Application of Machine Learning Models to Biomedical and Information System Signals From Critically Ill Adults.

BACKGROUND: Machine learning (ML)-derived notifications for impending episodes of hemodynamic instability and respiratory failure events are interesting because they can alert physicians in time to intervene before these complications occur. RESEARCH QUESTION: Do ML alerts, telemedicine system (TS)-generated alerts, or biomedical monitors (BMs) have superior performance for predicting episodes of intubation or administration of vasopressors? STUDY DESIGN AND METHODS: An ML algorithm was trained to predict intubation and vasopressor initiation events among critically ill adults. Its performance was compared with BM alarms and TS alerts. RESULTS: ML notifications were substantially more accurate and precise, with 50-fold lower alarm burden than TS alerts for predicting vasopressor initiation and intubation events. ML notifications of internal validation cohorts demonstrated similar performance for independent academic medical center external validation and COVID-19 cohorts. Characteristics were also measured for a control group of recent patients that validated event detection methods and compared TS alert and BM alarm performance. The TS test characteristics were substantially better, with 10-fold less alarm burden than BM alarms. The accuracy of ML alerts (0.87-0.94) was in the range of other clinically actionable tests; the accuracy of TS (0.28-0.53) and BM (0.019-0.028) alerts were not. Overall test performance (F scores) for ML notifications were more than fivefold higher than for TS alerts, which were higher than those of BM alarms. INTERPRETATION: ML-derived notifications for clinically actioned hemodynamic instability and respiratory failure events represent an advance because the magnitude of the differences of accuracy, precision, misclassification rate, and pre-event lead time is large enough to allow more proactive care and has markedly lower frequency and interruption of bedside physician work flows.

Validation of an Automatic Tagging System for Identifying Respiratory and Hemodynamic Deterioration Events in the Intensive Care Unit.

OBJECTIVE: Predictive models for critical events in the intensive care unit (ICU) might help providers anticipate patient deterioration. At the heart of predictive model development lies the ability to accurately label significant events, thereby facilitating the use of machine learning and similar strategies. We conducted this study to establish the validity of an automated system for tagging respiratory and hemodynamic deterioration by comparing automatic tags to tagging by expert reviewers. METHODS: This retrospective cohort study included 72,650 unique patient stays collected from Electronic Medical Records of the University of Massachusetts' eICU. An enriched subgroup of stays was manually tagged by expert reviewers. The tags generated by the reviewers were compared to those generated by an automated system. RESULTS: The automated system was able to rapidly and efficiently tag the complete database utilizing available clinical data. The overall agreement rate between the automated system and the clinicians for respiratory and hemodynamic deterioration tags was 89.4% and 87.1%, respectively. The automatic system did not add substantial variability beyond that seen among the reviewers. CONCLUSIONS: We demonstrated that a simple rule-based tagging system could provide a rapid and accurate tool for mass tagging of a compound database. These types of tagging systems may replace human reviewers and save considerable resources when trying to create a validated, labeled database used to train artificial intelligence algorithms. The ability to harness the power of artificial intelligence depends on efficient clinical validation of targeted conditions; hence, these systems and the methodology used to validate them are crucial.

CXCL12 is a constitutive and inflammatory chemokine in the intestinal immune system.

BACKGROUND: Inflammatory bowel disease (IBD) is characterized by increased lymphocytic infiltrate to the lamina propria (LP) and upregulation of inflammatory chemokines and receptors. CXCL12 is a constitutive chemokine involved in lung, brain, and joint inflammation. We hypothesized that CXCL12 and its receptor, CXCR4, would have a constitutive and inflammatory role in the gut. METHODS: Intestinal epithelial cells (IECs) and T lymphocytes were isolated from intestinal mucosa of IBD and control patients undergoing bowel resection. Autologous T cells were isolated from peripheral blood (PB). CXCL12 and CXCR4 expression by IECs was assessed by polymerase chain reaction and immunohistochemistry, lymphocyte phenotype by flow cytometry, and migration by Transwells. RESULTS: IECs expressed CXCL12 and expression was increased and more diffuse in IBD compared to normal crypts (ulcerative colitis [UC] > Crohn's disease [CD], inflamed > noninflamed). CXCR4 was expressed by IECs, LP T cells (LPTs), and PB T cells (PBTs), and CXCR4+ cells were increased in IBD LP in situ. PBTs and LPTs from all patients had a high and comparable migration toward CXCL12 (P < 0.0001 and P < 0.05 vs. medium, respectively). Migration toward IBD-IEC-derived supernatant was significantly higher compared to normal. Antibodies against CXCR4 and CXCL12 blocked migration. CONCLUSIONS: CXCL12 is expressed by normal IECs and upregulated and differentially distributed in IBD IECs. CXCR4 is expressed by IECs and LPTs, and CXCR4+ cells are significantly increased in IBD LP. CXCL12 is chemotactic for both PBTs and LPTs. Thus, CXCL12 and CXCR4 have a constitutive and inflammatory role in the intestinal mucosa and their selective therapeutic manipulation may be considered in IBD management.

Serum cortisol levels in patients admitted to the department of medicine: Prognostic correlations and effects of age, infection, and comorbidity.

BACKGROUND: In contrast to healthy adults or critically ill patients, data on serum cortisol levels in noncritically ill patients admitted to general internal medicine wards has not been well characterized. We aimed to describe the distribution and range of serum cortisol levels in patients admitted to the department of medicine, to discover whether old age, severe infections, or comorbidity induced a blunted hypothalamic-pituitary-adrenal (HPA) response and whether initial serum cortisol value had a prognostic significance. METHODS: Morning (8 am) serum cortisol level together with epidemiologic, clinical, and laboratory data were analyzed for 252 consecutive adult (age > or = 18 yrs) patients admitted to the department of internal medicine during a 6-weeks period. RESULTS: The mean serum cortisol level (541 +/- 268 nmol/L) was within the normal range. Only one patient had a low serum cortisol level of 72 nmol/L, whereas the majority of patients had either normal (80%) or increased (19%) serum cortisol levels. Older age, sepsis, prolonged duration of fever, higher comorbidity score, and higher serum creatinine level were each associated with significantly higher serum cortisol level. In addition, a higher serum cortisol level was significantly related to longer hospitalization and higher in-hospital mortality rate. CONCLUSIONS: Serum cortisol level positively correlated with age, disease severity, and outcome. All admitted patients, except one, had normal to high serum cortisol. Whether this increased cortisol level is an adequate HPA response or less than required for the disease-induced stress should be investigated in further studies.