Clinically applicable approach for predicting mechanical ventilation in patients with COVID-19.

BACKGROUND: Patients with coronavirus disease 2019 (COVID-19) requiring mechanical ventilation have high mortality and resource utilisation. The ability to predict which patients may require mechanical ventilation allows increased acuity of care and targeted interventions to potentially mitigate deterioration. METHODS: We included hospitalised patients with COVID-19 in this single-centre retrospective observational study. Our primary outcome was mechanical ventilation or death within 24 h. As clinical decompensation is more recognisable, but less modifiable, as the prediction window shrinks, we also assessed 4, 8, and 48 h prediction windows. Model features included demographic information, laboratory results, comorbidities, medication administration, and vital signs. We created a Random Forest model, and assessed performance using 10-fold cross-validation. The model was compared with models derived from generalised estimating equations using discrimination. RESULTS: Ninety-three (23%) of 398 patients required mechanical ventilation or died within 14 days of admission. The Random Forest model predicted pending mechanical ventilation with good discrimination (C-statistic=0.858; 95% confidence interval, 0.841-0.874), which is comparable with the discrimination of the generalised estimating equation regression. Vitals sign data including SpO2/FiO2 ratio (Random Forest Feature Importance Z-score=8.56), ventilatory frequency (5.97), and heart rate (5.87) had the highest predictive utility. In our highest-risk cohort, the number of patients needed to identify a single new case was 3.2, and for our second quintile it was 5.0. CONCLUSION: Machine learning techniques can be leveraged to improve the ability to predict which patients with COVID-19 are likely to require mechanical ventilation, identifying unrecognised bellwethers and providing insight into the constellation of accompanying signs of respiratory failure in COVID-19.

Genetic mutations associated with susceptibility to perioperative complications in a longitudinal biorepository with integrated genomic and electronic health records.

BACKGROUND: Existing genetic information can be leveraged to identify patients with susceptibilities to conditions that might impact their perioperative care, but clinicians generally have limited exposure and are not trained to contextualise this information. We identified patients with genetic susceptibilities to anaesthetic complications using a perioperative biorepository and characterised the concordance with existing diagnoses. METHODS: Adult patients undergoing surgery within Michigan Medicine from 2012 to 2017 were consented for genotyping. Genotypes were integrated with the electronic health record (EHR). We retrospectively characterised frequencies of variants associated with butyrylcholinesterase deficiency, factor V Leiden, and malignant hyperthermia, three pharmacogenetic factors with perioperative implications. We calculated the percentage homozygous and heterozygous for each that had been diagnosed previously and searched for EHR findings consistent with a predisposition. RESULTS: Analysis of genetic data revealed that 25 out of 40 769 (0.1%) patients were homozygous and 1918 (4.7%) were heterozygous for mutations associated with butyrylcholinesterase deficiency. Of the homozygous individuals, 14 (56%) carried a pre-existing diagnosis. For factor V Leiden, 29 (0.1%) were homozygous and 2153 (5.3%) heterozygous. Of the homozygous individuals, three (10%) were diagnosed by EHR-derived phenotype and six (21%) by clinician review. Malignant hyperthermia was assessed in a subset of patients. We detected two patients with associated mutations. Neither carried clinical diagnoses. CONCLUSIONS: We identified patients with genetic susceptibility to perioperative complications using an open source script designed for clinician use. We validated this application in a retrospective analysis for three conditions with well-characterised inheritance, and showed that not all genetic susceptibilities were documented in the EHR.

Use of a Polygenic Risk Score Improves Prediction of Myocardial Injury After Non-Cardiac Surgery.

BACKGROUND: While postoperative myocardial injury remains a major driver of morbidity and mortality, the ability to accurately identify patients at risk remains limited despite decades of clinical research. The role of genetic information in predicting myocardial injury after noncardiac surgery (MINS) remains unknown and requires large scale electronic health record and genomic data sets. METHODS: In this retrospective observational study of adult patients undergoing noncardiac surgery, we defined MINS as new troponin elevation within 30 days following surgery. To determine the incremental value of polygenic risk score (PRS) for coronary artery disease, we added the score to 3 models of MINS risk: revised cardiac risk index, a model comprised entirely of preoperative variables, and a model with combined preoperative plus intraoperative variables. We assessed performance without and with PRSs via area under the receiver operating characteristic curve and net reclassification index. RESULTS: Among 90 053 procedures across 40 498 genotyped individuals, we observed 429 cases with MINS (0.5%). PRS for coronary artery disease was independently associated with MINS for each multivariable model created (odds ratio=1.12 [95% CI, 1.02-1.24], P=0.023 in the revised cardiac risk index-based model; odds ratio, 1.19 [95% CI, 1.07-1.31], P=0.001 in the preoperative model; and odds ratio, 1.17 [95% CI, 1.06-1.30], P=0.003 in the preoperative plus intraoperative model). The addition of clinical risk factors improved model discrimination. When PRS was included with preoperative and preoperative plus intraoperative models, up to 3.6% of procedures were shifted into a new outcome classification. CONCLUSIONS: The addition of a PRS does not significantly improve discrimination but remains independently associated with MINS and improves goodness of fit. As genetic analysis becomes more common, clinicians will have an opportunity to use polygenic risk to predict perioperative complications. Further studies are necessary to determine if PRSs can inform MINS surveillance.