ABSTRACT
BACKGROUND: Information retrieval (IR) from the free text within electronic health records (EHRs) is time consuming and complex. We hypothesize that natural language processing (NLP)-enhanced search functionality for EHRs can make clinical workflows more efficient and reduce cognitive load for clinicians. OBJECTIVE: This study aimed to evaluate the efficacy of 3 levels of search functionality (no search, string search, and NLP-enhanced search) in supporting IR for clinical users from the free text of EHR documents in a simulated clinical environment. METHODS: A clinical environment was simulated by uploading 3 sets of patient notes into an EHR research software application and presenting these alongside 3 corresponding IR tasks. Tasks contained a mixture of multiple-choice and free-text questions. A prospective crossover study design was used, for which 3 groups of evaluators were recruited, which comprised doctors (n=19) and medical students (n=16). Evaluators performed the 3 tasks using each of the search functionalities in an order in accordance with their randomly assigned group. The speed and accuracy of task completion were measured and analyzed, and user perceptions of NLP-enhanced search were reviewed in a feedback survey. RESULTS: NLP-enhanced search facilitated more accurate task completion than both string search (5.14%; P=.02) and no search (5.13%; P=.08). NLP-enhanced search and string search facilitated similar task speeds, both showing an increase in speed compared to the no search function, by 11.5% (P=.008) and 16.0% (P=.007) respectively. Overall, 93% of evaluators agreed that NLP-enhanced search would make clinical workflows more efficient than string search, with qualitative feedback reporting that NLP-enhanced search reduced cognitive load. CONCLUSIONS: To the best of our knowledge, this study is the largest evaluation to date of different search functionalities for supporting target clinical users in realistic clinical workflows, with a 3-way prospective crossover study design. NLP-enhanced search improved both accuracy and speed of clinical EHR IR tasks compared to browsing clinical notes without search. NLP-enhanced search improved accuracy and reduced the number of searches required for clinical EHR IR tasks compared to direct search term matching.
ABSTRACT
Causal machine learning (CML) has experienced increasing popularity in healthcare. Beyond the inherent capabilities of adding domain knowledge into learning systems, CML provides a complete toolset for investigating how a system would react to an intervention (e.g. outcome given a treatment). Quantifying effects of interventions allows actionable decisions to be made while maintaining robustness in the presence of confounders. Here, we explore how causal inference can be incorporated into different aspects of clinical decision support systems by using recent advances in machine learning. Throughout this paper, we use Alzheimer's disease to create examples for illustrating how CML can be advantageous in clinical scenarios. Furthermore, we discuss important challenges present in healthcare applications such as processing high-dimensional and unstructured data, generalization to out-of-distribution samples and temporal relationships, that despite the great effort from the research community remain to be solved. Finally, we review lines of research within causal representation learning, causal discovery and causal reasoning which offer the potential towards addressing the aforementioned challenges.
ABSTRACT
OBJECTIVES: Therapeutic hypothermia has been of topical interest for many years and with the publication of two international, multicenter randomized controlled trials, the evidence base now needs updating. The aim of this systematic review of randomized controlled trials is to assess the efficacy of therapeutic hypothermia in adult traumatic brain injury focusing on mortality, poor outcomes, and new pneumonia. DATA SOURCES: The following databases were searched from January 1, 2011, to January 26, 2018: Cochrane Central Register of Controlled Trial, MEDLINE, PubMed, and EMBASE. STUDY SELECTION: Only foreign articles published in the English language were included. Only articles that were randomized controlled trials investigating adult traumatic brain injury sustained following an acute, closed head injury were included. Two authors independently assessed at each stage. DATA EXTRACTION: Quality was assessed using the Cochrane Collaboration's tool for assessing the risk of bias. All extracted data were combined using the Mantel-Haenszel estimator for pooled risk ratio with 95% CIs. p value of less than 0.05 was considered statistically significant. All statistical analyses were conducted using RevMan 5 (Cochrane Collaboration, Version 5.3, Copenhagen: The Nordic Cochrane Centre, The Cochrane Collaboration, 2014). DATA SYNTHESIS: Twenty-two studies with 2,346 patients are included. Randomized controlled trials with a low risk of bias show significantly more mortality in the therapeutic hypothermia group (risk ratio, 1.37; 95% CI, 1.04-1.79; p = 0.02), whereas randomized controlled trials with a high risk of bias show the opposite with a higher mortality in the control group (risk ratio, 0.70; 95% CI, 0.60-0.82; p < 0.00001). CONCLUSIONS: Overall, this review is in-keeping with the conclusions published by the most recent randomized controlled trials. High-quality studies show no significant difference in mortality, poor outcomes, or new pneumonia. In addition, this review shows a place for fever control in the management of traumatic brain injury.
