Search

BackgroundDespite steady gains in life expectancy, individuals with cystic fibrosis (CF) lung disease still experience rapid pulmonary decline throughout their clinical course, which can ultimately end in respiratory failure. Point-of-care tools for accurate and timely information regarding the risk of rapid decline is essential for clinical decision support. ObjectiveThis study aims to translate a novel algorithm for earlier, more accurate prediction of rapid lung function decline in patients with CF into an interactive web-based application that can be integrated within electronic health record systems, via collaborative development with clinicians. MethodsLongitudinal clinical history, lung function measurements, and time-invariant characteristics were obtained for 30,879 patients with CF who were followed in the US Cystic Fibrosis Foundation Patient Registry (2003-2015). We iteratively developed the application using the R Shiny framework and by conducting a qualitative study with care provider focus groups (N=17). ResultsA clinical conceptual model and 4 themes were identified through coded feedback from application users: (1) ambiguity in rapid decline, (2) clinical utility, (3) clinical significance, and (4) specific suggested revisions. These themes were used to revise our application to the currently released version, available online for exploration. This study has advanced the application’s potential prognostic utility for monitoring individuals with CF lung disease. Further application development will incorporate additional clinical characteristics requested by the users and also a more modular layout that can be useful for care provider and family interactions. ConclusionsOur framework for creating an interactive and visual analytics platform enables generalized development of applications to synthesize, model, and translate electronic health data, thereby enhancing clinical decision support and improving care and health outcomes for chronic diseases and disorders. A prospective implementation study is necessary to evaluate this tool’s effectiveness regarding increased communication, enhanced shared decision-making, and improved clinical outcomes for patients with CF.

We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of [Formula: see text] 4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics.

This article is a transcript of a conversation that took place with Edwin Shneidman, PhD, on August 19, 2008. Recent advances in machine learning, particularly neurocognitive computing, have provided a fresh approach to the idea of using computers to analyze the language of the suicidal person. Here this notion and many others are discussed.

This article is a transcript of a conversation that took place with Edwin Shneidman, PhD, on August 19, 2008. Recent advances in machine learning, particularly neurocognitive computing, have provided a fresh approach to the idea of using computers to analyze the language of the suicidal person. Here this notion and many others are discussed.

ABSTRACT Approximately 57 different types of clinical annotations construct a patient's medical record. These annotations include radiology reports, discharge summaries, and surgical and nursing notes. Hospitals typically produce millions of […]

Objective. Several studies have demonstrated that acute otitis media (AOM) in children can be managed without antibiotics. Because children with AOM have traditionally been treated with antibiotics in the United States, there are concerns that parents may not be comfortable with their children being treated with pain control alone. Recently, Cates in England showed that antibiotic usage for AOM could be decreased by prescribing a safety-net antibiotic prescription (SNAP) to be filled if symptoms do not resolve with observation after 48 hours. It is not clear whether a SNAP will be acceptable to parents in other settings such as the United States. The objective of our study was to determine whether parents in the United States find a SNAP for AOM acceptable and whether antibiotic usage could be decreased by its use. Methods. A pediatric practice-based research network in a midwestern community of 1.8 million was the setting for this study. The Cincinnati Pediatric Research Group (CPRG) includes practices in Ohio, Kentucky, and Indiana. Children who were between 1 and 12 years of age and presented to the offices of the CPRG with uncomplicated AOM were eligible for the study. Children were excluded when they had temperature >101.5[degrees]F, had an ear infection in the past 3 months, showed signs of another bacterial infection, or were toxic appearing. Families were given acetaminophen, ibuprofen, or topical otic anesthetic drops for pain control. They were also given a prescription for an antibiotic and instructed not to fill it unless symptoms either increased or did not resolve after 48 hours. The data were entered directly by investigators via an Internet site. Results. A total of 194 children were enrolled in 11 offices over 12 months; 175 (90%) completed the follow-up interview. The average child's age was 5.0 years. Only 55 (31%) of the 175 who were contacted for follow-up had filled their antibiotic prescription. Compared with their previous experience, parents were overwhelmingly willing to treat AOM with pain medication alone ([chi square] = 111). Seventy-eight percent (95% confidence interval: 71%-84%) of parents reported that the pain medication was effective. Sixty-three percent (95% confidence interval: 55%-70%) of parents reported that they would be willing to treat future AOM episodes without antibiotics and with pain medication alone. Conclusions. A subset of parents find a safety-net prescription and pain control acceptable in the treatment of AOM, and antibiotic usage can be lowered with this strategy. Pediatrics 2003;112:527-531; acute otitis media, safety-net antibiotic prescription, practice-based research network, observation., Acute otitis media (AOM) is the most commonly treated bacterial infection in children. (1) Treatment of this infection accounts for >50% of pediatric antibiotic prescriptions and as much as $5 [...]

Children with a severe exacerbation of asthma may benefit from a dose of ipratropium. Researchers randomly assigned 434 children who were seen at a hospital emergency department to receive ipratropium or a placebo in addition to several doses of albuterol. Among children with moderate asthma, hospitalization rates were similar in both groups. Among children with severe asthma, only 37% of children receiving ipratropium were hospitalized, compared to 53% of those receiving a placebo.