Importance Surgeons make complex, high-stakes decisions under time constraints and uncertainty, with significant effect on patient outcomes. This review describes the weaknesses of traditional clinical decision-support systems and proposes that artificial intelligence should be used to augment surgical decision-making. Observations Surgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics. These factors can lead to bias, error, and preventable harm. Traditional predictive analytics and clinical decision-support systems are intended to augment surgical decision-making, but their clinical utility is compromised by time-consuming manual data management and suboptimal accuracy. These challenges can be overcome by automated artificial intelligence models fed by livestreaming electronic health record data with mobile device outputs. This approach would require data standardization, advances in model interpretability, careful implementation and monitoring, attention to ethical challenges involving algorithm bias and accountability for errors, and preservation of bedside assessment and human intuition in the decision-making process. Conclusions and Relevance Integration of artificial intelligence with surgical decision-making has the potential to transform care by augmenting the decision to operate, informed consent process, identification and mitigation of modifiable risk factors, decisions regarding postoperative management, and shared decisions regarding resource use.

Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require time-consuming, error-prone calculations using static variable thresholds. These methods do not capitalize on the emerging availability of streaming electronic health record data or capture time-sensitive individual physiological patterns, a critical task in the intensive care unit. We propose a novel acuity score framework (DeepSOFA) that leverages temporal measurements and interpretable deep learning models to assess illness severity at any point during an ICU stay. We compare DeepSOFA with SOFA (Sequential Organ Failure Assessment) baseline models using the same model inputs and find that at any point during an ICU admission, DeepSOFA yields significantly more accurate predictions of in-hospital mortality. A DeepSOFA model developed in a public database and validated in a single institutional cohort had a mean AUC for the entire ICU stay of 0.90 (95% CI 0.90–0.91) compared with baseline SOFA models with mean AUC 0.79 (95% CI 0.79–0.80) and 0.85 (95% CI 0.85–0.86). Deep models are well-suited to identify ICU patients in need of life-saving interventions prior to the occurrence of an unexpected adverse event and inform shared decision-making processes among patients, providers, and families regarding goals of care and optimal resource utilization.

Clinical and technological advances promoting early hemorrhage control and physiologic resuscitation as well as early diagnosis and optimal treatment of sepsis have significantly decreased in-hospital mortality for many critically ill patient populations. However, a substantial proportion of severe trauma and sepsis survivors will develop protracted organ dysfunction termed chronic critical illness (CCI), defined as ≥14 days requiring intensive care unit (ICU) resources with ongoing organ dysfunction. A subset of CCI patients will develop the persistent inflammation, immunosuppression, and catabolism syndrome (PICS), and these individuals are predisposed to a poor quality of life and indolent death. We propose that CCI and PICS after trauma or sepsis are the result of an inappropriate bone marrow response characterized by the generation of dysfunctional myeloid populations at the expense of lympho- and erythropoiesis. This review describes similarities among CCI/PICS phenotypes in sepsis, cancer, and aging and reviews the role of aberrant myelopoiesis in the pathophysiology of CCI and PICS. In addition, we characterize pathogen recognition, the interface between innate and adaptive immune systems, and therapeutic approaches including immune modulators, gut microbiota support, and nutritional and exercise therapy. Finally, we discuss the future of diagnostic and prognostic approaches guided by machine and deep-learning models trained and validated on big data to identify patients for whom these approaches will yield the greatest benefits. A deeper understanding of the pathophysiology of CCI and PICS and continued investigation into novel therapies harbor the potential to improve the current dismal long-term outcomes for critically ill post-injury and post-infection patients.

Background: Many sepsis survivors develop chronic critical illness (CCI) and are assumed to be immunosuppressed, but there is limited clinical evidence to support this. We sought to determine whether the incidence of secondary infections and immunosuppressive biomarker profiles of patients with CCI differ from those with rapid recovery (RAP) after sepsis. Methods: This prospective observational study evaluated 88 critically ill patients with sepsis and 20 healthy controls. Cohorts were defined based on clinical trajectory (early death, RAP, or CCI), whereas immunosuppression was clinically determined by the presence of a postsepsis secondary infection. Serial blood samples were collected for absolute lymphocyte counts (ALCs), monocytic human leukocyte antigen-DR (mHLA-DR) expression, and plasma-soluble programmed death-ligand 1 (sPD-L1) concentrations. Results: Of the 88 patients with sepsis, 3 (3%) died within 14 days of sepsis onset, 50 (57%) experienced RAP, and 35 (40%) developed CCI. Compared with RAP patients, CCI patients exhibited a higher incidence and overall number of infections adjusted for hospital length of stay. ALC and mHLA-DR levels were dramatically reduced at the time of sepsis diagnosis when compared with healthy controls, whereas sPD-L1 concentrations were significantly elevated. There were no differences between RAP and CCI patients in ALC, sPD-L1, or mHLA-DR at the time of diagnosis or within 24 h after sepsis diagnosis. However, in contrast to the RAP group, CCI patients failed to exhibit any trend toward restoration of normal values of ALC, HLA-DR, and sPD-L1. Conclusions: Septic patients demonstrate clinical and biological evidence to suggest they are immunosuppressed at the time of sepsis diagnosis. Those who develop CCI have a greater incidence of secondary infections and persistently aberrant markers of impaired host immunity, although measurements at the time of sepsis onset did not distinguish between subjects with RAP and CCI.

Human pathophysiology is occasionally too complex for unaided hypothetical-deductive reasoning and the isolated application of additive or linear statistical methods. Clustering algorithms use input data patterns and distributions to form groups of similar patients or diseases that share distinct properties. Although clinicians frequently perform tasks that may be enhanced by clustering, few receive formal training and clinician-centered literature in clustering is sparse. To add value to clinical care and research, optimal clustering practices require a thorough understanding of how to process and optimize data, select features, weigh strengths and weaknesses of different clustering methods, select the optimal clustering method, and apply clustering methods to solve problems. These concepts and our suggestions for implementing them are described in this narrative review of published literature. All clustering methods share the weakness of finding potential clusters even when natural clusters do not exist, underscoring the importance of applying data-driven techniques as well as clinical and statistical expertise to clustering analyses. When applied properly, patient and disease phenotype clustering can reveal obscured associations that can help clinicians understand disease pathophysiology, predict treatment response, and identify patients for clinical trial enrollment.