ABSTRACT
OBJECTIVES: Elevated intracranial pressure (ICP) is a potentially devastating complication of neurologic injury. Developing an ICP prediction algorithm to help the clinician adjust treatments and potentially prevent elevated ICP episodes. DESIGN: Retrospective study. SETTING: Three hundred thirty-five ICUs at 208 hospitals in the United States. SUBJECTS: Adults patients from the electronic ICU (eICU) Collaborative Research Database was used to train an ensemble machine learning model to predict the ICP 30 minutes in the future. Predictive performance was evaluated using a left-out test dataset and externally evaluated on the Medical Information Mart for Intensive Care-III (MIMIC-III) Matched Waveform Database. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Predictors included age, assigned sex, laboratories, medications and infusions, input/output, Glasgow Coma Scale (GCS) components, and time-series vitals (heart rate, ICP, mean arterial pressure, respiratory rate, and temperature). Each patient ICU stay was divided into successive 95-minute timeblocks. For each timeblock, the model was trained on nontime-varying covariates as well as on 12 observations of time-varying covariates at 5-minute intervals and asked to predict the 5-minute median ICP 30 minutes after the last observed ICP value. Data from 931 patients with ICP monitoring in the eICU dataset were extracted (46,207 timeblocks). The root mean squared error was 4.51 mm Hg in the eICU test set and 3.56 mm Hg in the MIMIC-III dataset. The most important variables driving ICP prediction were previous ICP history, patients' temperature, weight, serum creatinine, age, GCS, and hemodynamic parameters. CONCLUSIONS: IntraCranial pressure prediction AlgoRithm using machinE learning, an ensemble machine learning model, trained to predict the ICP of a patient 30 minutes in the future based on baseline characteristics and vitals data from the past hour showed promising predictive performance including in an external validation dataset.
ABSTRACT
INTRODUCTION: Risk factors for interpersonal violence-related injury (IPVRI) in low-income and middle-income countries (LMICs) remain poorly defined. We describe associations between IPVRI and select social determinants of health (SDH) in Cameroon. METHODS: We conducted a cross-sectional analysis of prospective trauma registry data collected from injured patients >15 years old between October 2017 and January 2020 at four Cameroonian hospitals. Our primary outcome was IPVRI, compared with unintentional injury. Explanatory SDH variables included education level, employment status, household socioeconomic status (SES) and alcohol use. The EconomicClusters model grouped patients into household SES clusters: rural, urban poor, urban middle-class (MC) homeowners, urban MC tenants and urban wealthy. Results were stratified by sex. Categorical variables were compared via Pearson's χ2 statistic. Associations with IPVRI were estimated using adjusted odds ratios (aOR) with 95% confidence intervals (95%CI). RESULTS: Among 7605 patients, 5488 (72.2%) were men. Unemployment was associated with increased odds of IPVRI for men (aOR 2.44 (95% CI 1.95 to 3.06), p<0.001) and women (aOR 2.53 (95% CI 1.35 to 4.72), p=0.004), as was alcohol use (men: aOR 2.33 (95% CI 1.91 to 2.83), p<0.001; women: aOR 3.71 (95% CI 2.41 to 5.72), p<0.001). Male patients from rural (aOR 1.45 (95% CI 1.04 to 2.03), p=0.028) or urban poor (aOR 2.08 (95% CI 1.27 to 3.41), p=0.004) compared with urban wealthy households had increased odds of IPVRI, as did female patients with primary-level/no formal (aOR 1.78 (95% CI 1.10 to 2.87), p=0.019) or secondary-level (aOR 1.54 (95% CI 1.03 to 2.32), p=0.037) compared with tertiary-level education. CONCLUSION: Lower educational attainment, unemployment, lower household SES and alcohol use are risk factors for IPVRI in Cameroon. Future research should explore LMIC-appropriate interventions to address SDH risk factors for IPVRI.
