An official website of the United States government
Accurate prediction and monitoring of patient health in the intensive care unit can inform shared decisions regarding appropriateness of care delivery, risk-reduction strategies, and intensive care resource use. Traditionally, algorithmic solutions for patient outcome prediction rely solely on data available from electronic health records (EHR). In this pilot study, we explore the benefits of augmenting existing EHR data with novel measurements from wrist-worn activity sensors as part of a clinical environment known as the Intelligent ICU. We implemented temporal deep learning models based on two distinct sources of patient data: (1) routinely measured vital signs from electronic health records, and (2) activity data collected from wearable sensors. As a proxy for illness severity, our models predicted whether patients leaving the intensive care unit would be successfully or unsuccessfully discharged from the hospital. We overcome the challenge of small sample size in our prospective cohort by applying deep transfer learning using EHR data from a much larger cohort of traditional ICU patients. Our experiments quantify added utility of non-traditional measurements for predicting patient health, especially when applying a transfer learning procedure to small novel Intelligent ICU cohorts of critically ill patients.
more »
« less
Improving Risk Prediction of Methicillin-Resistant Staphylococcus aureus Using Machine Learning Methods With Network Features: Retrospective Development Study
Health care–associated infections due to multidrug-resistant organisms (MDROs), such as methicillin-resistant Staphylococcus aureus (MRSA) and Clostridioides difficile (CDI), place a significant burden on our health care infrastructure. Screening for MDROs is an important mechanism for preventing spread but is resource intensive. The objective of this study was to develop automated tools that can predict colonization or infection risk using electronic health record (EHR) data, provide useful information to aid infection control, and guide empiric antibiotic coverage. We retrospectively developed a machine learning model to detect MRSA colonization and infection in undifferentiated patients at the time of sample collection from hospitalized patients at the University of Virginia Hospital. We used clinical and nonclinical features derived from on-admission and throughout-stay information from the patient’s EHR data to build the model. In addition, we used a class of features derived from contact networks in EHR data; these network features can capture patients’ contacts with providers and other patients, improving model interpretability and accuracy for predicting the outcome of surveillance tests for MRSA. Finally, we explored heterogeneous models for different patient subpopulations, for example, those admitted to an intensive care unit or emergency department or those with specific testing histories, which perform better. We found that the penalized logistic regression performs better than other methods, and this model’s performance measured in terms of its receiver operating characteristics-area under the curve score improves by nearly 11% when we use polynomial (second-degree) transformation of the features. Some significant features in predicting MDRO risk include antibiotic use, surgery, use of devices, dialysis, patient’s comorbidity conditions, and network features. Among these, network features add the most value and improve the model’s performance by at least 15%. The penalized logistic regression model with the same transformation of features also performs better than other models for specific patient subpopulations. Our study shows that MRSA risk prediction can be conducted quite effectively by machine learning methods using clinical and nonclinical features derived from EHR data. Network features are the most predictive and provide significant improvement over prior methods. Furthermore, heterogeneous prediction models for different patient subpopulations enhance the model’s performance.
more »
« less
- Award ID(s):
- 1955797
- PAR ID:
- 10510616
- Publisher / Repository:
- JMIR
- Date Published:
- Journal Name:
- JMIR AI
- Volume:
- 3
- ISSN:
- 2817-1705
- Page Range / eLocation ID:
- e48067
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract The World Health Organization has declared antibiotic resistance “one of the biggest threats to global health.” Mounting evidence suggests that antibiotic use in industrial‐scale hog farming is contributing to the spread of antibiotic‐resistantStaphylococcus aureus. To capture available evidence on these risks, we searched peer‐reviewed studies published before June 2017 and conducted a meta‐analysis of these studies’ estimates of the prevalence of swine‐associated, antibiotic‐resistantS. aureusin animals, humans, and the environment. The 166 relevant studies revealed consistent evidence of livestock‐associated methicillin‐resistantS. aureus(MRSA) in hog herds (55.3%) raised with antibiotics. MRSA prevalence was also substantial in slaughterhouse pigs (30.4%), industrial hog operation workers (24.4%), and veterinarians (16.8%). The prevalence of swine‐associated, multidrug‐resistantS. aureus(MDRSA)—with resistance to three or more antibiotics—is not as well documented. Nonetheless, sufficient studies were available to estimate MDRSA pooled prevalence in conventional hog operation workers (15.0%), workers’ household members (13.0%), and community members (5.37%). Evidence also suggests that antibiotic‐resistantS. aureuscan be present in air, soil, water, and household surface samples gathered in or near high‐intensity hog operations. An important caveat is that prevalence estimates for humans reflect colonization, not active infection, and the health risks of colonization remain poorly understood. In addition, these pooled results may not represent risks in specific locations, due to wide geographic variation. Nonetheless, these results underscore the need for additional preventive action to stem the spread of antibiotic‐resistant pathogens from livestock operations and a streamlined reporting system to track this risk.more » « less
-
In this study, we introduce a novel representation of patient data called Disease Severity Hierarchy (DSH) that explores specific diseases and their known treatment pathways in a nested fashion to create subpopulations in a clinically meaningful way. As the DSH tree is traversed from the root towards the leaves, we encounter subpopulations that share increasing richer amounts of clinical details such as similar disease severity, illness trajectories, and time to event that are discriminative, and suitable for learning risk stratification models. The proposed DSH risk scores effectively and accurately predict the age at which a patient may be at risk of dying or developing MCE significantly better than a traditional representation of disease conditions. DSH utilizes known relationships among various entities in EHR data to capture disease severity in a natural way and has the additional benefit of being expressive and interpretable. This novel patient representation can help support critical decision making, development of smart EBP guidelines, and enhance healthcare care and disease management by helping to identify and reduce disease burden among high-risk patients.more » « less
-
The increased growth of the aging population (i.e., 65 years or older) has led to emerging technologies in health care that provide in-home support to patients using devices throughout the household. Such smart home environments can monitor and interact with patients and their doctors/caregivers to augment patient medical data for diagnosis than can be generated via traditional doctor visits. Moreover, smart homes are enabling older adults to stay at home longer as opposed to permanent moves to assisted living or nursing facilities, increasing health and well-being and decreasing overall costs to the individual and society at large. This paper proposes Cognitive Assisted Living (CAL), a cyber-physical system comprising a network of embedded devices for collecting and analyzing patient speech patterns over time for monitoring cognitive function beginning in the early stages of Alzheimer’s disease. Specifically, CAL will analyze patient speech patterns and spatial abilities, via a set of daily interactions, to provide a longitudinal analysis of speech deterioration, a significant indicator of cognitive decline resulting from Alzheimer’s disease. Understanding the rate of cognitive decline can enable caregivers and health care professionals to better manage the patient’s daily care and medical requirements. Additionally, the patient’s cognitive state can be shared across household devices to increase the patient’s comfort and better accommodate lifestyle changes. To these ends, we describe the architecture of the proposed system, the methods to which we will detect cognitive decline, and specify how the system will provide continuing fault tolerance and data security at run time.more » « less
-
BackgroundHealth care interactions may require patients to share with a physician information they believe but is incorrect. While a key piece of physicians’ work is educating their patients, people’s concerns of being seen as uninformed or incompetent by physicians may lead them to think that sharing incorrect health beliefs comes with a penalty. We tested people’s perceptions of patients who share incorrect information and how these perceptions vary by the reasonableness of the belief and its centrality to the patient’s disease. DesignWe recruited 399 United States Prolific.co workers (357 retained after exclusions), 200 Prolific.co workers who reported having diabetes (139 after exclusions), and 244 primary care physicians (207 after exclusions). Participants read vignettes describing patients with type 2 diabetes sharing health beliefs that were central or peripheral to the management of diabetes. Beliefs included true and incorrect statements that were reasonable or unreasonable to believe. Participants rated how a doctor would perceive the patient, the patient’s ability to manage their disease, and the patient’s trust in doctors. ResultsParticipants rated patients who shared more unreasonable beliefs more negatively. There was an extra penalty for incorrect statements central to the patient’s diabetes management (sample 1). These results replicated for participants with type 2 diabetes (sample 2) and physician participants (sample 3). ConclusionsParticipants believed that patients who share incorrect information with their physicians will be penalized for their honesty. Physicians need to be educated on patients’ concerns so they can help patients disclose what may be most important for education. HighlightsUnderstanding how people think they will be perceived in a health care setting can help us understand what they may be wary to share with their physicians. People think that patients who share incorrect beliefs will be viewed negatively. Helping patients share incorrect beliefs can improve care.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.2196/48067
