Decision Support System Detecting Patients at Risk of Prolonged QT and Associated Mortality.

Prolonged QT interval is an independent risk factor for all-cause mortality. However, evaluation of mortality associated to the implementation of a clinical decision support system to increase awareness and provide management recommendations has been challenging. Here we present our attempt to develop a model using only electronic data and different control groups.

SDF-1α in glycan nanoparticles exhibits full activity and reduces pulmonary hypertension in rats.

To establish a homing signal in the lung to recruit circulating stem cells for tissue repair, we formulated a nanoparticle, SDF-1α NP, by complexing SDF-1α with dextran sulfate and chitosan. The data show that SDF-1α was barely released from the nanoparticles over an extended period of time in vitro (3% in 7 days at 37 °C); however, incorporated SDF-1α exhibited full chemotactic activity and receptor activation compared to its free form. The nanoparticles were not endocytosed after incubation with Jurkat cells. When aerosolized into the lungs of rats, SDF-1α NP displayed a greater retention time compared to free SDF-1α (64 vs 2% remaining at 16 h). In a rat model of monocrotaline-induced lung injury, SDF-1α NP, but not free form SDF-1α, was found to reduce pulmonary hypertension. These data suggest that the nanoparticle formulation protected SDF-1α from rapid clearance in the lung and sustained its biological function in vivo.

A Clinician's Guide to Running Custom Machine-Learning Models in an Electronic Health Record Environment.

We recently brought an internally developed machine-learning model for predicting which patients in the emergency department would require hospital admission into the live electronic health record environment. Doing so involved navigating several engineering challenges that required the expertise of multiple parties across our institution. Our team of physician data scientists developed, validated, and implemented the model. We recognize a broad interest and need to adopt machine-learning models into clinical practice and seek to share our experience to enable other clinician-led initiatives. This Brief Report covers the entire model deployment process, starting once a team has trained and validated a model they wish to deploy in live clinical operations.

Assessing the Generalizability of a Clinical Machine Learning Model Across Multiple Emergency Departments.

Objective: To assess the generalizability of a clinical machine learning algorithm across multiple emergency departments (EDs). Patients and Methods: We obtained data on all ED visits at our health care system's largest ED from May 5, 2018, to December 31, 2019. We also obtained data from 3 satellite EDs and 1 distant-hub ED from May 1, 2018, to December 31, 2018. A gradient-boosted machine model was trained on pooled data from the included EDs. To prevent the effect of differing training set sizes, the data were randomly downsampled to match those of our smallest ED. A second model was trained on this downsampled, pooled data. The model's performance was compared using area under the receiver operating characteristic (AUC). Finally, site-specific models were trained and tested across all the sites, and the importance of features was examined to understand the reasons for differing generalizability. Results: The training data sets contained 1918-64,161 ED visits. The AUC for the pooled model ranged from 0.84 to 0.94 across the sites; the performance decreased slightly when Ns were downsampled to match those of our smallest ED site. When site-specific models were trained and tested across all the sites, the AUCs ranged more widely from 0.71 to 0.93. Within a single ED site, the performance of the 5 site-specific models was most variable for our largest and smallest EDs. Finally, when the importance of features was examined, several features were common to all site-specific models; however, the weight of these features differed. Conclusion: A machine learning model for predicting hospital admission from the ED will generalize fairly well within the health care system but will still have significant differences in AUC performance across sites because of site-specific factors.

Practical development and operationalization of a 12-hour hospital census prediction algorithm.

Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop simple yet useful models for 12-hour census prediction and design a dashboard application to display this output to our hospital's decision-makers. Specifically, we found that linear models with ElasticNet regularization performed well for this task with relative 95% error of +/- 3.4% and that this work could be completed in approximately 7 months.

Human metapneumovirus nucleoprotein and phosphoprotein interact and provide the minimal requirements for inclusion body formation.

Human metapneumovirus (HMPV) is a recently discovered paramyxovirus of the subfamily Pneumovirinae, which also includes avian pneumovirus and human respiratory syncytial virus (HRSV). HMPV is an important cause of respiratory disease worldwide. To understand early events in HMPV replication, cDNAs encoding the HMPV nucleoprotein (N), phosphoprotein (P), matrix protein (M), M2-1 protein and M2-2 protein were cloned from cells infected with the genotype A1 HMPV wild-type strain TN/96-12. HMPV N and P were shown to interact using a variety of techniques: yeast two-hybrid assays, co-immunoprecipitation and fluorescence resonance energy transfer (FRET). Confocal microscopy studies showed that, when expressed individually, fluorescently tagged HMPV N and P exhibited a diffuse expression pattern in the host-cell cytoplasm of uninfected cells but were recruited to cytoplasmic viral inclusion bodies in HMPV-infected cells. Furthermore, when HMPV N and P were expressed together, they also formed cytoplasmic inclusion-like complexes, even in the absence of viral infection. FRET microscopy revealed that HMPV N and P interacted directly within cytoplasmic inclusion-like complexes. Moreover, it was shown by yeast two-hybrid analysis that the N-terminal 28 aa are required for the recruitment to and formation of cytoplasmic inclusions, but are dispensable for binding to HMPV P. This work showed that HMPV N and P proteins provide the minimal viral requirements for HMPV inclusion body formation, which may be a distinguishing characteristic of members of the subfamily Pneumovirinae.