Dynamic ElecTronic hEalth reCord deTection (DETECT) of individuals at risk of a first episode of psychosis: a case-control development and validation study.

BACKGROUND: Many individuals who will experience a first episode of psychosis (FEP) are not detected before occurrence, limiting the effect of preventive interventions. The combination of machine-learning methods and electronic health records (EHRs) could help address this gap. METHODS: This case-control development and validation study is based on EHR data from IBM Explorys. The IBM Explorys Platform holds standardised, longitudinal, de-identified, patient-level EHR data pooled from different health-care systems with distinct EHRs. The present EHR-based studies were retrospective, matched (1:1), case-control studies compliant with RECORD, STROBE, and TRIPOD statements. The study included individuals in the IBM Explorys database who at some point between 1990 and 2018 had a diagnosis of FEP followed by schizophrenia, and psychosis-free matched control individuals from a random subsample of the full cohort. For every individual in the FEP cohort, the individual in the control cohort was matched to have a similar date for inclusion in the database and a similar total observation time. Individuals in the FEP cohort had their index date defined as the first diagnosis of psychosis or the first prescription of antipsychotic medication. Individuals in the control cohort had their index date defined to occur the same number of days after inclusion in the database as their matching FEP individual. The FEP and control cohorts were both randomly split into development and validation datasets in a ratio of 7:3. The subset of individuals in the validation dataset who had all their health-care encounters at providers that were not seen in the development dataset made up the external validation subset. A novel recurrent neural network model was developed to predict the risk of FEP 1 year before the index date by employing demographics and medical events (in the categories diagnoses, prescriptions, procedures, encounters and admissions, observations, and laboratory test results) dynamically collected in the EHR as part of clinical routine. We named the recurrent neural network Dynamic ElecTronic hEalth reCord deTection (DETECT). The main outcomes were accuracy and area under receiver operating characteristic curve (AUROC). Decision-curve analyses and dynamic patient journey plots were used to evaluate clinical usefulness. FINDINGS: The FEP and control cohorts each comprised 72 860 individuals. 102 030 individuals (51 015 matching pairs) were randomly allocated to the development dataset and the remaining 43 690 to the validation dataset. In the validation dataset, 4770 individuals had all their encounters outside of the 118 790 health-care providers that were encountered in the development dataset. The data from these individuals made up the external validation subset. The median follow-up (observation time before index date) was 6·0 years (IQR 3·0-10·4). In the development dataset, DETECT's prognostic accuracy was 0·787 and AUROC was 0·868. In the validation dataset, DETECT's prognostic accuracy was 0·774 and AUROC was 0·856. In the external test subset, DETECT's balanced prognostic accuracy was 0·724 and AUROC was 0·799. Prevalence-adjusted decision-curve analyses suggested that DETECT was associated with a positive net benefit in two different scenarios for FEP detection. INTERPRETATION: DETECT showed adequate prognostic accuracy to detect individuals at risk of developing a FEP in primary and secondary care. Replication and refinement in a population-based setting are needed to consolidate these findings. FUNDING: Lundbeck.

Weekday variation in triglyceride concentrations in 1.8 million blood samples.

Triglyceride (TG) concentration is used as a marker of cardiometabolic risk. However, diurnal and possibly weekday variation exists in TG concentrations. The objective of this work was to investigate weekday variation in TG concentrations among 1.8 million blood samples drawn between 2008 and 2015 from patients in the Capital region of Denmark. Plasma TG was extracted from a central clinical laboratory information system. Weekday variation was investigated by means of linear mixed models. In addition to the profound diurnal variation, the TG concentration was 4.5% lower on Fridays compared with Mondays (P < 0.0001). The variation persisted after multiple adjustments for confounders and was consistent across all sensitivity analyses. Out-patients and in-patients, respectively, had 5.0% and 1.9% lower TG concentrations on Fridays compared with Mondays (both P < 0.0001). The highest weekday variations in TG concentrations were recorded for out-patients between the ages of 9 and 26 years, with up to 20% higher values on Mondays compared with Fridays (all P < 0.05). In conclusion, TG concentrations were highest after the weekend and gradually declined during the week. We suggest that unhealthy food intake and reduced physical activity during the weekend increase TG concentrations which track into the week. This weekday variation may carry implications for public health and future research practice.

Potatoes and risk of obesity, type 2 diabetes, and cardiovascular disease in apparently healthy adults: a systematic review of clinical intervention and observational studies.

BACKGROUND: Potatoes have been related to increased risks of obesity, type 2 diabetes (T2D), and cardiovascular disease (CVD) mainly because of their high glycemic index. OBJECTIVE: We conducted a systematic review to evaluate the relation between intake of potatoes and risks of obesity, T2D, and CVD in apparently healthy adults. DESIGN: MEDLINE, Embase, the Web of Science, and the Cochrane Central Register of Controlled Trials were searched for intervention and prospective observational studies that investigated adults without any known illnesses at baseline, recorded intake of potatoes, and measured adiposity (body weight, body mass index, or waist circumference), cases of T2D, cases of cardiovascular events, or risk markers thereof. RESULTS: In total, 13 studies were deemed eligible; 5 studies were related to obesity, 7 studies were related to T2D, and one study was related to CVD. Only observational studies were identified; there were 3 studies with moderate, 9 studies with serious, and one study with critical risk of bias. The association between potatoes (not including french fries) and adiposity was neutral in 2 studies and was positive in 2 studies. French fries were positively associated with adiposity in 3 of 3 studies. For T2D, 2 studies showed a positive association, whereas 5 studies showed no or a negative association with intake of potatoes and T2D. French fries were positively associated with T2D in 3 of 3 studies that distinguished this relation. For CVD, no association was observed. CONCLUSIONS: The identified studies do not provide convincing evidence to suggest an association between intake of potatoes and risks of obesity, T2D, or CVD. French fries may be associated with increased risks of obesity and T2D although confounding may be present. In this systematic review, only observational studies were identified. These findings underline the need for long-term randomized controlled trials. This trial was registered at the PROSPERO International prospective register of systematic reviews (www.crd.york.ac.uk/PROSPERO/) as CRD42015026491.