Dataset Information

Machine Learning Approaches for Hospital Acquired Pressure Injuries: A Retrospective Study of Electronic Medical Records.

ABSTRACT:

Background

Many machine learning heuristics integrate well with Electronic Medical Record (EMR) systems yet often fail to surpass traditional statistical models for biomedical applications.

Objective

We sought to compare predictive performances of 12 machine learning and traditional statistical techniques to predict the occurrence of Hospital Acquired Pressure Injuries (HAPI).

Methods

EMR information was collected from 57,227 hospitalizations acquired from Dartmouth Hitchcock Medical Center (April 2011 to December 2016). Twelve classification algorithms, chosen based upon classic regression and recent machine learning techniques, were trained to predict HAPI incidence and performance was assessed using the Area Under the Receiver Operating Characteristic Curve (AUC).

Results

Logistic regression achieved a performance (AUC = 0.91 ± 0.034) comparable to the other machine learning approaches. We report discordance between machine learning derived predictors compared to the traditional statistical model. We visually assessed important patient-specific factors through Shapley Additive Explanations.

Conclusions

Machine learning models will continue to inform clinical decision-making processes but should be compared to traditional modeling approaches to ensure proper utilization. Disagreements between important predictors found by traditional and machine learning modeling approaches can potentially confuse clinicians and need to be reconciled. These developments represent important steps forward in developing real-time predictive models that can be integrated into EMR systems to reduce unnecessary harm.

SUBMITTER: Levy JJ

PROVIDER: S-EPMC9243224 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundPsoriasis (PsO) is a chronic, systemic, immune-mediated disease with multiorgan involvement. Psoriatic arthritis (PsA) is an inflammatory arthritis that is present in 6%-42% of patients with PsO. Approximately 15% of patients with PsO have undiagnosed PsA. Predicting patients with a risk of PsA is crucial for providing them with early examination and treatment that can prevent irreversible disease progression and function loss.ObjectiveThe aim of this study was to develop and validate a prediction model for PsA based on chronological large-scale and multidimensional electronic medical records using a machine learning algorithm.MethodsThis case-control study used Taiwan's National Health Insurance Research Database from January 1, 1999, to December 31, 2013. The original data set was split into training and holdout data sets in an 80:20 ratio. A convolutional neural network was used to develop a prediction model. This model used 2.5-year diagnostic and medical records (inpatient and outpatient) with temporal-sequential information to predict the risk of PsA for a given patient within the next 6 months. The model was developed and cross-validated using the training data and was tested using the holdout data. An occlusion sensitivity analysis was performed to identify the important features of the model.ResultsThe prediction model included a total of 443 patients with PsA with earlier diagnosis of PsO and 1772 patients with PsO without PsA for the control group. The 6-month PsA risk prediction model that uses sequential diagnostic and drug prescription information as a temporal phenomic map yielded an area under the receiver operating characteristic curve of 0.70 (95% CI 0.559-0.833), a mean sensitivity of 0.80 (SD 0.11), a mean specificity of 0.60 (SD 0.04), and a mean negative predictive value of 0.93 (SD 0.04).ConclusionsThe findings of this study suggest that the risk prediction model can identify patients with PsO at a high risk of PsA. This model may help health care professionals to prioritize treatment for target high-risk populations and prevent irreversible disease progression and functional loss.

Project description:BackgroundPatients develop pressure injuries (PIs) in the hospital owing to low mobility, exposure to localized pressure, circulatory conditions, and other predisposing factors. Over 2.5 million Americans develop PIs annually. The Center for Medicare and Medicaid considers hospital-acquired PIs (HAPIs) as the most frequent preventable event, and they are the second most common claim in lawsuits. With the growing use of electronic health records (EHRs) in hospitals, an opportunity exists to build machine learning models to identify and predict HAPI rather than relying on occasional manual assessments by human experts. However, accurate computational models rely on high-quality HAPI data labels. Unfortunately, the different data sources within EHRs can provide conflicting information on HAPI occurrence in the same patient. Furthermore, the existing definitions of HAPI disagree with each other, even within the same patient population. The inconsistent criteria make it impossible to benchmark machine learning methods to predict HAPI.ObjectiveThe objective of this project was threefold. We aimed to identify discrepancies in HAPI sources within EHRs, to develop a comprehensive definition for HAPI classification using data from all EHR sources, and to illustrate the importance of an improved HAPI definition.MethodsWe assessed the congruence among HAPI occurrences documented in clinical notes, diagnosis codes, procedure codes, and chart events from the Medical Information Mart for Intensive Care III database. We analyzed the criteria used for the 3 existing HAPI definitions and their adherence to the regulatory guidelines. We proposed the Emory HAPI (EHAPI), which is an improved and more comprehensive HAPI definition. We then evaluated the importance of the labels in training a HAPI classification model using tree-based and sequential neural network classifiers.ResultsWe illustrate the complexity of defining HAPI, with <13% of hospital stays having at least 3 PI indications documented across 4 data sources. Although chart events were the most common indicator, it was the only PI documentation for >49% of the stays. We demonstrate a lack of congruence across existing HAPI definitions and EHAPI, with only 219 stays having a consensus positive label. Our analysis highlights the importance of our improved HAPI definition, with classifiers trained using our labels outperforming others on a small manually labeled set from nurse annotators and a consensus set in which all definitions agreed on the label.ConclusionsStandardized HAPI definitions are important for accurately assessing HAPI nursing quality metric and determining HAPI incidence for preventive measures. We demonstrate the complexity of defining an occurrence of HAPI, given the conflicting and incomplete EHR data. Our EHAPI definition has favorable properties, making it a suitable candidate for HAPI classification tasks.

Project description:BackgroundSecondary hypertension is a kind of hypertension with a definite etiology and may be cured. Patients with suspected secondary hypertension can benefit from timely detection and treatment and, conversely, will have a higher risk of morbidity and mortality than those with primary hypertension.ObjectiveThe aim of this study was to develop and validate machine learning (ML) prediction models of common etiologies in patients with suspected secondary hypertension.MethodsThe analyzed data set was retrospectively extracted from electronic medical records of patients discharged from Fuwai Hospital between January 1, 2016, and June 30, 2019. A total of 7532 unique patients were included and divided into 2 data sets by time: 6302 patients in 2016-2018 as the training data set for model building and 1230 patients in 2019 as the validation data set for further evaluation. Extreme Gradient Boosting (XGBoost) was adopted to develop 5 models to predict 4 etiologies of secondary hypertension and occurrence of any of them (named as composite outcome), including renovascular hypertension (RVH), primary aldosteronism (PA), thyroid dysfunction, and aortic stenosis. Both univariate logistic analysis and Gini Impurity were used for feature selection. Grid search and 10-fold cross-validation were used to select the optimal hyperparameters for each model.ResultsValidation of the composite outcome prediction model showed good performance with an area under the receiver-operating characteristic curve (AUC) of 0.924 in the validation data set, while the 4 prediction models of RVH, PA, thyroid dysfunction, and aortic stenosis achieved AUC of 0.938, 0.965, 0.959, and 0.946, respectively, in the validation data set. A total of 79 clinical indicators were identified in all and finally used in our prediction models. The result of subgroup analysis on the composite outcome prediction model demonstrated high discrimination with AUCs all higher than 0.890 among all age groups of adults.ConclusionsThe ML prediction models in this study showed good performance in detecting 4 etiologies of patients with suspected secondary hypertension; thus, they may potentially facilitate clinical diagnosis decision making of secondary hypertension in an intelligent way.

Project description:Researchers have shown in laboratory studies that different types of fabrics were associated with changes in skin moisture, friction, shear, and temperature that may predispose patients to pressure injury. There was an association between type of fiber used in hospital linens and pressure injury development in previous clinical studies. We examined if bed linens made from a newly developed synthetic fiber fabric affected occurrence rate, time to development, and severity of unit-acquired pressure injury in critically ill adult inpatients.DesignCluster randomized controlled trial.SettingFive adult medical ICUs within one quaternary care center in the Midwest United States.PatientsPatients were assigned to a unit based on bed availability. In total, there were 3,332 patients in the study.InterventionsParticipating medical ICUs were randomly assigned to cotton fiber or synthetic fiber linens for the first 6 months of the study period, and assignment reversed after a 14-day washout period for the final 6 months.Measurements and main resultsUnit-acquired pressure injury occurrence rate, time to first unit-acquired pressure injury, and severity were evaluated using generalized mixed effect models with patient as a random effect, and a marginal Cox proportional hazards model with repeated admissions from the same patient accounted for by use of a sandwich estimator of the variance. There were 1,706 patients on cotton fiber linens and 1,626 patients on synthetic fiber linens. Groups were similar on demographics except race and admitting diagnosis groupings. Occurrence rate (p = 0.99), time to development (p = 0.99), and maximum severity of unit-acquired pressure (p = 0.86) were similar between groups before and after controlling for race and admitting diagnosis groupings.ConclusionsLinen type did not affect unit-acquired pressure injury occurrence rate, severity, or timing. Standard unit-acquired pressure injury prevention efforts may be more cost-effective than investment in synthetic fiber linens.

Project description:ObjectivesTo separately examine and comprehensively compare the risk factors for hospital-acquired (HAPIs) and community-acquired pressure injuries (CAPIs).DesignA mixed case-control study.SettingFour medical centres in China.ParticipantsInclusion criteria included patients who were (1) aged ≥18 years on admission; (2) admitted between January 2014 and December 2018, and (3) diagnosed with HAPIs (cases) or with no HAPIs (controls) during hospitalisation in the HAPIs study, and confirmed with CAPIs (cases) or with no PIs (controls) on admission in the CAPIs study. The exclusion criteria were as follows: (1) admitted for childbirth, psychiatric reasons or rehabilitation; (2) admitted for observation; (3) transferred from another hospital and (4) confirmed to have suffered PIs from previous hospitalisations in the CAPIs study. In total, 320 cases and 1657 controls were included in the HAPIs study, and 1763 cases and 1786 controls were included in the CAPIs study.Primary and secondary outcome measuresThe outcome variable was the occurrence of PIs.ResultsThe existence of PIs or scars from previous PIs on admission, presence of forced posture, use of medical devices and surgery during hospitalisation were found to be independent risk factors for HAPIs, as evidenced by the corresponding OR and 95% CI values of 51.931 (34.241 to 78.763), 2.006 (1.405 to 2.864), 3.226 (1.709 to 6.089) and 2.161 (1.452 to 3.215), respectively. Age, sex, Braden rating and diabetes were found to be independent risk factors for CAPIs, as evidenced by the corresponding OR and 95% CI values of 1.031 (1.026 to 1.036), 0.810 (0.698 to 0.941), 1.235 (1.167 to 1.307) and 2.059 (1.332 to 3.184), respectively.ConclusionsThe existence of PIs or scars from previous PIs on admission, presence of forced posture, use of medical devices and surgery during hospitalisation are suggested to be included as independent items for the risk assessment of PIs, together with the Braden scale. The Braden rating plays different roles in the development of CAPIs and HAPIs.