Machine learning can help clinicians to make individualized patient predictions only if researchers demonstrate models that contribute novel insights, rather than learning the most likely next step in a set of actions a clinician will take. We trained deep learning models using only clinician-initiated, administrative data for 42.9 million admissions using three subsets of data: demographic data only, demographic data and information available at admission, and the previous data plus charges recorded during the first day of admission. Models trained on charges during the first day of admission achieve performance close to published full EMR-based benchmarks for inpatient outcomes: inhospital mortality (0.89 AUC), prolonged length of stay (0.82 AUC), and 30-day readmission rate (0.71 AUC). Similar performance between models trained with only clinician-initiated data and those trained with full EMR data purporting to include information about patient state and physiology should raise concern in the deployment of these models. Furthermore, these models exhibited significant declines in performance when evaluated over only myocardial infarction (MI) patients relative to models trained over MI patients alone, highlighting the importance of physician diagnosis in the prognostic performance of these models. These results provide a benchmark for predictive accuracy trained only on prior clinical actions and indicate that models with similar performance may derive their signal by looking over clinician’s shoulders—using clinical behavior as the expression of preexisting intuition and suspicion to generate a prediction. For models to guide clinicians in individual decisions, performance exceeding these benchmarks is necessary.

Background Characterization of prediagnostic Parkinson’s Disease (PD) and early prediction of subsequent development are critical for preventive interventions, risk stratification and understanding of disease pathology. This study aims to characterize the role of the prediagnostic period in PD and, using selected features from this period as novel interception points, construct a prediction model to accelerate the diagnosis in a real-world setting. Methods We constructed two sets of machine learning models: a retrospective approach highlighting exposures up to 5 years prior to PD diagnosis, and an alternative model that prospectively predicted future PD diagnosis from all individuals at their first diagnosis of a gait or tremor disorder, these being features that appeared to represent the initiation of a differential diagnostic window. Results We found many novel features captured by the retrospective models; however, the high accuracy was primarily driven from surrogate diagnoses for PD, such as gait and tremor disorders, suggesting the presence of a distinctive differential diagnostic period when the clinician already suspected PD. The model utilizing a gait/tremor diagnosis as the interception point, achieved a validation AUC of 0.874 with potential time compression to a future PD diagnosis of more than 300 days. Comparisons of predictive diagnoses between the prospective and prediagnostic cohorts suggest the presence of distinctive trajectories of PD progression based on comorbidity profiles. Conclusions Overall, our machine learning approach allows for both guiding clinical decisions such as the initiation of neuroprotective interventions and importantly, the possibility of earlier diagnosis for clinical trials for disease modifying therapies.

A randomized, 4-week, double-blind trial followed by an open-label extension trial assessed the efficacy and safety of a once-daily, extended-release morphine formulation (Avinza (previously referred to as Morphelan)) in 295 patients with chronic, moderate-to-severe osteoarthritis pain who had failed to obtain adequate pain relief with NSAIDs and acetaminophen. Participants received one of four treatments: Avinza 30 mg once daily (QAM or QPM), MS Contin(R) 15 mg twice daily, or placebo twice daily. Patients (n =181) received Avinza QAM or QPM during the 26-week open-label extension trial and could increase their dose to optimize pain control. Avinza and MS Contin reduced pain and improved several sleep measures versus placebo. Analgesic efficacy was comparable between Avinza and MS Contin; however, Avinza QAM demonstrated greater improvements in overall quality of sleep. The most common adverse events were constipation and nausea. The majority of AEs occurred at a similar incidence among the active treatment groups.

Since the discovery of the prolyl hydroxylases domain (PHD) proteins and their canonical hypoxia-inducible factor (HIF) substrate two decades ago, a number of in vitro hydroxylation (IVH) assays for PHD activity have been developed to measure the PHD–HIF interaction. However, most of these assays either require complex proteomics mass spectrometry methods that rely on the specific PHD–HIF interaction or require the handling of radioactive material, as seen in the most commonly used assay measuring [ 14 C]O 2 release from labeled [ 14 C]α-ketoglutarate. Here, we report an alternative rapid, cost-effective assay in which the consumption of α-ketoglutarate is monitored by its derivatization with 2,4-dinitrophenylhydrazine (2,4-DNPH) followed by treatment with concentrated base. We extensively optimized this 2,4-DNPH α-ketoglutarate assay to maximize the signal-to-noise ratio and demonstrated that it is robust enough to obtain kinetic parameters of the well-characterized PHD2 isoform comparable with those in published literature. We further showed that it is also sensitive enough to detect and measure the IC 50 values of pan-PHD inhibitors and several PHD2 inhibitors in clinical trials for chronic kidney disease (CKD)-induced anemia. Given the efficiency of this assay coupled with its multiwell format, the 2,4-DNPH α-KG assay may be adaptable to explore non-HIF substrates of PHDs and potentially to high-throughput assays.