Medical Research Council of South Africa.

BackgroundBetter understanding and prediction of PD progression could improve disease management and clinical trial design. We aimed to use longitudinal clinical, molecular, and genetic data to develop predictive models, compare potential biomarkers, and identify novel predictors for motor progression in PD. We also sought to assess the use of these models in the design of treatment trials in PD.MethodsA Bayesian multivariate predictive inference platform was applied to data from the Parkinson’s Progression Markers Initiative (PPMI) study (NCT01141023). We used genetic data and baseline molecular and clinical variables from PD patients and healthy controls to construct an ensemble of models to predict the annualised rate of the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale parts II and III combined. We tested our overall explanatory power, as assessed by the coefficient of determination (R2), and replicated novel findings in an independent clinical cohort of PD patients from the Longitudinal and Biomarker Study in PD (LABS-PD; NCT00605163). The potential utility of these models for clinical trial design was quantified by comparing simulated randomized placebo-controlled trials within the out-of sample LABS-PD cohort.FindingsA total of 117 controls and 312 PD cases were available for analysis. Our model ensemble exhibited strong performance in-cohort (5-fold cross-validated R2=41%, 95% CI: 35% – 47%) and significant, though reduced, performance out-of-cohort (R2=9%, 95% CI: 4% – 16%). Individual predictive features identified from PPMI data were confirmed in the LABS-PD cohort of 317 PD patients. These included significant replication of higher baseline motor score, male sex, and increased age, as well as a novel PD-specific epistatic interaction all indicative of faster motor progression. Genetic variation was the most useful predictive marker of motor progression (2.9%, 95%CI: 1.5–4.3%). CSF biomarkers at baseline showed a more modest (0.3%; 95%CI: 0.1–0.5%), but still significant effect on motor progression prediction. The simulations (n=5000) showed that incorporating the predicted rates of motor progression into the final models of treatment effect reduced the variability in the study outcome allowing significant differences to be detected at sample sizes up to 20% smaller than in naïve trials.InterpretationOur model ensemble confirmed established and identified novel predictors of PD motor progression. Improving existing prognostic models through machine learning approaches should benefit trial design and evaluation, as well as clinical disease monitoring and treatment.FundingMichael J. Fox Foundation for Parkinson’s Research and National Institute of Neurological Disorders and Stroke (1P20NS092529-01).

Background Maternal and neonatal mortality is high in Africa, but few large, prospective studies have been done to investigate the risk factors associated with these poor maternal and neonatal outcomes. Methods A 7-day, international, prospective, observational cohort study was done in patients having caesarean delivery in 183 hospitals across 22 countries in Africa. The inclusion criteria were all consecutive patients (aged ≥18 years) admitted to participating centres having elective and non-elective caesarean delivery during the 7-day study cohort period. To ensure a representative sample, each hospital had to provide data for 90% of the eligible patients during the recruitment week. The primary outcome was in-hospital maternal mortality and complications, which were assessed by local investigators. The study was registered on the South African National Health Research Database, number KZ_2015RP7_22, and on ClinicalTrials.gov, number NCT03044899. Findings Between February, 2016, and May, 2016, 3792 patients were recruited from hospitals across Africa. 3685 were included in the postoperative complications analysis (107 missing data) and 3684 were included in the maternal mortality analysis (108 missing data). These hospitals had a combined number of specialist surgeons, obstetricians, and anaesthetists totalling 0•7 per 100 000 population (IQR 0•2-2•0). Maternal mortality was 20 (0•5%) of 3684 patients (95% CI 0•3-0•8). Complications occurred in 633 (17•4%) of 3636 mothers (16•2-18•6), which were predominantly severe intraoperative and postoperative bleeding (136 [3•8%] of 3612 mothers). Maternal mortality was independently associated with a preoperative presentation of placenta praevia, placental abruption, ruptured uterus, antepartum haemorrhage (odds ratio 4•47 [95% CI 1•46-13•65]), and perioperative severe obstetric haemorrhage (5•87 [1•99-17•34]) or anaesthesia complications (11•47 (1•20-109•20]). Neonatal mortality was 153 (4•4%) of 3506 infants (95% CI 3•7-5•0). Interpretation Maternal mortality after caesarean delivery in Africa is 50 times higher than that of high-income countries and is driven by peripartum haemorrhage and anaesthesia complications. Neonatal mortality is double the global average. Early identification and appropriate management of mothers at risk of peripartum haemorrhage might improve maternal and neonatal outcomes in Africa.

We constructed accurate prediction models from EHR data using a hypothesis-free machine learning approach. Identification of established risk factors for T2D serves as proof of concept for this analytical approach, while novel factors selected by REFS represent emerging areas of T2D research. This methodology has potentially valuable downstream applications to personalized medicine and clinical research.