Predicting Nondiagnostic Home Sleep Apnea Tests Using Machine Learning.

STUDY OBJECTIVES: Home sleep apnea testing (HSAT) is an efficient and cost-effective method of diagnosing obstructive sleep apnea (OSA). However, nondiagnostic HSAT necessitates additional tests that erode these benefits, delaying diagnoses and increasing costs. Our objective was to optimize this diagnostic pathway by using predictive modeling to identify patients who should be referred directly to polysomnography (PSG) due to their high probability of nondiagnostic HSAT. METHODS: HSAT performed as the initial test for suspected OSA within the Veterans Administration Greater Los Angeles Healthcare System was analyzed retrospectively. Data were extracted from pre-HSAT questionnaires and the medical record. Tests were diagnostic if there was a respiratory event index (REI) ≥ 5 events/h. Tests with REI < 5 events/h or technical inadequacy-two outcomes requiring additional testing with PSG-were considered nondiagnostic. Standard logistic regression models were compared with models trained using machine learning techniques. RESULTS: Models were trained using 80% of available data and validated on the remaining 20%. Performance was evaluated using partial area under the precision-recall curve (pAUPRC). Machine learning techniques consistently yielded higher pAUPRC than standard logistic regression, which had pAUPRC of 0.574. The random forest model outperformed all other models (pAUPRC 0.862). Preferred calibration of this model yielded the following: sensitivity 0.46, specificity 0.95, positive predictive value 0.81, negative predictive value 0.80. CONCLUSIONS: Compared with standard logistic regression models, machine learning models improve prediction of patients requiring in-laboratory PSG. These models could be implemented into a clinical decision support tool to help clinicians select the optimal test to diagnose OSA.

Effect of Boarding on Mortality in ICUs.

OBJECTIVES: Hospitals use a variety of strategies to maximize the availability of limited ICU beds. Boarding, which involves assigning patients to an open bed in a different subspecialty ICU, is one such practice employed when ICU occupancy levels are high, and beds in a particular unit are unavailable. Boarding disrupts the normal geographic colocation of patients and care teams, exposing patients to nursing staff with different training and expertise to those caring for nonboarders. We analyzed whether medical ICU patients boarding in alternative specialty ICUs are at increased risk of mortality. DESIGN: Retrospective cohort study using an instrumental variable analysis to control for unmeasured confounding. A semiparametric bivariate probit estimation strategy was employed for the instrumental model. Propensity score matching and standard logistic regression (generalized linear modeling) were used as robustness checks. SETTING: The medical ICU of a tertiary care nonprofit hospital in the United States between 2002 and 2012. PATIENTS: All medical ICU admissions during the specified time period. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The study population consisted of 8,429 patients of whom 1,871 were boarders. The instrumental variable model demonstrated a relative risk of 1.18 (95% CI, 1.01-1.38) for ICU stay mortality for boarders. The relative risk of in-hospital mortality among boarders was 1.22 (95% CI, 1.00-1.49). GLM and propensity score matching without use of the instrument yielded similar estimates. Instrumental variable estimates are for marginal patients, whereas generalized linear modeling and propensity score matching yield population average effects. CONCLUSIONS: Mortality increased with boarding of critically ill patients. Further research is needed to identify safer practices for managing patients during periods of high ICU occupancy.

Response to Comment on "Estimating the reproducibility of psychological science".

Gilbert et al. conclude that evidence from the Open Science Collaboration's Reproducibility Project: Psychology indicates high reproducibility, given the study methodology. Their very optimistic assessment is limited by statistical misconceptions and by causal inferences from selectively interpreted, correlational data. Using the Reproducibility Project: Psychology data, both optimistic and pessimistic conclusions about reproducibility are possible, and neither are yet warranted.