Raising awareness of potential biases in medical machine learning: Experience from a Datathon.

Objective: To challenge clinicians and informaticians to learn about potential sources of bias in medical machine learning models through investigation of data and predictions from an open-source severity of illness score.

Methods: Over a two-day period (total elapsed time approximately 28 hours), we conducted a datathon that challenged interdisciplinary teams to investigate potential sources of bias in the Global Open Source Severity of Illness Score. Teams were invited to develop hypotheses, to use tools of their choosing to identify potential sources of bias, and to provide a final report.

Raising awareness of potential biases in medical machine learning: Experience from a Datathon.

Objective: To challenge clinicians and informaticians to learn about potential sources of bias in medical machine learning models through investigation of data and predictions from an open-source severity of illness score.

Methods: Over a two-day period (total elapsed time approximately 28 hours), we conducted a datathon that challenged interdisciplinary teams to investigate potential sources of bias in the Global Open Source Severity of Illness Score. Teams were invited to develop hypotheses, to use tools of their choosing to identify potential sources of bias, and to provide a final report.

Creation and Expansion of a Mixed Patient Intermediate Care Unit to Improve ICU Capacity.

Objectives: ICU capacity strain is associated with worsened outcomes. Intermediate care units (IMCs) comprise one potential option to offload ICUs while providing appropriate care for intermediate acuity patients, but their impact on ICU capacity has not been thoroughly characterized. The aims of this study are to describe the creation of a medical-surgical IMC and assess how the IMC affected ICU capacity.

The Global Open Source Severity of Illness Score (GOSSIS).

Objectives: To develop and demonstrate the feasibility of a Global Open Source Severity of Illness Score (GOSSIS)-1 for critical care patients, which generalizes across healthcare systems and countries.

Design: A merger of several critical care multicenter cohorts derived from registry and electronic health record data. Data were split into training (70%) and test (30%) sets, using each set exclusively for development and evaluation, respectively.

Data-driven curation process for describing the blood glucose management in the intensive care unit.

Analysis of real-world glucose and insulin clinical data recorded in electronic medical records can provide insights into tailored approaches to clinical care, yet presents many analytic challenges. This work makes publicly available a dataset that contains the curated entries of blood glucose readings and administered insulin on a per-patient basis during ICU admissions in the Medical Information Mart for Intensive Care (MIMIC-III) database version 1.4.

How is the Doctor Feeling? ICU Provider Sentiment is Associated with Diagnostic Imaging Utilization.

The judgment of intensive care unit (ICU) providers is difficult to measure using conventional structured electronic medical record (EMR) data. However, provider sentiment may be a proxy for such judgment. Utilizing 10 years of EMR data, this study evaluates the association between provider sentiment and diagnostic imaging utilization.

Impact of Intensive Care Unit Discharge Delays on Patient Outcomes: A Retrospective Cohort Study.

Objective: Patients often overstay in intensive care units (ICU) after they are deemed discharge ready. The objective of this study was to examine the impact of such discharge delays (DD) on subsequent in-hospital morbidity and mortality.

Design: Retrospective cohort study.

The eICU Collaborative Research Database, a freely available multi-center database for critical care research.

Critical care patients are monitored closely through the course of their illness. As a result of this monitoring, large amounts of data are routinely collected for these patients. Philips Healthcare has developed a telehealth system, the eICU Program, which leverages these data to support management of critically ill patients.

Vasopressin Administration Is Associated With Rising Serum Lactate Levels in Patients With Sepsis.

Background: Vasopressin is used in conjunction with norepinephrine during treatment of patients with septic shock. Serum lactate is often used in monitoring of patients with sepsis; however, its importance as a therapeutic target is unclear. The objective of this study is to examine the relationship of vasopressin use on serum lactate levels in patients with sepsis.

: An open source Python package for producing summary statistics for research papers.

Objectives: In quantitative research, understanding basic parameters of the study population is key for interpretation of the results. As a result, it is typical for the first table ("Table 1") of a research paper to include summary statistics for the study data. Our objectives are 2-fold.

A Comparative Analysis of Sepsis Identification Methods in an Electronic Database.

Objectives: To evaluate the relative validity of criteria for the identification of sepsis in an ICU database.

Design: Retrospective cohort study of adult ICU admissions from 2008 to 2012.

Setting: Tertiary teaching hospital in Boston, MA.

Severity of Illness Scores May Misclassify Critically Ill Obese Patients.

Objective: Severity of illness scores rest on the assumption that patients have normal physiologic values at baseline and that patients with similar severity of illness scores have the same degree of deviation from their usual state. Prior studies have reported differences in baseline physiology, including laboratory markers, between obese and normal weight individuals, but these differences have not been analyzed in the ICU. We compared deviation from baseline of pertinent ICU laboratory test results between obese and normal weight patients, adjusted for the severity of illness.

Bridging the Health Data Divide.

Fundamental quality, safety, and cost problems have not been resolved by the increasing digitization of health care. This digitization has progressed alongside the presence of a persistent divide between clinicians, the domain experts, and the technical experts, such as data scientists. The disconnect between clinicians and data scientists translates into a waste of research and health care resources, slow uptake of innovations, and poorer outcomes than are desirable and achievable.

Power and Effective Study Size in Heritability Studies.

Correlation between study units in quantitative genetics studies often makes it difficult to compare important inferential aspects of studies. Describing the relatedness between study units is critical to capture features of pedigree studies involving heritability, including power and precision of heritability estimates. Blangero et al (2012) showed that in pedigree studies the power to detect heritability is a function of the true heritability and the eigenvalues of the kinship matrix.

Multivariate longitudinal data analysis with mixed effects hidden Markov models.

Multiple longitudinal responses are often collected as a means to capture relevant features of the true outcome of interest, which is often hidden and not directly measurable. We outline an approach which models these multivariate longitudinal responses as generated from a hidden disease process. We propose a class of models which uses a hidden Markov model with separate but correlated random effects between multiple longitudinal responses.

Continued low uptake of treatment for hepatitis C virus infection in a large community-based cohort of inner city residents.

Background & Aims: Despite advances in HCV treatment, recent data on treatment uptake is sparse. HCV treatment uptake and associated factors were evaluated in a community-based cohort in Vancouver, Canada.

Methods: The CHASE study is a cohort of inner city residents recruited from January 2003-June 2004.

Mortality in a large community-based cohort of inner-city residents in Vancouver, Canada.

Background: The Downtown Eastside is a robust and densely populated neighbourhood in Vancouver, Canada, that is characterized by low-income housing and drug use and a high prevalence of HIV infection. We evaluated mortality and excess mortality among the broader community of individuals living in this neighbourhood.

Methods: The Community Health and Safety Evaluation is a community-based study of inner-city residents in the Downtown Eastside who were recruited in 2003 and 2004.

Reinfection with hepatitis C virus following sustained virological response in injection drug users.

Background And Aim: Despite that 60-90% of injection drug users (IDUs) are infected with hepatitis C virus (HCV) infection, IDUs are often denied therapy based on concerns of reinfection following treatment. However, there are little data in this regard. We evaluated HCV re-infection following sustained virologic response (SVR) among HCV-infected IDUs having received HCV treatment in a multidisciplinary program.

Optimizing assessment and treatment for hepatitis C virus infection in illicit drug users: a novel model incorporating multidisciplinary care and peer support.

Objectives: We evaluated assessment and treatment for hepatitis C virus (HCV) among illicit drug users accepting referral to a weekly HCV peer-support group at a multidisciplinary community health centre.

Methods: From March 2005 to 2008, HCV-infected individuals were referred to a weekly peer-support group and assessed for HCV infection. A retrospective chart review of outcomes 3 years after the initiation of the group was conducted (including HCV assessment and treatment).

Primary drug resistance in antiretroviral-naïve injection drug users.

Objectives: We evaluated the prevalence of primary HIV drug resistance in a population of 128 injection drug users (48 female) prior to initiating antiretroviral therapy.

Methods: Genotypic and phenotypic profiles were obtained retrospectively for the period June 1996 to February 2007. Genotypic drug resistance was defined as the presence of a major mutation (IAS-USA table, 2007 revision), adding revertants at reverse transcriptase (RT) codon 215.