Machine Learning-Based Prediction Models for 30-Day Readmission after Hospitalization for Chronic Obstructive Pulmonary Disease

Automated detection of airflow obstructive diseases: A systematic review of the last decade (2013-2022)

BACKGROUND AND OBJECTIVE

Obstructive airway diseases, including asthma and Chronic Obstructive Pulmonary Disease (COPD), are two of the most common chronic respiratory health problems. Both of these conditions require health professional expertise in making a diagnosis. Hence, this process is time intensive for healthcare providers and the diagnostic quality is subject to intra- and inter- operator variability. In this study we investigate the role of automated detection of obstructive airway diseases to reduce cost and improve diagnostic quality.

METHODS

We investigated the existing body of evidence and applied Preferred Reporting Items for Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to search records in IEEE, Google scholar, and PubMed databases. We identified 65 papers that were published from 2013 to 2022 and these papers cover 67 different studies. The review process was structured according to the medical data that was used for disease detection. We identified six main categories, namely air flow, genetic, imaging, signals, and miscellaneous. For each of these categories, we report both disease detection methods and their performance.

RESULTS

We found that medical imaging was used in 14 of the reviewed studies as data for automated obstructive airway disease detection. Genetics and physiological signals were used in 13 studies. Medical records and air flow were used in 9 and 7 studies, respectively. Most papers were published in 2020 and we found three times more work on Machine Learning (ML) when compared to Deep Learning (DL). Statistical analysis shows that DL techniques achieve higher Accuracy (ACC) when compared to ML. Convolutional Neural Network (CNN) is the most common DL classifier and Support Vector Machine (SVM) is the most widely used ML classifier. During our review, we discovered only two publicly available asthma and COPD datasets. Most studies used private clinical datasets, so data size and data composition are inconsistent.

CONCLUSIONS

Our review results indicate that Artificial Intelligence (AI) can improve both decision quality and efficiency of health professionals during COPD and asthma diagnosis. However, we found several limitations in this review, such as a lack of dataset consistency, a limited dataset and remote monitoring was not sufficiently explored. We appeal to society to accept and trust computer aided airflow obstructive diseases diagnosis and we encourage health professionals to work closely with AI scientists to promote automated detection in clinical practice and hospital settings.

A cohort of patients in New York State with an alcohol use disorder and subsequent treatment information - A merging of two administrative data sources

OBJECTIVE

Despite the high prevalence of alcohol use disorder (AUD) in the United States, limited research is focused on the associations among AUD, pain, and opioids/benzodiazepine use. In addition, little is known regarding individuals with a history of AUD and their potential risk for pain diagnoses, pain prescriptions, and subsequent misuse. Moreover, the potential risk of pain diagnoses, prescriptions, and subsequent misuse among individuals with a history of AUD is not well known. The objective was to develop a tailored dataset by linking data from 2 New York State (NYS) administrative databases to investigate a series of hypotheses related to AUD and painful medical disorders.

METHODS

Data from the NYS Office of Addiction Services and Supports (OASAS) Client Data System (CDS) and Medicaid claims data from the NYS Department of Health Medicaid Data Warehouse (MDW) were merged using a stepwise deterministic method. Multiple patient-level identifier combinations were applied to create linkage rules. We included patients aged 18 and older from the OASAS CDS who initially entered treatment with a primary substance use of alcohol and no use of opioids between January 1, 2003, and September 23, 2019. This cohort was then linked to corresponding Medicaid claims.

RESULTS

A total of 177,685 individuals with a primary AUD problem and no opioid use history were included in the dataset. Of these, 37,346 (21.0%) patients had an OUD diagnosis, and 3,365 (1.9%) patients experienced an opioid overdose. There were 121,865 (68.6%) patients found to have a pain condition.

CONCLUSION

The integrated database allows researchers to examine the associations among AUD, pain, and opioids/benzodiazepine use, and propose hypotheses to improve outcomes for at-risk patients. The findings of this study can contribute to the development of a prognostic prediction model and the analysis of longitudinal outcomes to improve the care of patients with AUD.

Development and Internal Validation of an Interpretable Machine Learning Model to Predict Readmissions in a United States Healthcare System

(1) One in four hospital readmissions is potentially preventable. Machine learning (ML) models have been developed to predict hospital readmissions and risk-stratify patients, but thus far they have been limited in clinical applicability, timeliness, and generalizability. (2) Methods: Using deidentified clinical data from the University of California, San Francisco (UCSF) between January 2016 and November 2021, we developed and compared four supervised ML models (logistic regression, random forest, gradient boosting, and XGBoost) to predict 30-day readmissions for adults admitted to a UCSF hospital. (3) Results: Of 147,358 inpatient encounters, 20,747 (13.9%) patients were readmitted within 30 days of discharge. The final model selected was XGBoost, which had an area under the receiver operating characteristic curve of 0.783 and an area under the precision-recall curve of 0.434. The most important features by Shapley Additive Explanations were days since last admission, discharge department, and inpatient length of stay. (4) Conclusions: We developed and internally validated a supervised ML model to predict 30-day readmissions in a US-based healthcare system. This model has several advantages including state-of-the-art performance metrics, the use of clinical data, the use of features available within 24 h of discharge, and generalizability to multiple disease states.

Machine Learning-Based 30-Day Hospital Readmission Predictions for COPD Patients Using Physical Activity Data of Daily Living with Accelerometer-Based Device

Chronic obstructive pulmonary disease (COPD) is a significantly concerning disease, and is ranked highest in terms of 30-day hospital readmission. Generally, physical activity (PA) of daily living reflects the health status and is proposed as a strong indicator of 30-day hospital readmission for patients with COPD. This study attempted to predict 30-day hospital readmission by analyzing continuous PA data using machine learning (ML) methods. Data were collected from 16 patients with COPD over 3877 days, and clinical information extracted from the patients’ hospital records. Activity-based parameters were conceptualized and evaluated, and ML models were trained and validated to retrospectively analyze the PA data, identify the nonlinear classification characteristics of different risk factors, and predict hospital readmissions. Overall, this study predicted 30-day hospital readmission and prediction performance is summarized as two distinct approaches: prediction-based performance and event-based performance. In a prediction-based performance analysis, readmissions predicted with 70.35% accuracy; and in an event-based performance analysis, the total 30-day readmissions were predicted with a precision of 72.73%. PA data reflect the health status; thus, PA data can be used to predict hospital readmissions. Predicting readmissions will improve patient care, reduce the burden of medical costs burden, and can assist in staging suitable interventions, such as promoting PA, alternate treatment plans, or changes in lifestyle to prevent readmissions.

Prediction of 30-day risk of acute exacerbation of readmission in elderly patients with COPD based on support vector machine model

Background

Acute exacerbation of chronic obstructive pulmonary disease (COPD) is an important event in the process of disease management. Early identification of high-risk groups for readmission and appropriate measures can avoid readmission in some groups, but there is still a lack of specific prediction tools. The predictive performance of the model built by support vector machine (SVM) has been gradually recognized by the medical field. This study intends to predict the risk of acute exacerbation of readmission in elderly COPD patients within 30 days by SVM, in order to provide scientific basis for screening and prevention of high-risk patients with readmission.

Methods

A total of 1058 elderly COPD patients from the respiratory department of 13 general hospitals in Ningxia region of China from April 2019 to August 2020 were selected as the study subjects by convenience sampling method, and were followed up to 30 days after discharge. Discuss the influencing factors of patient readmission, and built four kernel function models of Linear-SVM, Polynomial-SVM, Sigmoid-SVM and RBF-SVM based on the influencing factors. According to the ratio of training set and test set 7:3, they are divided into training set samples and test set samples, Analyze and Compare the prediction efficiency of the four kernel functions by the precision, recall, accuracy, F1 index and area under the ROC curve (AUC).

Results

Education level, smoking status, coronary heart disease, hospitalization times of acute exacerbation of COPD in the past 1 year, whether long-term home oxygen therapy, whether regular medication, nutritional status and seasonal factors were the influencing factors for readmission. The training set shows that Linear-SVM, Polynomial-SVM, Sigmoid-SVM and RBF-SVM precision respectively were 69.89, 78.07, 79.37 and 84.21; Recall respectively were 50.78, 69.53, 78.74 and 88.19; Accuracy respectively were 83.92, 88.69, 90.81 and 93.82; F1 index respectively were 0.59, 0.74, 0.79 and 0.86; AUC were 0.722, 0.819, 0.866 and 0.918. Test set precision respectively were86.36, 87.50, 80.77 and 88.24; Recall respectively were51.35, 75.68, 56.76 and 81.08; Accuracy respectively were 85.11, 90.78, 85.11 and 92.20; F1 index respectively were 0.64, 0.81, 0.67 and 0.85; AUC respectively were 0.742, 0.858, 0.759 and 0.885.

Conclusions

This study found the factors that may affect readmission, and the SVM model constructed based on the above factors achieved a certain predictive effect on the risk of readmission, which has certain reference value.

Machine learning reveals salivary glycopatterns as potential biomarkers for the diagnosis and prognosis of papillary thyroid cancer

The diagnosis of thyroid cancer, especially papillary thyroid cancer (PTC), is increasing rapidly worldwide. In this study, we aimed to study the glycosylation of salivary proteins associated with PTC and assess the likelihood that salivary glycopatterns may be a potential biomarker of PTC diagnosis. Firstly, 22 benign thyroid nodule (BTN) samples, 27 PTC samples, and 30 healthy volunteers (HV) samples were collected to probe the difference of salivary glycopatterns associated with PTC using lectin microarrays. Then, five machine learning models including K-Nearest Neighbor (KNN), Multilayer Perceptron (MLP), Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) were established to distinguish HV, BTN and PTC based on the changes of salivary glycopatterns. As a result, SVM had the best diagnostic effect with an accuracy rate of 92 % in testing set. Besides, lectin microarrays were used to explore the differences in salivary glycopatterns of 26 paired salivary samples of PTC patients before and after operation in order to probe into salivary glycopatterns as potential biomarkers for prognosis of PTC patients. The results showed that the levels of salivary glycopatterns recognized by 6 different lectins in patients after the operation almost convergenced with HVs. This study could help to screen and assess patients with PTC and their prognosis based on precise changes of salivary glycopatterns.

Predictive modeling for COVID-19 readmission risk using machine learning algorithms

Introduction

The COVID-19 pandemic overwhelmed healthcare systems with severe shortages in hospital resources such as ICU beds, specialized doctors, and respiratory ventilators. In this situation, reducing COVID-19 readmissions could potentially maintain hospital capacity. By employing machine learning (ML), we can predict the likelihood of COVID-19 readmission risk, which can assist in the optimal allocation of restricted resources to seriously ill patients.

Methods

In this retrospective single-center study, the data of 1225 COVID-19 patients discharged between January 9, 2020, and October 20, 2021 were analyzed. First, the most important predictors were selected using the horse herd optimization algorithms. Then, three classical ML algorithms, including decision tree, support vector machine, and k-nearest neighbors, and a hybrid algorithm, namely water wave optimization (WWO) as a precise metaheuristic evolutionary algorithm combined with a neural network were used to construct predictive models for COVID-19 readmission. Finally, the performance of prediction models was measured, and the best-performing one was identified.

Results

The ML algorithms were trained using 17 validated features. Among the four selected ML algorithms, the WWO had the best average performance in tenfold cross-validation (accuracy: 0.9705, precision: 0.9729, recall: 0.9869, specificity: 0.9259, F-measure: 0.9795).

Conclusions

Our findings show that the WWO algorithm predicts the risk of readmission of COVID-19 patients more accurately than other ML algorithms. The models developed herein can inform frontline clinicians and healthcare policymakers to manage and optimally allocate limited hospital resources to seriously ill COVID-19 patients.

Machine learning for predicting readmission risk among the frail: Explainable AI for healthcare

Healthcare costs due to unplanned readmissions are high and negatively affect health and wellness of patients. Hospital readmission is an undesirable outcome for elderly patients. Here, we present readmission risk prediction using five machine learning approaches for predicting 30-day unplanned readmission for elderly patients (age ≥ 50 years). We use a comprehensive and curated set of variables that include frailty, comorbidities, high-risk medications, demographics, hospital, and insurance utilization to build these models. We conduct a large-scale study with electronic health record (her) data with over 145,000 observations from 76,000 patients. Findings indicate that the category boost (CatBoost) model outperforms other models with a mean area under the curve (AUC) of 0.79. We find that prior readmissions, discharge to a rehabilitation facility, length of stay, comorbidities, and frailty indicators were all strong predictors of 30-day readmission. We present in-depth insights using Shapley additive explanations (SHAP), the state of the art in machine learning explainability.

Predicting hospital readmission risk in patients with COVID-19: A machine learning approach

Introduction

The Coronavirus 2019 (COVID-19) epidemic stunned the health systems with severe scarcities in hospital resources. In this critical situation, decreasing COVID-19 readmissions could potentially sustain hospital capacity. This study aimed to select the most affecting features of COVID-19 readmission and compare the capability of Machine Learning (ML) algorithms to predict COVID-19 readmission based on the selected features.

Material and methods

The data of 5791 hospitalized patients with COVID-19 were retrospectively recruited from a hospital registry system. The LASSO feature selection algorithm was used to select the most important features related to COVID-19 readmission. HistGradientBoosting classifier (HGB), Bagging classifier, Multi-Layered Perceptron (MLP), Support Vector Machine ((SVM) kernel = linear), SVM (kernel = RBF), and Extreme Gradient Boosting (XGBoost) classifiers were used for prediction. We evaluated the performance of ML algorithms with a 10-fold cross-validation method using six performance evaluation metrics.

Results

Out of the 42 features, 14 were identified as the most relevant predictors. The XGBoost classifier outperformed the other six ML models with an average accuracy of 91.7%, specificity of 91.3%, the sensitivity of 91.6%, F-measure of 91.8%, and AUC of 0.91%.

Conclusion

The experimental results prove that ML models can satisfactorily predict COVID-19 readmission. Besides considering the risk factors prioritized in this work, categorizing cases with a high risk of reinfection can make the patient triaging procedure and hospital resource utilization more effective.

Review of Artificial Intelligence techniques in Chronic Obstructive Lung Disease

BACKGROUND

Artificial Intelligence (AI) has proven to be an invaluable asset in the healthcare domain, where massive amounts of data are produced. Chronic Obstructive Pulmonary Disease (COPD) is a heterogeneous chronic condition with multiscale manifestations and complex interactions that represents an ideal target for AI.

OBJECTIVE

The aim of this review article is to appraise the adoption of AI in COPD research, and more specifically its applications to date along with reported results, potential challenges and future prospects.

METHODS

We performed a review of the literature from PubMed and DBLP and assembled studies published up to 2020, yielding 156 articles relevant to the scope of this review.

RESULTS

The resulting articles were assessed and organized into four basic contextual categories, namely: i) COPD diagnosis, ii) COPD prognosis, iii) Patient classification, iv) COPD management, and subsequently presented in an orderly manner based on a set of qualitative and quantitative criteria.

CONCLUSIONS

We observed considerable acceleration of research activity utilizing AI techniques in COPD research, especially in the last couple of years, nevertheless, the massive production of large and complex data in COPD calls for broader adoption of AI and more advanced techniques.

AI in predicting COPD in the Canadian population

Chronic obstructive pulmonary disease (COPD) is a progressive lung disease that produces non-reversible airflow limitations. Approximately 10% of Canadians aged 35 years or older are living with COPD. Primary care is often the first contact an individual will have with the healthcare system providing acute care, chronic disease management, and services aimed at health maintenance. This study used Electronic Medical Record (EMR) data from primary care clinics in seven provinces across Canada to develop predictive models to identify COPD in the Canadian population. The comprehensive nature of this primary care EMR data containing structured numeric, categorical, hybrid, and unstructured text data, enables the predictive models to capture symptoms of COPD and discriminate it from diseases with similar symptoms. We applied two supervised machine learning models, a Multilayer Neural Networks (MLNN) model and an Extreme Gradient Boosting (XGB) to identify COPD patients. The XGB model achieved an accuracy of 86% in the test dataset compared to 83% achieved by the MLNN. Utilizing feature importance, we identified a set of key symptoms from the EMR for diagnosing COPD, which included medications, health conditions, risk factors, and patient age. Application of this XGB model to primary care structured EMR data can identify patients with COPD from others having similar chronic conditions for disease surveillance, and improve evidence-based care delivery.

Analyzing the use of artificial intelligence for the management of chronic obstructive pulmonary disease (COPD)

OBJECTIVE

Chronic obstructive pulmonary disease (COPD) is a disease that causes airflow limitation to the lungs and has a high morbidity around the world. The objective of this study was to evaluate how artificial intelligence (AI) is being applied for the management of the disease, analyzing the objectives that are raised, the algorithms that are used and what results they offer.

METHODS

We conducted a scoping review following the Arksey and O'Malley (2005) and Levac et al. (2010) guidelines. Two reviewers independently searched, analyzed and extracted data from papers of five databases: Web of Science, PubMed, Scopus, Cinahl and Cochrane. To be included, the studies had to apply some AI techniques for the management of at least one stage of the COPD clinical process. In the event of any discrepancy between both reviewers, the criterion of a third reviewer prevailed.

RESULTS

380 papers were identified through database searches. After applying the exclusion criteria, 67 papers were included in the study. The studies were of a different nature and pursued a wide range of objectives, highlighting mainly those focused on the identification, classification and prevention of the disease. Neural nets, support vector machines and decision trees were the AI algorithms most commonly used. The mean and median values of all the performance metrics evaluated were between 80% and 90%.

CONCLUSIONS

The results obtained show a growing interest in the development of medical applications that manage the different phases of the COPD clinical process, especially predictive models. According to the performance shown, these models could be a useful complementary tool in the decision-making by health specialists, although more high-quality ML studies are needed to endorse the findings of this study.

Clinical Data Prediction Model to Identify Patients With Early-Stage Pancreatic Cancer

PURPOSE

Pancreatic cancer is an aggressive malignancy with patients often experiencing nonspecific symptoms before diagnosis. This study evaluates a machine learning approach to help identify patients with early-stage pancreatic cancer from clinical data within electronic health records (EHRs).

MATERIALS AND METHODS

From the Optum deidentified EHR data set, we identified early-stage (n = 3,322) and late-stage (n = 25,908) pancreatic cancer cases over 40 years of age diagnosed between 2009 and 2017. Patients with early-stage pancreatic cancer were matched to noncancer controls (1:16 match). We constructed a prediction model using eXtreme Gradient Boosting (XGBoost) to identify early-stage patients on the basis of 18,220 features within the EHR including diagnoses, procedures, information within clinical notes, and medications. Model accuracy was assessed with sensitivity, specificity, positive predictive value, and the area under the curve.

RESULTS

The final predictive model included 582 predictive features from the EHR, including 248 (42.5%) physician note elements, 146 (25.0%) procedure codes, 91 (15.6%) diagnosis codes, 89 (15.3%) medications, and 9 (1.5%) demographic features. The final model area under the curve was 0.84. Choosing a model cut point with a sensitivity of 60% and specificity of 90% would enable early detection of 58% late-stage patients with a median of 24 months before their actual diagnosis.

CONCLUSION

Prediction models using EHR data show promise in the early detection of pancreatic cancer. Although widespread use of this approach on an unselected population would produce high rates of false-positive tests, this technique may be rapidly impactful if deployed among high-risk patients or paired with other imaging or biomarker screening tools.

Development of a Scoring System to Predict Prolonged Post-Stroke Dysphagia Remaining at Discharge from a Subacute Care Hospital to the Home

BACKGROUND

Prolonged dysphagia is an important stroke-related complication that imposes a substantial burden on patients and families. However, simple scoring tool to predict prolonged dysphagia is not existing.

MATERIALS AND METHODS

This retrospective cohort study used data from April 2010 to March 2016. Adult patients with first-ever stroke were included. The outcome was swallowing function at discharge from the subacute care hospital to the patient's home. We collected the following factors obtained at discharge from the University of Fukui Hospital: age, sex, type of stroke, comorbidities, smoking status, alcohol use, denture use, functional dependency in daily living before admission, National Institutes of Health Stroke Scale score (NIHSS) at admission, and Functional Independence Measure(FIM). Data were divided into a training set (70%) and test set (30%). Lasso and logistic regression were used for feature selection, a scoring system was then developed, and its prediction performance evaluated.

RESULTS

This study enrolled 462 patients with acute stroke. Using lasso and logistic regression, three variables (functional dependency before admission, Functional Independence Measure [FIM]-cognitive and FIM-motor scores at transfer) remained statistically significant predictors of prolonged dysphagia. Risk scores were categorized as low risk (0-2), moderate risk (3-4), and high risk (5-7), with dysphagia rates of 0%-1%, 13%-29%, and 50%-100%, respectively. A newly developed score ≥3 was the optimal cutoff for identifying patients with the potential risk of prolonged dysphagia (C-statistics, 0.92 in the test set).

CONCLUSION

The developed scoring system is simple and has a high performance in predicting prolonged dysphagia after acute stroke.

Artificial Intelligence and Machine Learning in Chronic Airway Diseases: Focus on Asthma and Chronic Obstructive Pulmonary Disease

Chronic airway diseases are characterized by airway inflammation, obstruction, and remodeling and show high prevalence, especially in developing countries. Among them, asthma and chronic obstructive pulmonary disease (COPD) show the highest morbidity and socioeconomic burden worldwide. Although there are extensive guidelines for the prevention, early diagnosis, and rational treatment of these lifelong diseases, their value in precision medicine is very limited. Artificial intelligence (AI) and machine learning (ML) techniques have emerged as effective methods for mining and integrating large-scale, heterogeneous medical data for clinical practice, and several AI and ML methods have recently been applied to asthma and COPD. However, very few methods have significantly contributed to clinical practice. Here, we review four aspects of AI and ML implementation in asthma and COPD to summarize existing knowledge and indicate future steps required for the safe and effective application of AI and ML tools by clinicians.

The determinants of dyspnoea evaluated by the mMRC scale: The French Palomb cohort

INTRODUCTION AND OBJECTIVE

Dyspnoea is a major symptom in COPD patients, but the determinants that could be associated with a higher dyspnoea mMRC score in COPD patients remain unclear. Our research aimed to study the determinants of dyspnoea at the threshold of 1, 2, 3 and 4 mMRC.

PATIENTS AND METHODS

Diagnosis of COPD was made using spirometry with post-bronchodilator FEV₁FVC<70%. An online questionnaire has been employed by pulmonologists to recruit COPD patients. The following variables were collected: age, gender, BMI, FEV₁, RV, IC, TLC, FRC, mMRC, frequency of exacerbations and comorbidities. The LASSO was used to select the variables associated with the mMRC dyspnoea scale in a subgroup (who had no missing IC, RV and FRC values) of 421 COPD patients defined by the previously mentioned variables.

RESULTS

One thousand nine hundred and sevety-three patients (65.3% males, average age=66±10, 38% current smokers) were included. Dyspnoea was correlated with a low FEV₁ and with the number of exacerbations in the past 12 months. Multivariate analysis showed that the determinants of dyspnoea(mMRC≥2) are: FEV₁: OR=3.71[2.86-4.82]; anxiety: OR=2.52[1.82-3.47]; cough: OR=1.94[1.57-2.40]; bronchiectasis: OR=1.84[1.03-3.29]; age: OR=1.80[1.45-2.24]; hyperinflation (RV/TLC): OR=1.68[1.34-2.11]; ischemic cardiopathy: OR=1.63[1.22-2.18]; hypertension: OR=1.52[1.21-1.91]; exacerbations (≥2): OR=1.41[1.10-1.81]; women: OR=1.39[1.10-1.74] and overweight: OR=1.33[1.06-1.67]. The subgroup analysis showed that: FEV₁: OR=3.47[1.96-6.12]; exacerbations (≥2) OR=2.31[1.33-4.17] and hyperinflation (IC/TLC) OR=0.57[0.35-0.85] were associated with higher dyspnoea (mMRC≥2).

CONCLUSION

Our results showed that dyspnoea is related to the severity of airflow limitation, gender, exacerbations, comorbidities and hyperinflation.

Predicting 6-Month Unfavorable Outcome of Acute Ischemic Stroke Using Machine Learning

Background and Purpose: Accurate prediction of functional outcome after stroke would provide evidence for reasonable post-stroke management. This study aimed to develop a machine learning-based prediction model for 6-month unfavorable functional outcome in Chinese acute ischemic stroke (AIS) patient. Methods: We collected AIS patients at National Advanced Stroke Center of Nanjing First Hospital (China) between September 2016 and March 2019. The unfavorable outcome was defined as modified Rankin Scale score (mRS) 3-6 at 6-month. We developed five machine-learning models (logistic regression, support vector machine, random forest classifier, extreme gradient boosting, and fully-connected deep neural network) and assessed the discriminative performance by the area under the receiver-operating characteristic curve. We also compared them to the Houston Intra-arterial Recanalization Therapy (HIAT) score, the Totaled Health Risks in Vascular Events (THRIVE) score, and the NADE nomogram. Results: A total of 1,735 patients were included into this study, and 541 (31.2%) of them had unfavorable outcomes. Incorporating age, National Institutes of Health Stroke Scale score at admission, premorbid mRS, fasting blood glucose, and creatinine, there were similar predictive performance between our machine-learning models, while they are significantly better than HIAT score, THRIVE score, and NADE nomogram. Conclusions: Compared with the HIAT score, the THRIVE score, and the NADE nomogram, the RFC model can improve the prediction of 6-month outcome in Chinese AIS patients.

Implementation of Artificial Intelligence-Based Clinical Decision Support to Reduce Hospital Readmissions at a Regional Hospital

BACKGROUND

Hospital readmissions are a key quality metric, which has been tied to reimbursement. One strategy to reduce readmissions is to direct resources to patients at the highest risk of readmission. This strategy necessitates a robust predictive model coupled with effective, patient-centered interventions.

OBJECTIVE

The aim of this study was to reduce unplanned hospital readmissions through the use of artificial intelligence-based clinical decision support.

METHODS

A commercially vended artificial intelligence tool was implemented at a regional hospital in La Crosse, Wisconsin between November 2018 and April 2019. The tool assessed all patients admitted to general care units for risk of readmission and generated recommendations for interventions intended to decrease readmission risk. Similar hospitals were used as controls. Change in readmission rate was assessed by comparing the 6-month intervention period to the same months of the previous calendar year in exposure and control hospitals.

RESULTS

Among 2,460 hospitalizations assessed using the tool, 611 were designated by the tool as high risk. Sensitivity and specificity for risk assignment were 65% and 89%, respectively. Over 6 months following implementation, readmission rates decreased from 11.4% during the comparison period to 8.1% (p < 0.001). After accounting for the 0.5% decrease in readmission rates (from 9.3 to 8.8%) at control hospitals, the relative reduction in readmission rate was 25% (p < 0.001). Among patients designated as high risk, the number needed to treat to avoid one readmission was 11.

CONCLUSION

We observed a decrease in hospital readmission after implementing artificial intelligence-based clinical decision support. Our experience suggests that use of artificial intelligence to identify patients at the highest risk for readmission can reduce quality gaps when coupled with patient-centered interventions.

Validation of chief complaints, medical history, medications, and physician diagnoses structured with an integrated emergency department information system in Japan: the Next Stage ER system

Aim

Emergency department information systems (EDIS) facilitate free‐text data use for clinical research; however, no study has validated whether the Next Stage ER system (NSER), an EDIS used in Japan, accurately translates electronic medical records (EMRs) into structured data.

Methods

This is a retrospective cohort study using data from the emergency department (ED) of a tertiary care hospital from 2018 to 2019. We used EMRs of 500 random samples from 27,000 ED visits during the study period. Through the NSER system, chief complaints were translated into 231 chief complaint categories based on the Japan Triage and Acuity Scale. Medical history and physician’s diagnoses were encoded using the International Classification of Diseases, 10th Revision; medications were encoded as Anatomical Therapeutic Chemical Classification System codes. Two reviewers independently reviewed 20 items (e.g., presence of fever) for each study component (e.g., chief complaints). We calculated association measures of the structured data by the NSER system, using the chart review results as the gold standard.

Results

Sensitivities were very high (>90%) in 17 chief complaints. Positive predictive values were high for 14 chief complaints (≥80%). Negative predictive values were ≥96% for all chief complaints. For medical history and medications, most of the association measures were very high (>90%). For physicians’ ED diagnoses, sensitivities were very high (>93%) in 16 diagnoses; specificities and negative predictive values were very high (>97%).

Conclusions

Chief complaints, medical history, medications, and physician’s ED diagnoses in EMRs were well‐translated into existing categories or coding by the NSER system.