Richard Lee Kennedy

Feature engineering is a time consuming component of predictive modeling. We propose a versatile platform to automatically extract features for risk prediction, based on a pre-defined and extensible entity schema. The extraction is independent of disease type or risk prediction task. We contrast auto-extracted features to baselines generated from the Elixhauser comorbidities. Hospital medical records was transformed to event sequences, to which filters were applied to extract feature sets capturing diversity in temporal scales and data types. The features were evaluated on a readmission prediction task, comparing with baseline feature sets generated from the Elixhauser comorbidities. The prediction model was through logistic regression with elastic net regularization. Predictions horizons of 1, 2, 3, 6, 12 months were considered for four diverse diseases: diabetes, COPD, mental disorders and pneumonia, with derivation and validation cohorts defined on non-overlapping data-collection periods. For unplanned readmissions, auto-extracted feature set using socio-demographic information and medical records, outperformed baselines derived from the socio-demographic information and Elixhauser comorbidities, over 20 settings (5 prediction horizons over 4 diseases). In particular over 30-day prediction, the AUCs are: COPD—baseline: 0.60 (95% CI: 0.57, 0.63), auto-extracted: 0.67 (0.64, 0.70); diabetes—baseline: 0.60 (0.58, 0.63), auto-extracted: 0.67 (0.64, 0.69); mental disorders—baseline: 0.57 (0.54, 0.60), auto-extracted: 0.69 (0.64,0.70); pneumonia—baseline: 0.61 (0.59, 0.63), auto-extracted: 0.70 (0.67, 0.72). The advantages of auto-extracted standard features from complex medical records, in a disease and task agnostic manner were demonstrated. Auto-extracted features have good predictive power over multiple time horizons. Such feature sets have potential to form the foundation of complex automated analytic tasks.

Objective: Readmission rates are high following acute myocardial infarction (AMI), but risk stratification has proved difficult because known risk factors are only weakly predictive. In the present study, we applied hospital data to identify the risk of unplanned admission following AMI hospitalisations. Methods: The study included 1660 consecutive AMI admissions. Predictive models were derived from 1107 randomly selected records and tested on the remaining 553 records. The electronic medical record (EMR) model was compared with a seven-factor predictive score known as the HOSPITAL score and a model derived from Elixhauser comorbidities. All models were evaluated for the ability to identify patients at high risk of 30-day ischaemic heart disease readmission and those at risk of all-cause readmission within 12 months following the initial AMI hospitalisation. Results: The EMR model has higher discrimination than other models in predicting ischaemic heart disease readmissions (area under the curve (AUC) 0.78; 95% confidence interval (CI) 0.71–0.85 for 30-day readmission). The positive predictive value was significantly higher with the EMR model, which identifies cohorts that were up to threefold more likely to be readmitted. Factors associated with readmission included emergency department attendances, cardiac diagnoses and procedures, renal impairment and electrolyte disturbances. The EMR model also performed better than other models (AUC 0.72; 95% CI 0.66–0.78), and with greater positive predictive value, in identifying 12-month risk of all-cause readmission. Conclusions: Routine hospital data can help identify patients at high risk of readmission following AMI. This could lead to decreased readmission rates by identifying patients suitable for targeted clinical interventions. What is known about the topic?: Many clinical and demographic risk factors are known for hospital readmissions following acute myocardial infarction, including multivessel disease, high baseline heart rate, hypertension, diabetes, obesity, chronic obstructive pulmonary disease and psychiatric morbidity. However, combining these risk factors into indices for predicting readmission had limited success. A recent study reported a C-statistic of 0.73 for predicting 30-day readmissions. In a recent American study, a simple seven-factor score was shown to predict hospital readmissions among medical patients. What does this paper add?: This paper presents a way to predict readmissions following myocardial infarction using routinely collected administrative data. The model performed better than the recently described HOSPITAL score and a model derived from Elixhauser comorbidities. Moreover, the model uses only data generally available in most hospitals. What are the implications for practitioners?: Routine hospital data available at discharges can be used to tailor preventative care for AMI patients, to improve institutional performance and to decrease the cost burden associated with AMI.

To date, our ability to accurately identify patients at high risk from suicidal behaviour, and thus to target interventions, has been fairly limited. This study examined a large pool of factors that are potentially associated with suicide risk from the comprehensive electronic medical record (EMR) and to derive a predictive model for 1–6 month risk. 7,399 patients undergoing suicide risk assessment were followed up for 180 days. The dataset was divided into a derivation and validation cohorts of 4,911 and 2,488 respectively. Clinicians used an 18-point checklist of known risk factors to divide patients into low, medium, or high risk. Their predictive ability was compared with a risk stratification model derived from the EMR data. The model was based on the continuation-ratio ordinal regression method coupled with lasso (which stands for least absolute shrinkage and selection operator). In the year prior to suicide assessment, 66.8% of patients attended the emergency department (ED) and 41.8% had at least one hospital admission. Administrative and demographic data, along with information on prior self-harm episodes, as well as mental and physical health diagnoses were predictive of high-risk suicidal behaviour. Clinicians using the 18-point checklist were relatively poor in predicting patients at high-risk in 3 months (AUC 0.58, 95% CIs: 0.50 – 0.66). The model derived EMR was superior (AUC 0.79, 95% CIs: 0.72 – 0.84). At specificity of 0.72 (95% CIs: 0.70-0.73) the EMR model had sensitivity of 0.70 (95% CIs: 0.56-0.83). Predictive models applied to data from the EMR could improve risk stratification of patients presenting with potential suicidal behaviour. The predictive factors include known risks for suicide, but also other information relating to general health and health service utilisation.

Gestational Diabetes Mellitus (GDM) has well recognised adverse health implications for the mother and her newborn that are both short and long term. Obesity is a significant risk factor for developing GDM and the prevalence of obesity is increasing globally. It is a matter of public health importance that clinicians have evidence based strategies to inform practice and currently there is insufficient evidence regarding the impact of dietary and lifestyle interventions on improving maternal and newborn outcomes. The primary aim of this study is to measure the impact of a telephone based intervention that promotes positive lifestyle modifications on the incidence of GDM. Secondary aims include: the impact on gestational weight gain; large for gestational age babies; differences in blood glucose levels taken at the Oral Glucose Tolerance Test (OGTT) and selected factors relating to self-efficacy and psychological wellbeing.