Explore the vast range of titles available.

A comprehensive guide for both quantitative and qualitative research methods, this book on the discipline of human-computer interaction (HCI) is essential reading for researchers of all types.

Background There is an increasing interest in clinical prediction tools that can achieve high prediction accuracy and provide explanations of the factors leading to increased risk of adverse outcomes. However, approaches to explaining complex machine learning (ML) models are rarely informed by end-user needs and user evaluations of model interpretability are lacking in the healthcare domain. We used extended revisions of previously-published theoretical frameworks to propose a framework for the design of user-centered displays of explanations. This new framework served as the basis for qualitative inquiries and design review sessions with critical care nurses and physicians that informed the design of a user-centered explanation display for an ML-based prediction tool. Methods We used our framework to propose explanation displays for predictions from a p ediatric i ntensive c are u nit (PICU) in-hospital mortality risk model. Proposed displays were based on a model-agnostic, instance-level explanation approach based on feature influence, as determined by Shapley values. Focus group sessions solicited critical care provider feedback on the proposed displays, which were then revised accordingly. Results The proposed displays were perceived as useful tools in assessing model predictions. However, specific explanation goals and information needs varied by clinical role and level of predictive modeling knowledge. Providers preferred explanation displays that required less information processing effort and could support the information needs of a variety of users. Providing supporting information to assist in interpretation was seen as critical for fostering provider understanding and acceptance of the predictions and explanations. The user-centered explanation display for the PICU in-hospital mortality risk model incorporated elements from the initial displays along with enhancements suggested by providers. Conclusions We proposed a framework for the design of user-centered displays of explanations for ML models. We used the proposed framework to motivate the design of a user-centered display of an explanation for predictions from a PICU in-hospital mortality risk model. Positive feedback from focus group participants provides preliminary support for the use of model-agnostic, instance-level explanations of feature influence as an approach to understand ML model predictions in healthcare and advances the discussion on how to effectively communicate ML model information to healthcare providers.

Cancer is mainly caused by somatic genome alterations (SGAs). Precision oncology involves identifying and targeting tumor-specific aberrations resulting from causative SGAs. We developed a novel tumor-specific computational framework that finds the likely causative SGAs in an individual tumor and estimates their impact on oncogenic processes, which suggests the disease mechanisms that are acting in that tumor. This information can be used to guide precision oncology. We report a tumor-specific causal inference (TCI) framework, which estimates causative SGAs by modeling causal relationships between SGAs and molecular phenotypes (e.g., transcriptomic, proteomic, or metabolomic changes) within an individual tumor. We applied the TCI algorithm to tumors from The Cancer Genome Atlas (TCGA) and estimated for each tumor the SGAs that causally regulate the differentially expressed genes (DEGs) in that tumor. Overall, TCI identified 634 SGAs that are predicted to cause cancer-related DEGs in a significant number of tumors, including most of the previously known drivers and many novel candidate cancer drivers. The inferred causal relationships are statistically robust and biologically sensible, and multiple lines of experimental evidence support the predicted functional impact of both the well-known and the novel candidate drivers that are predicted by TCI. TCI provides a unified framework that integrates multiple types of SGAs and molecular phenotypes to estimate which genome perturbations are causally influencing one or more molecular/cellular phenotypes in an individual tumor. By identifying major candidate drivers and revealing their functional impact in an individual tumor, TCI sheds light on the disease mechanisms of that tumor, which can serve to advance our basic knowledge of cancer biology and to support precision oncology that provides tailored treatment of individual tumors.

Computational models of infectious diseases have become valuable tools for research and the public health response against epidemic threats. The reproducibility of computational models has been limited, undermining the scientific process and possibly trust in modeling results and related response strategies, such as vaccination. We translated published reproducibility guidelines from a wide range of scientific disciplines into an implementation framework for improving reproducibility of infectious disease computational models. The framework comprises 22 elements that should be described, grouped into 6 categories: computational environment, analytical software, model description, model implementation, data, and experimental protocol. The framework can be used by scientific communities to develop actionable tools for sharing computational models in a reproducible way.

Sarcoidosis is a systemic disease characterized by noncaseating granulomatous inflammation with tremendous clinical heterogeneity and uncertain pathobiology and lacking in clinically useful biomarkers. The Genomic Research in Alpha-1 Antitrypsin Deficiency and Sarcoidosis (GRADS) study is an observational cohort study designed to explore the role of the lung microbiome and genome in these two diseases. This article describes the design and rationale for the GRADS study sarcoidosis protocol. The study addresses the hypothesis that distinct patterns in the lung microbiome are characteristic of sarcoidosis phenotypes and are reflected in changes in systemic inflammatory responses as measured by peripheral blood changes in gene transcription. The goal is to enroll 400 participants, with a minimum of 35 in each of 9 clinical phenotype subgroups prioritized by their clinical relevance to understanding of the pathobiology and clinical heterogeneity of sarcoidosis. Participants with a confirmed diagnosis of sarcoidosis undergo a baseline visit with self-administered questionnaires, chest computed tomography, pulmonary function tests, and blood and urine testing. A research or clinical bronchoscopy with a research bronchoalveolar lavage will be performed to obtain samples for genomic and microbiome analyses. Comparisons will be made by blood genomic analysis and with clinical phenotypic variables. A 6-month follow-up visit is planned to assess each participant's clinical course. By the use of an integrative approach to the analysis of the microbiome and genome in selected clinical phenotypes, the GRADS study is powerfully positioned to inform and direct studies on the pathobiology of sarcoidosis, identify diagnostic or prognostic biomarkers, and provide novel molecular phenotypes that could lead to improved personalized approaches to therapy for sarcoidosis.

Couture et al. used these data to generate a Bayesian hierarchical model expressing state-level hospitalizations in terms of unobserved \"true\" hospitalization rates, which were in turn determined by covariates.\" The resulting models stratified estimated hospitalization counts by age group, month, and state. ENCOURAGING OPEN SCIENCE PRACTICES To fully realize the utility of these and similar infectious disease modeling efforts, epidemiologists responsible for initial data collection and dissemination and modelers who use those data must work together to adopt modern data science techniques. Proposed reporting checklists aimed at supporting increased reproducibility of infectious disease modeling efforts specify extensive information, including the types of data used, how those data were processed, evaluation methods, the source code used to build the model, and other relevant details.'

Background Infectious disease computational modeling studies have been widely published during the coronavirus disease 2019 (COVID-19) pandemic, yet they have limited reproducibility. Developed through an iterative testing process with multiple reviewers, the Infectious Disease Modeling Reproducibility Checklist (IDMRC) enumerates the minimal elements necessary to support reproducible infectious disease computational modeling publications. The primary objective of this study was to assess the reliability of the IDMRC and to identify which reproducibility elements were unreported in a sample of COVID-19 computational modeling publications. Methods Four reviewers used the IDMRC to assess 46 preprint and peer reviewed COVID-19 modeling studies published between March 13th, 2020, and July 30th, 2020. The inter-rater reliability was evaluated by mean percent agreement and Fleiss’ kappa coefficients (κ). Papers were ranked based on the average number of reported reproducibility elements, and average proportion of papers that reported each checklist item were tabulated. Results Questions related to the computational environment (mean κ = 0.90, range = 0.90–0.90), analytical software (mean κ = 0.74, range = 0.68–0.82), model description (mean κ = 0.71, range = 0.58–0.84), model implementation (mean κ = 0.68, range = 0.39–0.86), and experimental protocol (mean κ = 0.63, range = 0.58–0.69) had moderate or greater (κ > 0.41) inter-rater reliability. Questions related to data had the lowest values (mean κ = 0.37, range = 0.23–0.59). Reviewers ranked similar papers in the upper and lower quartiles based on the proportion of reproducibility elements each paper reported. While over 70% of the publications provided data used in their models, less than 30% provided the model implementation. Conclusions: The IDMRC is the first comprehensive, quality-assessed tool for guiding researchers in reporting reproducible infectious disease computational modeling studies. The inter-rater reliability assessment found that most scores were characterized by moderate or greater agreement. These results suggest that the IDMRC might be used to provide reliable assessments of the potential for reproducibility of published infectious disease modeling publications. Results of this evaluation identified opportunities for improvement to the model implementation and data questions that can further improve the reliability of the checklist.

The principles of genetics apply across the entire tree of life. At the cellular level we share biological mechanisms with species from which we diverged millions, even billions of years ago. We can exploit this common ancestry to learn about health and disease, by analyzing DNA and protein sequences, but also through the observable outcomes of genetic differences, i.e. phenotypes. To solve challenging disease problems we need to unify the heterogeneous data that relates genomics to disease traits. Without a big-picture view of phenotypic data, many questions in genetics are difficult or impossible to answer. The Monarch Initiative (https://monarchinitiative.org) provides tools for genotype-phenotype analysis, genomic diagnostics, and precision medicine across broad areas of disease.

Electronic medical record (EMR) systems capture large amounts of data per patient and present that data to physicians with little prioritization. Without prioritization, physicians must mentally identify and collate relevant data, an activity that can lead to cognitive overload. To mitigate cognitive overload, a Learning EMR (LEMR) system prioritizes the display of relevant medical record data. Relevant data are those that are pertinent to a context-defined as the combination of the user, clinical task, and patient case. To determine which data are relevant in a specific context, a LEMR system uses supervised machine learning models of physician information-seeking behavior. Since obtaining information-seeking behavior data via manual annotation is slow and expensive, automatic methods for capturing such data are needed. The goal of the research was to propose and evaluate eye tracking as a high-throughput method to automatically acquire physician information-seeking behavior useful for training models for a LEMR system. Critical care medicine physicians reviewed intensive care unit patient cases in an EMR interface developed for the study. Participants manually identified patient data that were relevant in the context of a clinical task: preparing a patient summary to present at morning rounds. We used eye tracking to capture each physician's gaze dwell time on each data item (eg, blood glucose measurements). Manual annotations and gaze dwell times were used to define target variables for developing supervised machine learning models of physician information-seeking behavior. We compared the performance of manual selection and gaze-derived models on an independent set of patient cases. A total of 68 pairs of manual selection and gaze-derived machine learning models were developed from training data and evaluated on an independent evaluation data set. A paired Wilcoxon signed-rank test showed similar performance of manual selection and gaze-derived models on area under the receiver operating characteristic curve (P=.40). We used eye tracking to automatically capture physician information-seeking behavior and used it to train models for a LEMR system. The models that were trained using eye tracking performed like models that were trained using manual annotations. These results support further development of eye tracking as a high-throughput method for training clinical decision support systems that prioritize the display of relevant medical record data.

Objective To understand home-care nurses’ perceptions of the post-hospitalisation information needs and communication problems of older patients, and how these factors might contribute to undesirable outcomes including poor patient reintegration into prior living environments and unplanned hospital readmissions. Design A ranked list of information needs experienced by patients was developed by two Nominal Group Technique (NGT) sessions from the perspective of home-care nurses. The list was combined with results from previously published work to develop a web-based survey administered to home-care nurses to elicit perceptions of patients’ post-hospitalisation information needs. Results Seventeen nurses participated in the NGT sessions, producing a list of 28 challenges grouped into five themes: medications, disease/condition, non-medication care/treatment/safety, functional limitations and communication problems. The survey was sent to 220 home-care nurses, with a 54.1% (119/220) response rate. Respondents identified several frequent, high-impact information and communication needs that have received little attention in readmission literature, including information about medication regimens; the severity of their condition; the hospital discharge management process; non-medication care regimens such as wound care, use of durable medical equipment and home safety; the extent of care needed; and which providers are best suited to provide that care. Responses also identified several communication difficulties that may play a role in readmissions. Conclusions Information needs and communication problems identified by home-care nurses expanded upon and reinforced results from prior studies. These results might be used to develop interventions that may improve information sharing among clinicians, patients and caregivers during care transitions to ensure patient reintegration into prior living environments, potentially preventing unplanned hospital readmissions.