Explore the vast range of titles available.

A common problem in machine learning and pattern recognition is the process of identifying the most relevant features, specifically in dealing with high-dimensional datasets in bioinformatics. In this paper, we propose a new feature selection method, called Singular-Vectors Feature Selection (SVFS). Let D = [ A ∣ b ] be a labeled dataset, where b is the class label and features (attributes) are columns of matrix A . We show that the signature matrix S A = I - A † A can be used to partition the columns of A into clusters so that columns in a cluster correlate only with the columns in the same cluster. In the first step, SVFS uses the signature matrix S D of D to find the cluster that contains b . We reduce the size of A by discarding features in the other clusters as irrelevant features. In the next step, SVFS uses the signature matrix S A of reduced A to partition the remaining features into clusters and choose the most important features from each cluster. Even though SVFS works perfectly on synthetic datasets, comprehensive experiments on real world benchmark and genomic datasets shows that SVFS exhibits overall superior performance compared to the state-of-the-art feature selection methods in terms of accuracy, running time, and memory usage. A Python implementation of SVFS along with the datasets used in this paper are available at https://github.com/Majid1292/SVFS .

The purpose of this guideline is to optimize evaluation and management of patients with obesity hypoventilation syndrome (OHS). A multidisciplinary panel identified and prioritized five clinical questions. The panel performed systematic reviews of available studies (up to July 2018) and followed the Grading of Recommendations, Assessment, Development, and Evaluation evidence-to-decision framework to develop recommendations. All panel members discussed and approved the recommendations. After considering the overall very low quality of the evidence, the panel made five conditional recommendations. We suggest that: ) clinicians use a serum bicarbonate level <27 mmol/L to exclude the diagnosis of OHS in obese patients with sleep-disordered breathing when suspicion for OHS is not very high (<20%) but to measure arterial blood gases in patients strongly suspected of having OHS, ) stable ambulatory patients with OHS receive positive airway pressure (PAP), ) continuous positive airway pressure (CPAP) rather than noninvasive ventilation be offered as the first-line treatment to stable ambulatory patients with OHS and coexistent severe obstructive sleep apnea, ) patients hospitalized with respiratory failure and suspected of having OHS be discharged with noninvasive ventilation until they undergo outpatient diagnostic procedures and PAP titration in the sleep laboratory (ideally within 2-3 mo), and ) patients with OHS use weight-loss interventions that produce sustained weight loss of 25% to 30% of body weight to achieve resolution of OHS (which is more likely to be obtained with bariatric surgery). Clinicians may use these recommendations, on the basis of the best available evidence, to guide management and improve outcomes among patients with OHS.

Although wetlands provide valuable services to humans and the environment and cover a large portion of Canada, there is currently no Canada-wide wetland inventory based on the specifications defined by the Canadian Wetland Classification System (CWCS). The most practical approach for creating the Canadian Wetland Inventory (CWI) is to develop a remote sensing method feasible for large areas with the potential to be updated within certain time intervals to monitor dynamic wetland landscapes. Thus, this study aimed to create the first Canada-wide wetland inventory using Landsat-8 imagery and innovative image processing techniques available within Google Earth Engine (GEE). For this purpose, a large amount of field samples and approximately 30,000 Landsat-8 surface reflectance images were initially processed using several advanced algorithms within GEE. Then, the random forest (RF) algorithm was applied to classify the entire country. The final step was an original CWI map considering the five wetland classes defined by the CWCS (i.e., bog, fen, marsh, swamp, and shallow water) and providing updated and comprehensive information regarding the location and spatial extent of wetlands in Canada. The map had reasonable accuracy in terms of both visual and statistical analyses considering the large area of country that was classified (9.985 million km2). The overall classification accuracy and the average producer and user accuracies for wetland classes exclusively were 71%, 66%, and 63%, respectively. Additionally, based on the final classification map, it was estimated that 36% of Canada is covered by wetlands.

Approaches are needed to better delineate the continuum of opioid misuse that occurs in hospitalized patients. A prognostic enrichment strategy with latent class analysis (LCA) may facilitate treatment strategies in subtypes of opioid misuse. We aim to identify subtypes of patients with opioid misuse and examine the distinctions between the subtypes by examining patient characteristics, topic models from clinical notes, and clinical outcomes. This was an observational study of inpatient hospitalizations at a tertiary care center between 2007 and 2017. Patients with opioid misuse were identified using an operational definition applied to all inpatient encounters. LCA with eight class-defining variables from the electronic health record (EHR) was applied to identify subtypes in the cohort of patients with opioid misuse. Comparisons between subtypes were made using the following approaches: (1) descriptive statistics on patient characteristics and healthcare utilization using EHR data and census-level data; (2) topic models with natural language processing (NLP) from clinical notes; (3) association with hospital outcomes. The analysis cohort was 6,224 (2.7% of all hospitalizations) patient encounters with opioid misuse with a data corpus of 422,147 clinical notes. LCA identified four subtypes with differing patient characteristics, topics from the clinical notes, and hospital outcomes. Class 1 was categorized by high hospital utilization with known opioid-related conditions (36.5%); Class 2 included patients with illicit use, low socioeconomic status, and psychoses (12.8%); Class 3 contained patients with alcohol use disorders with complications (39.2%); and class 4 consisted of those with low hospital utilization and incidental opioid misuse (11.5%). The following hospital outcomes were the highest for each subtype when compared against the other subtypes: readmission for class 1 (13.9% vs. 10.5%, p<0.01); discharge against medical advice for class 2 (12.3% vs. 5.3%, p<0.01); and in-hospital death for classes 3 and 4 (3.2% vs. 1.9%, p<0.01). A 4-class latent model was the most parsimonious model that defined clinically interpretable and relevant subtypes for opioid misuse. Distinct subtypes were delineated after examining multiple domains of EHR data and applying methods in artificial intelligence. The approach with LCA and readily available class-defining substance use variables from the EHR may be applied as a prognostic enrichment strategy for targeted interventions.

Addiction medicine consultation services (ACS) may improve outcomes of hospitalized patients with substance use disorders (SUD). Our aim was to examine the difference in length of stay and the hazard ratio for a routine hospital discharge between SUD patients receiving and not receiving ACS. Structured EHR data from 2018 of 1,900 adult patients with a SUD-related diagnostic code at an urban academic health center were examined among 35,541 total encounters. Cox proportional hazards regression models were fit using a cause-specific approach to examine differences in hospital outcome (i.e., routine discharge, leaving against medical advice, in-hospital death, or transfer to another level of care). Models were adjusted for age, sex, race, ethnicity, insurance status, and comorbidities. Length of stay was shorter among encounters with a SUD that received a SUIT consultation versus those admissions that did not receive one (5.77 v. 6.54 days, p<0.01). In adjusted analyses, admissions that received a SUIT consultation had a higher hazard of a routine discharge [hazard ratio (95% confidence interval): 1.16 (1.03-1.30)] compared to those not receiving a SUIT consultation. The SUIT consultation service was associated with a reduced length of stay and an increased hazard of a routine discharge. The SUIT model may serve as a benchmark and inform other health systems attempting to improve outcomes in SUD patient cohorts.

Background Automated de-identification methods for removing protected health information (PHI) from the source notes of the electronic health record (EHR) rely on building systems to recognize mentions of PHI in text, but they remain inadequate at ensuring perfect PHI removal. As an alternative to relying on de-identification systems, we propose the following solutions: (1) Mapping the corpus of documents to standardized medical vocabulary (concept unique identifier [CUI] codes mapped from the Unified Medical Language System) thus eliminating PHI as inputs to a machine learning model; and (2) training character-based machine learning models that obviate the need for a dictionary containing input words/n-grams. We aim to test the performance of models with and without PHI in a use-case for an opioid misuse classifier. Methods An observational cohort sampled from adult hospital inpatient encounters at a health system between 2007 and 2017. A case-control stratified sampling ( n  = 1000) was performed to build an annotated dataset for a reference standard of cases and non-cases of opioid misuse. Models for training and testing included CUI codes, character-based, and n-gram features. Models applied were machine learning with neural network and logistic regression as well as expert consensus with a rule-based model for opioid misuse. The area under the receiver operating characteristic curves (AUROC) were compared between models for discrimination. The Hosmer-Lemeshow test and visual plots measured model fit and calibration. Results Machine learning models with CUI codes performed similarly to n-gram models with PHI. The top performing models with AUROCs > 0.90 included CUI codes as inputs to a convolutional neural network, max pooling network, and logistic regression model. The top calibrated models with the best model fit were the CUI-based convolutional neural network and max pooling network. The top weighted CUI codes in logistic regression has the related terms ‘Heroin’ and ‘Victim of abuse’. Conclusions We demonstrate good test characteristics for an opioid misuse computable phenotype that is void of any PHI and performs similarly to models that use PHI. Herein we share a PHI-free, trained opioid misuse classifier for other researchers and health systems to use and benchmark to overcome privacy and security concerns.

A molecular test to distinguish between sepsis and systemic inflammation of noninfectious etiology could potentially have clinical utility. This study evaluated the diagnostic performance of a molecular host response assay (SeptiCyte LAB) designed to distinguish between sepsis and noninfectious systemic inflammation in critically ill adults. The study employed a prospective, observational, noninterventional design and recruited a heterogeneous cohort of adult critical care patients from seven sites in the United States (n = 249). An additional group of 198 patients, recruited in the large MARS (Molecular Diagnosis and Risk Stratification of Sepsis) consortium trial in the Netherlands ( www.clinicaltrials.gov identifier NCT01905033), was also tested and analyzed, making a grand total of 447 patients in our study. The performance of SeptiCyte LAB was compared with retrospective physician diagnosis by a panel of three experts. In receiver operating characteristic curve analysis, SeptiCyte LAB had an estimated area under the curve of 0.82-0.89 for discriminating sepsis from noninfectious systemic inflammation. The relative likelihood of sepsis versus noninfectious systemic inflammation was found to increase with increasing test score (range, 0-10). In a forward logistic regression analysis, the diagnostic performance of the assay was improved only marginally when used in combination with other clinical and laboratory variables, including procalcitonin. The performance of the assay was not significantly affected by demographic variables, including age, sex, or race/ethnicity. SeptiCyte LAB appears to be a promising diagnostic tool to complement physician assessment of infection likelihood in critically ill adult patients with systemic inflammation. Clinical trial registered with www.clinicaltrials.gov (NCT01905033 and NCT02127502).

Arsenic exposure has been linked to poor pulmonary function, and inefficient arsenic metabolizers may be at increased risk. Dietary rice has recently been identified as a possible substantial route of exposure to arsenic, and it remains unknown whether it can provide a sufficient level of exposure to affect pulmonary function in inefficient metabolizers. Within 12,609 participants of HCHS/SOL, asthma diagnoses and spirometry-based measures of pulmonary function were assessed, and rice consumption was inferred from grain intake via a food frequency questionnaire. After stratifying by smoking history, the relationship between arsenic metabolism efficiency [percentages of inorganic arsenic (%iAs), monomethylarsenate (%MMA), and dimethylarsinate (%DMA) species in urine] and the measures of pulmonary function were estimated in a two-sample Mendelian randomization approach (genotype information from an Illumina HumanOmni2.5-8v1-1 array), focusing on participants with high inferred rice consumption. Among never-smoking high inferred consumers of rice (n = 1395), inefficient metabolism was associated with past asthma diagnosis and forced vital capacity below the lower limit of normal (LLN) (OR 1.40, p = 0.0212 and OR 1.42, p = 0.0072, respectively, for each percentage-point increase in %iAs; OR 1.26, p = 0.0240 and OR 1.24, p = 0.0193 for %MMA; OR 0.87, p = 0.0209 and OR 0.87, p = 0.0123 for the marker of efficient metabolism, %DMA). Among ever-smoking high inferred consumers of rice (n = 1127), inefficient metabolism was associated with peak expiratory flow below LLN (OR 1.54, p = 0.0108/percentage-point increase in %iAs, OR 1.37, p = 0.0097 for %MMA, and OR 0.83, p = 0.0093 for %DMA). Less efficient arsenic metabolism was associated with indicators of pulmonary dysfunction among those with high inferred rice consumption, suggesting that reductions in dietary arsenic could improve respiratory health.

One of the key challenges in successful deployment and meaningful adoption of AI in healthcare is health system-level governance of AI applications. Such governance is critical not only for patient safety and accountability by a health system, but to foster clinician trust to improve adoption and facilitate meaningful health outcomes. In this case study, we describe the development of such a governance structure at University of Wisconsin Health (UWH) that provides oversight of AI applications from assessment of validity and user acceptability through safe deployment with continuous monitoring for effectiveness. Our structure leverages a multi-disciplinary steering committee along with project specific sub-committees. Members of the committee formulate a multi-stakeholder perspective spanning informatics, data science, clinical operations, ethics, and equity. Our structure includes guiding principles that provide tangible parameters for endorsement of both initial deployment and ongoing usage of AI applications. The committee is tasked with ensuring principles of interpretability, accuracy, and fairness across all applications. To operationalize these principles, we provide a value stream to apply the principles of AI governance at different stages of clinical implementation. This structure has enabled effective clinical adoption of AI applications. Effective governance has provided several outcomes: (1) a clear and institutional structure for oversight and endorsement; (2) a path towards successful deployment that encompasses technologic, clinical, and operational, considerations; (3) a process for ongoing monitoring to ensure the solution remains acceptable as clinical practice and disease prevalence evolve; (4) incorporation of guidelines for the ethical and equitable use of AI applications.

Implementing machine learning models to identify clinical deterioration on the wards is associated with decreased morbidity and mortality. However, these models have high false positive rates and only use structured data. We aim to compare models with and without information from clinical notes for predicting deterioration. Adults admitted to the wards at the University of Chicago (development cohort) and University of Wisconsin-Madison (external validation cohort) were included. Predictors consisted of structured and unstructured variables extracted from notes as Concept Unique Identifiers (CUIs). We parameterized CUIs in five ways: Standard Tokenization (ST), ICD Rollup using Tokenization (ICDR-T), ICD Rollup using Binary Variables (ICDR-BV), CUIs as SapBERT Embeddings (SE), and CUI Clustering using SapBERT embeddings (CC). Each parameterization method combined with structured data and structured data-only were compared for predicting intensive care unit transfer or death in the next 24 hours using deep recurrent neural networks. The development (UC) cohort included 284,302 patients, while the external validation (UW) cohort included 248,055. In total, 4.9% (N=26,281) of patients experienced the outcome. The SE model achieved the highest AUPRC (0.208), followed by CC (0.199) and the structured-only model (0.199), ICDR-BV (0.194), ICDR-T (0.166), and ST (0.158). The CC and structured-only models achieved the highest AUROC (0.870), followed by ICDR-T (0.867), ICDR-BV (0.866), ST (0.860), and SE (0.859). In terms of sensitivity and positive predictive value, the CC model achieved the greatest positive predictive value (12.53%) and sensitivity (52.15%) at the cutoff that flagged 5% of the observations in the test set. At the 15% cutoff, the ICDR-T, CC, and ICDR-BV models tied for the highest positive predictive value at 5.67%, while their sensitivities were 70.95%, 70.92%, and 70.86%, respectively. All models were well calibrated, achieving Brier scores in the range of 0.011-0.012. The modified IG method revealed that CUIs corresponding to terms such as \"NPO - Nothing by mouth\", \"Chemotherapy\", \"Transplanted tissue\", and \"Dialysis procedure\" were most predictive of deterioration. A multimodal model combining structured data with embeddings using SapBERT had the highest AUPRC, but performance was similar between models with and without CUIs. Although the addition of CUIs from notes to structured data did not meaningfully improve model performance for predicting clinical deterioration, models using CUIs could provide clinicians with relevant information and additional clinical context for supporting decision-making.