Integrating genetic regulation and single-cell expression with GWAS prioritizes causal genes and cell types for glaucoma.

Primary open-angle glaucoma (POAG), characterized by retinal ganglion cell death, is a leading cause of irreversible blindness worldwide. However, its molecular and cellular causes are not well understood. Elevated intraocular pressure (IOP) is a major risk factor, but many patients have normal IOP. Colocalization and Mendelian randomization analysis of >240 POAG and IOP genome-wide association study (GWAS) loci and overlapping expression and splicing quantitative trait loci (e/sQTLs) in 49 GTEx tissues and retina prioritizes causal genes for 60% of loci. These genes are enriched in pathways implicated in extracellular matrix organization, cell adhesion, and vascular development. Analysis of single-nucleus RNA-seq of glaucoma-relevant eye tissues reveals that the POAG and IOP colocalizing genes and genome-wide associations are enriched in specific cell types in the aqueous outflow pathways, retina, optic nerve head, peripapillary sclera, and choroid. This study nominates IOP-dependent and independent regulatory mechanisms, genes, and cell types that may contribute to POAG pathogenesis.

Model-directed generation of CRISPR-Cas13a guide RNAs designs artificial sequences that improve nucleic acid detection.

Generating maximally-fit biological sequences has the potential to transform CRISPR guide RNA design as it has other areas of biomedicine. Here, we introduce model-directed exploration algorithms (MEAs) for designing maximally-fit, artificial CRISPR-Cas13a guides-with multiple mismatches to any natural sequence-that are tailored for desired properties around nucleic acid diagnostics. We find that MEA-designed guides offer more sensitive detection of diverse pathogens and discrimination of pathogen variants compared to guides derived directly from natural sequences, and illuminate interpretable design principles that broaden Cas13a targeting.

Optimized Risk Score to Predict Mortality in Patients With Cardiogenic Shock in the Cardiac Intensive Care Unit.

Background Mortality prediction in critically ill patients with cardiogenic shock can guide triage and selection of potentially high-risk treatment options. Methods and Results We developed and externally validated a checklist risk score to predict in-hospital mortality among adults admitted to the cardiac intensive care unit with Society for Cardiovascular Angiography & Interventions Shock Stage C or greater cardiogenic shock using 2 real-world data sets and Risk-Calibrated Super-sparse Linear Integer Modeling (RiskSLIM). We compared this model to those developed using conventional penalized logistic regression and published cardiogenic shock and intensive care unit mortality prediction models. There were 8815 patients in our training cohort (in-hospital mortality 13.4%) and 2237 patients in our validation cohort (in-hospital mortality 22.8%), and there were 39 candidate predictor variables. The final risk score (termed BOS,MA2) included maximum blood urea nitrogen ≥25 mg/dL, minimum oxygen saturation <88%, minimum systolic blood pressure <80 mm Hg, use of mechanical ventilation, age ≥60 years, and maximum anion gap ≥14 mmol/L, based on values recorded during the first 24 hours of intensive care unit stay. Predicted in-hospital mortality ranged from 0.5% for a score of 0 to 70.2% for a score of 6. The area under the receiver operating curve was 0.83 (0.82-0.84) in training and 0.76 (0.73-0.78) in validation, and the expected calibration error was 0.9% in training and 2.6% in validation. Conclusions Developed using a novel machine learning method and the largest cardiogenic shock cohorts among published models, BOS,MA2 is a simple, clinically interpretable risk score that has improved performance compared with existing cardiogenic-shock risk scores and better calibration than general intensive care unit risk scores.

Simplified Cas13-based assays for the fast identification of SARS-CoV-2 and its variants.

The widespread transmission and evolution of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) call for rapid nucleic acid diagnostics that are easy to use outside of centralized clinical laboratories. Here we report the development and performance benchmarking of Cas13-based nucleic acid assays leveraging lyophilised reagents and fast sample inactivation at ambient temperature. The assays, which we named SHINEv.2 (for 'streamlined highlighting of infections to navigate epidemics, version 2'), simplify the previously reported RNA-extraction-free SHINEv.1 technology by eliminating heating steps and the need for cold storage of the reagents. SHINEv.2 detected SARS-CoV-2 in nasopharyngeal samples with 90.5% sensitivity and 100% specificity (benchmarked against the reverse transcription quantitative polymerase chain reaction) in less than 90 min, using lateral-flow technology and incubation in a heat block at 37 °C. SHINEv.2 also allows for the visual discrimination of the Alpha, Beta, Gamma, Delta and Omicron SARS-CoV-2 variants, and can be run without performance losses by using body heat. Accurate, easy-to-use and equipment-free nucleic acid assays could facilitate wider testing for SARS-CoV-2 and other pathogens in point-of-care and at-home settings.

Designing sensitive viral diagnostics with machine learning.

Design of nucleic acid-based viral diagnostics typically follows heuristic rules and, to contend with viral variation, focuses on a genome's conserved regions. A design process could, instead, directly optimize diagnostic effectiveness using a learned model of sensitivity for targets and their variants. Toward that goal, we screen 19,209 diagnostic-target pairs, concentrated on CRISPR-based diagnostics, and train a deep neural network to accurately predict diagnostic readout. We join this model with combinatorial optimization to maximize sensitivity over the full spectrum of a virus's genomic variation. We introduce Activity-informed Design with All-inclusive Patrolling of Targets (ADAPT), a system for automated design, and use it to design diagnostics for 1,933 vertebrate-infecting viral species within 2 hours for most species and within 24 hours for all but three. We experimentally show that ADAPT's designs are sensitive and specific to the lineage level and permit lower limits of detection, across a virus's variation, than the outputs of standard design techniques. Our strategy could facilitate a proactive resource of assays for detecting pathogens.

Multiplexed CRISPR-based microfluidic platform for clinical testing of respiratory viruses and identification of SARS-CoV-2 variants.

The coronavirus disease 2019 (COVID-19) pandemic has demonstrated a clear need for high-throughput, multiplexed and sensitive assays for detecting severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and other respiratory viruses and their emerging variants. Here, we present a cost-effective virus and variant detection platform, called microfluidic Combinatorial Arrayed Reactions for Multiplexed Evaluation of Nucleic acids (mCARMEN), which combines CRISPR-based diagnostics and microfluidics with a streamlined workflow for clinical use. We developed the mCARMEN respiratory virus panel to test for up to 21 viruses, including SARS-CoV-2, other coronaviruses and both influenza strains, and demonstrated its diagnostic-grade performance on 525 patient specimens in an academic setting and 166 specimens in a clinical setting. We further developed an mCARMEN panel to enable the identification of 6 SARS-CoV-2 variant lineages, including Delta and Omicron, and evaluated it on 2,088 patient specimens with near-perfect concordance to sequencing-based variant classification. Lastly, we implemented a combined Cas13 and Cas12 approach that enables quantitative measurement of SARS-CoV-2 and influenza A viral copies in samples. The mCARMEN platform enables high-throughput surveillance of multiple viruses and variants simultaneously, enabling rapid detection of SARS-CoV-2 variants.

Predicting hypoglycemia in critically Ill patients using machine learning and electronic health records.

Hypoglycemia is a common occurrence in critically ill patients and is associated with significant mortality and morbidity. We developed a machine learning model to predict hypoglycemia by using a multicenter intensive care unit (ICU) electronic health record dataset. Machine learning algorithms were trained and tested on patient data from the publicly available eICU Collaborative Research Database. Forty-four features including patient demographics, laboratory test results, medications, and vitals sign recordings were considered. The outcome of interest was the occurrence of a hypoglycemic event (blood glucose < 72 mg/dL) during a patient's ICU stay. Machine learning models used data prior to the second hour of the ICU stay to predict hypoglycemic outcome. Data from 61,575 patients who underwent 82,479 admissions at 199 hospitals were considered in the study. The best-performing predictive model was the eXtreme gradient boosting model (XGBoost), which achieved an area under the received operating curve (AUROC) of 0.85, a sensitivity of 0.76, and a specificity of 0.76. The machine learning model developed has strong discrimination and calibration for the prediction of hypoglycemia in ICU patients. Prospective trials of these models are required to evaluate their clinical utility in averting hypoglycemia within critically ill patient populations.

A ketamine package for use in emergency cesarean delivery when no anesthetist is available: An analysis of 401 consecutive operations.

OBJECTIVE: To evaluate the safety and effectiveness of a ketamine-based anesthesia package to support emergency cesarean section when no anesthetist is available. METHODS: A prospective case-series was conducted between December 11, 2013 and September 30, 2021 across nine sub-county hospitals in Kenya. Non-anesthetist healthcare providers undertook an evidence-based five-day training course. A structured instrument was used to collect preoperative, intraoperative, and postoperative data, and patients were contacted 6 months following the surgery to collect outcomes. The primary outcome measures were maternal and newborn survival and the ability of the ketamine package (ESM-Ketamine) to safely support cesarean deliveries. RESULTS: A total of 401 emergency cesarean sections were performed using ketamine, administered by 54 non-anesthetist providers. All mothers survived to discharge. Brief oxygen desaturations were recorded among 33 (8.2%) mothers, and agitation and hallucinations occurred among 13 (3.2%). There were no maternal serious adverse events. At 6-month follow-up, 94.2% of mothers who could be reached reported no complaints. Additionally, 402 (92.4%) of the 435 operative births survived to discharge. CONCLUSION: The ESM-Ketamine package can be used by trained non-anesthetist providers to support emergency cesarean sections when no anesthetist is available. Ketamine has significant potential to increase access to emergency cesarean deliveries in resource-limited settings.

A systematic review of federated learning applications for biomedical data.

OBJECTIVES: Federated learning (FL) allows multiple institutions to collaboratively develop a machine learning algorithm without sharing their data. Organizations instead share model parameters only, allowing them to benefit from a model built with a larger dataset while maintaining the privacy of their own data. We conducted a systematic review to evaluate the current state of FL in healthcare and discuss the limitations and promise of this technology. METHODS: We conducted a literature search using PRISMA guidelines. At least two reviewers assessed each study for eligibility and extracted a predetermined set of data. The quality of each study was determined using the TRIPOD guideline and PROBAST tool. RESULTS: 13 studies were included in the full systematic review. Most were in the field of oncology (6 of 13; 46.1%), followed by radiology (5 of 13; 38.5%). The majority evaluated imaging results, performed a binary classification prediction task via offline learning (n = 12; 92.3%), and used a centralized topology, aggregation server workflow (n = 10; 76.9%). Most studies were compliant with the major reporting requirements of the TRIPOD guidelines. In all, 6 of 13 (46.2%) of studies were judged at high risk of bias using the PROBAST tool and only 5 studies used publicly available data. CONCLUSION: Federated learning is a growing field in machine learning with many promising uses in healthcare. Few studies have been published to date. Our evaluation found that investigators can do more to address the risk of bias and increase transparency by adding steps for data homogeneity or sharing required metadata and code.

Equipment-free detection of SARS-CoV-2 and Variants of Concern using Cas13.

The COVID-19 pandemic, and the recent rise and widespread transmission of SARS-CoV-2 Variants of Concern (VOCs), have demonstrated the need for ubiquitous nucleic acid testing outside of centralized clinical laboratories. Here, we develop SHINEv2, a Cas13-based nucleic acid diagnostic that combines quick and ambient temperature sample processing and lyophilized reagents to greatly simplify the test procedure and assay distribution. We benchmarked a SHINEv2 assay for SARS-CoV-2 detection against state-of-the-art antigen-capture tests using 96 patient samples, demonstrating 50-fold greater sensitivity and 100% specificity. We designed SHINEv2 assays for discriminating the Alpha, Beta, Gamma and Delta VOCs, which can be read out visually using lateral flow technology. We further demonstrate that our assays can be performed without any equipment in less than 90 minutes. SHINEv2 represents an important advance towards rapid nucleic acid tests that can be performed in any location.

Screening of Parkinson's Disease Using Geometric Features Extracted from Spiral Drawings.

Conventional means of Parkinson's Disease (PD) screening rely on qualitative tests typically administered by trained neurologists. Tablet technologies that enable data collection during handwriting and drawing tasks may provide low-cost, portable, and instantaneous quantitative methods for high-throughput PD screening. However, past efforts to use data from tablet-based drawing processes to distinguish between PD and control populations have demonstrated only moderate classification ability. Focusing on digitized drawings of Archimedean spirals, the present study utilized data from the open-access ParkinsonHW dataset to improve existing PD drawing diagnostic pipelines. Random forest classifiers were constructed using previously documented features and highly-predictive, newly-proposed features that leverage the many unique mathematical characteristics of the Archimedean spiral. This approach yielded an AUC of 0.999 on the particular dataset we tested on, and more importantly identified interpretable features with good promise for generalization across diverse patient cohorts. It demonstrated the potency of mathematical relationships inherent to the drawing shape and the usefulness of sparse feature sets and simple models, which further enhance interpretability, in the face of limited sample size. The results of this study also inform suggestions for future drawing task design and data analytics (feature extraction, shape selection, task diversity, drawing templates, and data sharing).

Low-Cost, Smartphone-Based Specular Imaging and Automated Analysis of the Corneal Endothelium.

Purpose: Specular and confocal microscopes are important tools to monitor the health of the corneal endothelium (CE), but their high costs significantly limit accessibility in low-resource environments. We developed and validated a low-cost, fully automated method to quantitatively evaluate the CE using smartphone-based specular microscopy. Methods: A OnePlus 7 Pro smartphone attached to a Topcon SL-D701 slit-lamp was used to image the central corneal endothelium of 30 eyes using the specular reflection technique. A novel on-device image processing algorithm automatically computed endothelial cell density (ECD), percentage of hexagonal cells (HEX), and coefficient of variation (CV) values. These values were compared with the ECD, HEX, and CV generated by a Tomey EM-4000 specular microscope used to image the same set of eyes. Results: No significant differences were found in ECD (2799 ± 156 cells/mm2 vs. 2779 ± 166 cells/mm2; P = 0.28) and HEX (52 ± 6% vs. 53 ± 6%; P = 0.50) computed by smartphone-based specular imaging and specular microscope, respectively. A statistically significant difference in CV (34 ± 3% vs. 30 ± 3%; P < 0.01) was found between the two methods. The concordance achieved between the smartphone-based method and the Tomey specular microscope is very similar to the concordance between two specular microscopes reported in the literature. Conclusions: Smartphone-based specular imaging and automated analysis is a low-cost method to quantitatively evaluate the CE with accuracy comparable to the clinical standard. Translational Relevance: This tool can be used to screen the CE in low-resource regions and prompt investigation of suspected corneal endotheliopathies.

Re-Examining the Race to Send Ventilators to Low-Resource Settings.

COVID-19 is devastating health systems globally and causing severe ventilator shortages. Since the beginning of the outbreak, the provision and use of ventilators has been a key focus of public discourse. Scientists and engineers from leading universities and companies have rushed to develop low-cost ventilators in hopes of supporting critically ill patients in developing countries. Philanthropists have invested millions in shipping ventilators to low-resource settings, and agencies such as the World Health Organization and the World Bank are prioritizing the purchase of ventilators. While we recognize the humanitarian nature of these efforts, merely shipping ventilators to low-resource environments may not improve outcomes of patients and could potentially cause harm. An ecosystem of considerable technological and human resources is required to support the usage of ventilators within intensive care settings. Medical-grade oxygen supplies, reliable electricity, bioengineering support, and consumables are all needed for ventilators to save lives. However, most ICUs in resource-poor settings do not have access to these resources. Patients on ventilators require continuous monitoring from physicians, nurses, and respiratory therapists skilled in critical care. Health care workers in many low-resource settings are already exceedingly overburdened, and pulling these essential human resources away from other critical patient needs could reduce the overall quality of patient care. When deploying medical devices, it is vital to align the technological intervention with the clinical reality. Low-income settings often will not benefit from resource-intensive equipment, but rather from contextually appropriate devices that meet the unique needs of their health systems.

Surfactant Administration in Preterm Infants: Drug Development Opportunities.

OBJECTIVE: To evaluate how frequently surfactant is used off-label in preterm infants. STUDY DESIGN: We conducted a retrospective cohort analysis of prospectively collected administrative data for 2005-2015 from 348 neonatal intensive care units in the US. We quantified off-label administration of poractant alfa, calfactant, or beractant in inborn infants born at <37 weeks of gestational age (GA). Off-label surfactant administration was defined according to the Food and Drug Administration (FDA) label. RESULTS: Of a total of 110 822 preterm infants who received surfactant, 68 226 (62%) received the surfactant off-label. The majority of infants who received surfactant off-label had a higher birth weight than those who received surfactant on-label (40 716 [37%]), had an older GA than those who received surfactant on-label (35 191 [32%]), or were treated with intubation and surfactant administration followed by immediate extubation (INSURE) (32 310 [29%]). Poractant alfa was administered via INSURE more frequently than beractant or calfactant (16 688 [38%], 7137 [20%], and 8485 [27%], respectively). An increasing number of infants received surfactant via INSURE from 2005 to 2015 (from 1697 [19%] to 3368 [36%]). CONCLUSIONS: The majority of surfactant given to preterm infants is administered off-label. The uptrend in administration via INSURE coincides with increased supporting evidence. The gap between FDA labeling and current clinic practice exemplifies an opportunity for label expansion, which may require additional prospective or retrospective safety and/or effectiveness data for infants of older GA and higher birth weight.