports suggest opportunities to incorporate longitudinal CDS frameworks, automated data entry, living guidelines, and user readiness assessments. Generating best practice guidelines for longitudinal CDS would require a greater depth and breadth of published work and expert opinion.

Transcriptomic Differences in Peripheral Monocyte Populations in Septic Patients Based on Outcome.

ABSTRACT: Post-sepsis early mortality is being replaced by survivors who experience either a rapid recovery and favorable hospital discharge or the development of chronic critical illness (CCI) with suboptimal outcomes. The underlying immunological response that determines these clinical trajectories remains poorly defined at the transcriptomic level. As classical and non-classical monocytes are key leukocytes in both the innate and adaptive immune systems, we sought to delineate the transcriptomic response of these cell types. Using single-cell RNA sequencing and pathway analyses, we identified gene expression patterns between these two groups that are consistent with differences in TNFα production based on clinical outcome. This may provide therapeutic targets for those at risk for CCI in order to improve their phenotype/endotype, morbidity, and long-term mortality.

Operating Room Supply Cost and Value of Care after Implementing a Sustainable Quality Intervention.

BACKGROUND: Variability in operating room supply cost is a modifiable cause of suboptimal resource use and low value of care (outcomes vs cost). This study describes implementation of a quality improvement intervention to decrease operating room supply costs. STUDY DESIGN: An automated electronic health record data pipeline harmonized operating room supply cost data with patient and case characteristics and outcomes. For inpatient procedures, predicted mortality and length of stay were used to calculate observed-to-expected ratios and value of care using validated equations. For commonly performed (1 or more per week) procedures, the pipeline generated figures illustrating individual surgeon performance vs peers, costs for each surgeon performing each case type, and control charts identifying out-of-control cases and surgeons with more than 90th percentile costs, which were shared with surgeons and division chiefs alongside guidance for modifying case-specific supply instructions to operating room nurses and technicians. RESULTS: Preintervention control (1,064 cases for 7 months) and postintervention (307 cases for 2 months) cohorts had similar baseline characteristics across all 16 commonly performed procedures. Median costs per case were lower in the intervention cohort ($811 [$525 to $1,367] vs controls: $1,080 [$603 to $1,574], p < 0.001), as was the incidence of out-of-control cases (19 (6.2%) vs 110 (10.3%), p = 0.03). Duration of surgery, length of stay, discharge disposition, and 30-day mortality and readmission rates were similar between cohorts. Value of care was higher in the intervention cohort (1.1 [0.1 to 1.5] vs 1.0 [0.2 to 1.4], p = 0.04). Pipeline runtime was 16:07. CONCLUSIONS: An automated, sustainable quality improvement intervention was associated with decreased operating room supply costs and increased value of care.

Exosomal microRNA following severe trauma: Role in bone marrow dysfunction.

INTRODUCTION: Severe trauma disrupts bone marrow function and is associated with persistent anemia and altered hematopoiesis. Previously, plasma-derived exosomes isolated after trauma have been shown to suppress in vitro bone marrow function. However, the cargo contained in these vesicles has not been examined. We hypothesized that trauma plasma-derived exosomes exhibit microRNA (miRNA) changes that impact bone marrow function after severe injury. METHODS: Plasma was collected from a prospective cohort study of trauma patients (n = 15; 7 males, 8 females) with hip and/or femur fractures and an Injury Severity Score of ≥15; elective total hip arthroplasty (THA) patients (n = 8; 4 males, 4 females) served as operative controls. Exosomes were isolated from plasma with the Invitrogen Total Exosome Isolation Kit (Thermo Fisher Scientific, Waltham, MA), and RNA was isolated using a miRNeasy Mini Kit (Qiagen, Hilden, Germany). Direct quantification of miRNA was performed by NanoString Technologies on a human miRNA gene panel and analyzed with nSolver with significance defined as p < 0.05. RESULTS: There were no differences in age or sex distribution between trauma and THA groups; the average Injury Severity Score was 23. Trauma plasma-derived exosomes had 60 miRNA identities that were significantly downregulated and 3 miRNAs that were upregulated when compared with THA ( p < 0.05). Twelve of the downregulated miRNAs have a direct role in hematopoiesis regulation. Furthermore, male trauma plasma-derived exosomes demonstrated downregulation of 150 miRNAs compared with male THA ( p < 0.05). Female trauma plasma-derived exosomes demonstrated downregulation of only four miRNAs and upregulation of two miRNAs compared with female THA ( p < 0.05). CONCLUSION: We observed downregulation of 12 miRNAs linked to hematopoiesis along with sexual dimorphism in miRNA expression from plasma-derived exosomes following severe trauma. Understanding sexually dimorphic miRNA expression provides new insight into sex-based changes in postinjury systemic inflammation, immune system dysregulation, and bone marrow dysfunction and will aid us in more precise future potential therapeutic strategies. LEVEL OF EVIDENCE: Prognostic and Epidemiological; Level III.

Machine Learning-Enabled Clinical Information Systems Using Fast Healthcare Interoperability Resources Data Standards: Scoping Review.

Background: Machine learning-enabled clinical information systems (ML-CISs) have the potential to drive health care delivery and research. The Fast Healthcare Interoperability Resources (FHIR) data standard has been increasingly applied in developing these systems. However, methods for applying FHIR to ML-CISs are variable. Objective: This study evaluates and compares the functionalities, strengths, and weaknesses of existing systems and proposes guidelines for optimizing future work with ML-CISs. Methods: Embase, PubMed, and Web of Science were searched for articles describing machine learning systems that were used for clinical data analytics or decision support in compliance with FHIR standards. Information regarding each system's functionality, data sources, formats, security, performance, resource requirements, scalability, strengths, and limitations was compared across systems. Results: A total of 39 articles describing FHIR-based ML-CISs were divided into the following three categories according to their primary focus: clinical decision support systems (n=18), data management and analytic platforms (n=10), or auxiliary modules and application programming interfaces (n=11). Model strengths included novel use of cloud systems, Bayesian networks, visualization strategies, and techniques for translating unstructured or free-text data to FHIR frameworks. Many intelligent systems lacked electronic health record interoperability and externally validated evidence of clinical efficacy. Conclusions: Shortcomings in current ML-CISs can be addressed by incorporating modular and interoperable data management, analytic platforms, secure interinstitutional data exchange, and application programming interfaces with adequate scalability to support both real-time and prospective clinical applications that use electronic health record platforms with diverse implementations.

Defining critical illness using immunological endotypes in patients with and without sepsis: a cohort study.

BACKGROUND: Sepsis is a heterogenous syndrome with limited therapeutic options. Identifying immunological endotypes through gene expression patterns in septic patients may lead to targeted interventions. We investigated whether patients admitted to a surgical intensive care unit (ICU) with sepsis and with high risk of mortality express similar endotypes to non-septic, but still critically ill patients using two multiplex transcriptomic metrics obtained both on admission to a surgical ICU and at set intervals. METHODS: We analyzed transcriptomic data from 522 patients in two single-site, prospective, observational cohorts admitted to surgical ICUs over a 5-year period ending in July 2020. Using an FDA-cleared analytical platform (nCounter FLEX®, NanoString, Inc.), we assessed a previously validated 29-messenger RNA transcriptomic classifier for likelihood of 30-day mortality (IMX-SEV-3) and a 33-messenger RNA transcriptomic endotype classifier. Clinical outcomes included all-cause mortality, development of chronic critical illness, and secondary infections. Univariate and multivariate analyses were performed to assess for true effect and confounding. RESULTS: Sepsis was associated with a significantly higher predicted and actual hospital mortality. At enrollment, the predominant endotype for both septic and non-septic patients was adaptive, though with significantly different distributions. Inflammopathic and coagulopathic septic patients, as well as inflammopathic non-septic patients, showed significantly higher frequencies of secondary infections compared to those with adaptive endotypes (p < 0.01). Endotypes changed during ICU hospitalization in 57.5% of patients. Patients who remained adaptive had overall better prognosis, while those who remained inflammopathic or coagulopathic had worse overall outcomes. For severity metrics, patients admitted with sepsis and a high predicted likelihood of mortality showed an inflammopathic (49.6%) endotype and had higher rates of cumulative adverse outcomes (67.4%). Patients at low mortality risk, whether septic or non-septic, almost uniformly presented with an adaptive endotype (100% and 93.4%, respectively). CONCLUSION: Critically ill surgical patients express different and evolving immunological endotypes depending upon both their sepsis status and severity of their clinical course. Future studies will elucidate whether endotyping critically ill, septic patients can identify individuals for targeted therapeutic interventions to improve patient management and outcomes.

Methods and evaluation metrics for reducing material waste in the operating room: a scoping review.

BACKGROUND: Operating rooms contribute up to 70% of total hospital waste. Although multiple studies have demonstrated reduced waste through targeted interventions, few examine processes. This scoping review highlights methods of study design, outcome assessment, and sustainability practices of operating room waste reduction strategies employed by surgeons. METHODS: Embase, PubMed, and Web of Science were screened for operating room-specific waste-reduction interventions. Waste was defined as hazardous and non-hazardous disposable material and energy consumption. Study-specific elements were tabulated by study design, evaluation metrics, strengths, limitations, and barriers to implementation in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines. RESULTS: A total of 38 articles were analyzed. Among them, 74% of studies had pre- versus postintervention designs, and 21% used quality improvement instruments. No studies used an implementation framework. The vast majority (92%) of studies measured cost as an outcome, whereas others included disposable waste by weight, hospital energy consumption, and stakeholder perspectives. The most common intervention was instrument tray optimization. Common barriers to implementation included lack of stakeholder buy-in, knowledge gaps, data capture, additional staff time, need for hospital or federal policies, and funding. Intervention sustainability was discussed in few studies (23%) and included regular waste audits, hospital policy change, and educational initiatives. Common methodologic limitations included limited outcome evaluation, narrow scope of intervention, and inability to capture indirect costs. CONCLUSION: Appraisal of quality improvement and implementation methods are critical for developing sustainable interventions for reducing operating room waste. Universal evaluation metrics and methodologies may aid in both quantifying the impact of waste reduction initiatives and understanding their implementation in clinical practice.

Resource use for cholecystectomy with versus without cholangiography: A multicenter, propensity-matched analysis.

BACKGROUND: Intraoperative cholangiography may allow for earlier identification of common bile duct injury and choledocholithiasis. The role of intraoperative cholangiography in decreasing resource use related to biliary pathology remains unclear. This study tests the null hypothesis that there is no difference in resource use for patients undergoing laparoscopic cholecystectomy with versus without intraoperative cholangiography. METHODS: This retrospective, longitudinal cohort study included 3,151 patients who underwent laparoscopic cholecystectomy at 3 university hospitals. To minimize differences in baseline characteristics while maintaining adequate statistical power, propensity scores were used to match 830 patients who underwent intraoperative cholangiography at surgeon discretion and 795 patients who underwent cholecystectomy without intraoperative cholangiography. Primary outcomes were the incidence of postoperative endoscopic retrograde cholangiography, the interval between surgery and endoscopic retrograde cholangiography, and total direct costs. RESULTS: In the propensity-matched analysis, the intraoperative cholangiography and no intraoperative cholangiography cohorts had similar age, comorbidities, American Society of Anesthesiologists Sequential Organ Failure Assessment scores, and total/direct bilirubin ratios. The intraoperative cholangiography cohort had a lower postoperative endoscopic retrograde cholangiography (2.4% vs 4.3%; P = .04), a shorter interval between cholecystectomy and endoscopic retrograde cholangiography (2.5 [1.0-17.8] vs 4.5 [2.0-9.5] days; P = .04), and shorter length of stay (0.3 [0.2-1.5] vs 1.4 [0.3-3.2] days; P < .001). Patients undergoing intraoperative cholangiography had lower total direct costs ($4.0K [3.6K-5.4K] vs $8.1K [4.9K-13.0K]; P < .001). There were no differences in 30-day or 1-year mortality among the cohorts. CONCLUSION: Compared with laparoscopic cholecystectomy without intraoperative cholangiography, cholecystectomy with intraoperative cholangiography was associated with decreased resource use, which was primarily attributable to decreased incidence and the earlier timing of postoperative endoscopic retrograde cholangiography.

Actionable artificial intelligence: Overcoming barriers to adoption of prediction tools.

Clinical prediction models based on artificial intelligence algorithms can potentially improve patient care, reduce errors, and add value to the health care system. However, their adoption is hindered by legitimate economic, practical, professional, and intellectual concerns. This article explores these barriers and highlights well-studied instruments that can be used to overcome them. Adopting actionable predictive models will require the purposeful incorporation of patient, clinical, technical, and administrative perspectives. Model developers must articulate a priori clinical needs, ensure explainability and low error frequency and severity, and promote safety and fairness. Models themselves require ongoing validation and monitoring to address variations in health care settings and must comply with an evolving regulatory environment. Through these principles, surgeons and health care providers can leverage artificial intelligence to optimize patient care.

Defining critical illness using immunological endotypes in patients with and without of sepsis: A cohort study.

Background: Sepsis is a heterogenous syndrome with limited therapeutic options. Identifying characteristic gene expression patterns, or endotypes, in septic patients may lead to targeted interventions. We investigated whether patients admitted to a surgical ICU with sepsis and with high risk of mortality express similar endotypes to non-septic, but still critically ill patients using two multiplex transcriptomic metrics obtained both on admission to a surgical intensive care unit (ICU) and at set intervals. Methods: We analyzed transcriptomic data from 522 patients in two single-site, prospective, observational cohorts admitted to surgical ICUs over a 5-year period ending in July 2020 . Using an FDA-cleared analytical platform (nCounter FLEX ® , NanoString, Inc.), we assessed a previously validated 29-messenger RNA transcriptomic classifier for likelihood of 30-day mortality (IMX-SEV-3) and a 33-messenger RNA transcriptomic endotype classifier. Clinical outcomes included all-cause (in-hospital, 30-, 90-day) mortality, development of chronic critical illness (CCI), and secondary infections. Univariate and multivariate analyses were performed to assess for true effect and confounding. Results: Sepsis was associated with a significantly higher predicted and actual hospital mortality. At enrollment, the predominant endotype for both septic and non-septic patients was adaptive , though with significantly different distributions. Inflammopathic and coagulopathic septic patients, as well as inflammopathic non-septic patients, showed significantly higher frequencies of secondary infections compared to those with adaptive endotypes (p<0.01). Endotypes changed during ICU hospitalization in 57.5% of patients. Patients who remained adaptive had overall better prognosis, while those who remained inflammopathic or coagulopathic had worse overall outcomes. For severity metrics, patients admitted with sepsis and a high predicted likelihood of mortality showed an inflammopathic (49.6%) endotype and had higher rates of cumulative adverse outcomes (67.4%). Patients at low mortality risk, whether septic or non-septic, almost uniformly presented with an adaptive endotype (100% and 93.4%, respectively). Conclusion : Critically ill surgical patients express different and evolving immunological endotypes depending upon both their sepsis status and severity of their clinical course. Future studies will elucidate whether endotyping critically ill, septic patients can identify individuals for targeted therapeutic interventions to improve patient management and outcomes.

Artificial Intelligence-enabled Decision Support in Surgery: State-of-the-art and Future Directions.

OBJECTIVE: To summarize state-of-the-art artificial intelligence-enabled decision support in surgery and to quantify deficiencies in scientific rigor and reporting. BACKGROUND: To positively affect surgical care, decision-support models must exceed current reporting guideline requirements by performing external and real-time validation, enrolling adequate sample sizes, reporting model precision, assessing performance across vulnerable populations, and achieving clinical implementation; the degree to which published models meet these criteria is unknown. METHODS: Embase, PubMed, and MEDLINE databases were searched from their inception to September 21, 2022 for articles describing artificial intelligence-enabled decision support in surgery that uses preoperative or intraoperative data elements to predict complications within 90 days of surgery. Scientific rigor and reporting criteria were assessed and reported according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines. RESULTS: Sample size ranged from 163-2,882,526, with 8/36 articles (22.2%) featuring sample sizes of less than 2000; 7 of these 8 articles (87.5%) had below-average (<0.83) area under the receiver operating characteristic or accuracy. Overall, 29 articles (80.6%) performed internal validation only, 5 (13.8%) performed external validation, and 2 (5.6%) performed real-time validation. Twenty-three articles (63.9%) reported precision. No articles reported performance across sociodemographic categories. Thirteen articles (36.1%) presented a framework that could be used for clinical implementation; none assessed clinical implementation efficacy. CONCLUSIONS: Artificial intelligence-enabled decision support in surgery is limited by reliance on internal validation, small sample sizes that risk overfitting and sacrifice predictive performance, and failure to report confidence intervals, precision, equity analyses, and clinical implementation. Researchers should strive to improve scientific quality.

Survival and neurologic outcomes following aortic occlusion for trauma and hemorrhagic shock in a hybrid operating room.

BACKGROUND: Outcomes following aortic occlusion for trauma and hemorrhagic shock are poor, leading some to question the clinical utility of aortic occlusion in this setting. This study evaluates neurologically intact survival following resuscitative endovascular balloon occlusion of the aorta (REBOA) versus resuscitative thoracotomy at a center with a dedicated trauma hybrid operating room with angiographic capabilities. METHODS: This retrospective cohort analysis compared patients who underwent zone 1 aortic occlusion via resuscitative thoracotomy (n = 13) versus REBOA (n = 13) for blunt or non-thoracic, penetrating trauma and refractory hemorrhagic shock (systolic blood pressure less than 90 mmHg despite volume resuscitation) at a level 1 trauma center with a dedicated trauma hybrid operating room. The primary outcome was survival to hospital discharge. The secondary outcome was neurologic status at hospital discharge, assessed by Glasgow Coma Scale (GCS) scores. RESULTS: Overall median age was 40 years, 27% had penetrating injuries, and 23% had pre-hospital closed-chest cardiopulmonary resuscitation. In both cohorts, median injury severity scores and head-abbreviated injury scores were 26 and 2, respectively. The resuscitative thoracotomy cohort had lower systolic blood pressure on arrival (0 [0-75] vs. 76 [65-99], p = 0.009). Hemorrhage control (systolic blood pressure 100 mmHg without ongoing vasopressor or transfusion requirements) was obtained in 77% of all REBOA cases and 8% of all resuscitative thoracotomy cases (p = 0.001). Survival to hospital discharge was greater in the REBOA cohort (54% vs. 8%, p = 0.030), as was discharge with GCS 15 (46% vs. 0%, p = 0.015). CONCLUSIONS: Among patients undergoing aortic occlusion for blunt or non-thoracic, penetrating trauma and refractory hemorrhagic shock at a center with a dedicated, trauma hybrid operating room, nearly half of all patients managed with REBOA had neurologically intact survival. The high death rate in resuscitative thoracotomy and differences in patient cohorts limit direct comparison.

Retrospective value assessment of a dedicated, trauma hybrid operating room.

BACKGROUND: In traumatic hemorrhage, hybrid operating rooms offer near simultaneous performance of endovascular and open techniques, with correlations to earlier hemorrhage control, fewer transfusions, and possible decreased mortality. However, hybrid operating rooms are resource intensive. This study quantifies and describes a single-center experience with the complications, cost-utility, and value of a dedicated trauma hybrid operating room. METHODS: This retrospective cohort study evaluated 292 consecutive adult trauma patients who underwent immediate (<4 hours) operative intervention at a Level I trauma center. A total of 106 patients treated before the construction of a hybrid operating room served as historical controls to the 186 patients treated thereafter. Demographics, hemorrhage-control procedures, and financial data as well as postoperative complications and outcomes were collected via electronic medical records. Value and incremental cost-utility ratio were calculated. RESULTS: Demographics and severity of illness were similar between cohorts. Resuscitative endovascular occlusion of the aorta was more frequently used in the hybrid operating room. Hemorrhage control occurred faster (60 vs. 49 minutes, p = 0.005) and, in the 4- to 24-hour postadmission period, required less red blood cell (mean, 1.0 vs. 0 U, p = 0.001) and plasma (mean, 1.0 vs. 0 U, p < 0.001) transfusions. Complications were similar except for a significant decrease in pneumonia (7% vs. 4%, p = 0.008). Severe complications (Clavien-Dindo classification, ≥3) were similar. Across the patient admission, costs were not significantly different ($50,023 vs. $54,740, p = 0.637). There was no change in overall value (1.00 vs. 1.07, p = 0.778). CONCLUSION: The conversion of our standard trauma operating room to an endovascular hybrid operating room provided measurable improvements in hemorrhage control, red blood cell and plasma transfusions, and postoperative pneumonia without significant increase in cost. Value was unchanged. LEVEL OF EVIDENCE: Economic/Value-Based Evaluations; Level III.

Surgical resident experience with common bile duct exploration and assessment of performance and autonomy with formative feedback.

BACKGROUND: Common bile duct exploration (CBDE) is safe and effective for managing choledocholithiasis, but most US general surgeons have limited experience with CBDE and are uncomfortable performing this procedure in practice. Surgical trainee exposure to CBDE is limited, and their learning curve for achieving autonomous, practice-ready performance has not been previously described. This study tests the hypothesis that receipt of one or more prior CBDE operative performance assessments, combined with formative feedback, is associated with greater resident operative performance and autonomy. METHODS: Resident and attending assessments of resident operative performance and autonomy were obtained for 189 laparoscopic or open CBDEs performed at 28 institutions. Performance and autonomy were graded along validated ordinal scales. Cases in which the resident had one or more prior CBDE case evaluations (n = 48) were compared with cases in which the resident had no prior evaluations (n = 141). RESULTS: Compared with cases in which the resident had no prior CBDE case evaluations, cases with a prior evaluation had greater proportions of practice-ready or exceptional performance ratings according to both residents (27% vs. 11%, p = .009) and attendings (58% vs. 19%, p < .001) and had greater proportions of passive help or supervision only autonomy ratings according to both residents (17% vs. 4%, p = .009) and attendings (69% vs. 32%, p < .01). CONCLUSIONS: Residents with at least one prior CBDE evaluation and formative feedback demonstrated better operative performance and received greater autonomy than residents without prior evaluations, underscoring the propensity of feedback to help residents achieve autonomous, practice-ready performance for rare operations.

Overtriage, Undertriage, and Value of Care after Major Surgery: An Automated, Explainable Deep Learning-Enabled Classification System.

BACKGROUND: In single-institution studies, overtriaging low-risk postoperative patients to ICUs has been associated with a low value of care; undertriaging high-risk postoperative patients to general wards has been associated with increased mortality and morbidity. This study tested the reproducibility of an automated postoperative triage classification system to generating an actionable, explainable decision support system. STUDY DESIGN: This longitudinal cohort study included adults undergoing inpatient surgery at two university hospitals. Triage classifications were generated by an explainable deep learning model using preoperative and intraoperative electronic health record features. Nearest neighbor algorithms identified risk-matched controls. Primary outcomes were mortality, morbidity, and value of care (inverted risk-adjusted mortality/total direct costs). RESULTS: Among 4,669 ICU admissions, 237 (5.1%) were overtriaged. Compared with 1,021 control ward admissions, overtriaged admissions had similar outcomes but higher costs ($15.9K [interquartile range $9.8K to $22.3K] vs $10.7K [$7.0K to $17.6K], p < 0.001) and lower value of care (0.2 [0.1 to 0.3] vs 1.5 [0.9 to 2.2], p < 0.001). Among 8,594 ward admissions, 1,029 (12.0%) were undertriaged. Compared with 2,498 control ICU admissions, undertriaged admissions had longer hospital length-of-stays (6.4 [3.4 to 12.4] vs 5.4 [2.6 to 10.4] days, p < 0.001); greater incidence of hospital mortality (1.7% vs 0.7%, p = 0.03), cardiac arrest (1.4% vs 0.5%, p = 0.04), and persistent acute kidney injury without renal recovery (5.2% vs 2.8%, p = 0.002); similar costs ($21.8K [$13.3K to $34.9K] vs $21.9K [$13.1K to $36.3K]); and lower value of care (0.8 [0.5 to 1.3] vs 1.2 [0.7 to 2.0], p < 0.001). CONCLUSIONS: Overtriage was associated with low value of care; undertriage was associated with both low value of care and increased mortality and morbidity. The proposed framework for generating automated postoperative triage classifications is reproducible.

Building an automated, machine learning-enabled platform for predicting post-operative complications.

Objective. In 2019, the University of Florida College of Medicine launched theMySurgeryRiskalgorithm to predict eight major post-operative complications using automatically extracted data from the electronic health record.Approach. This project was developed in parallel with our Intelligent Critical Care Center and represents a culmination of efforts to build an efficient and accurate model for data processing and predictive analytics.Main Results and Significance. This paper discusses how our model was constructed and improved upon. We highlight the consolidation of the database, processing of fixed and time-series physiologic measurements, development and training of predictive models, and expansion of those models into different aspects of patient assessment and treatment. We end by discussing future directions of the model.

Survival and neurologic outcomes following aortic occlusion for trauma and hemorrhagic shock in a hybrid operating room.

Background: Outcomes following aortic occlusion for trauma and hemorrhagic shock are poor, leading some to question the clinical utility of aortic occlusion in this setting. This study evaluates neurologically intact survival following resuscitative endovascular balloon occlusion of the aorta (REBOA) vs. resuscitative thoracotomy at a center with a dedicated trauma hybrid operating room with angiographic capabilities. Methods: This retrospective cohort analysis compared patients who underwent zone 1 aortic occlusion via resuscitative thoracotomy (n=13) vs. REBOA (n=13) for blunt or non-thoracic, penetrating trauma and refractory hemorrhagic shock (systolic blood pressure less than 90 mmHg despite volume resuscitation) at a level 1 trauma center with a dedicated, trauma hybrid operating room. The primary outcome was survival to hospital discharge. The secondary outcome was neurologic status at hospital discharge, assessed by Glasgow Coma Scale (GCS) scores. Results: Overall median age was 40 years, 27% had penetrating injuries, and 23% had pre-hospital closed-chest cardiopulmonary resuscitation. In both cohorts, median Injury Severity Scores and head Abbreviated Injury Scores were 26 and 2, respectively. The resuscitative thoracotomy cohort had lower systolic blood pressure on arrival (0 [0-75] vs. 76 [65-99], p=0.009). Hemorrhage control (systolic blood pressure 100 mmHg without ongoing vasopressor or transfusion requirements) was obtained in 77% of all REBOA cases and 8% of all resuscitative thoracotomy cases (p=0.001). Survival to hospital discharge was greater in the REBOA cohort (54% vs. 8%, p=0.030), as was discharge with GCS 15 (46% vs. 0%, p=0.015). Conclusions: Among patients undergoing aortic occlusion for blunt or non-thoracic, penetrating trauma and refractory hemorrhagic shock at a center with a dedicated, trauma hybrid operating room, nearly half of all patients managed with REBOA had neurologically intact survival. The high death rate in resuscitative thoracotomy and differences in patient cohorts limit direct comparison.