External validation of EPIC's Risk of Unplanned Readmission model, the LACE+ index and SQLape as predictors of unplanned hospital readmissions: A monocentric, retrospective, diagnostic cohort study in Switzerland

Machine Learning-Based Prediction of Readmission Risk in Cardiovascular and Cerebrovascular Conditions Using Patient EMR Data

The primary objective of this study was to develop a risk-based readmission prediction model using the EMR data available at discharge. This model was then validated with the LACE plus score. The study cohort consisted of about 310,000 hospital admissions of patients with cardiovascular and cerebrovascular conditions. The EMR data of the patients consisted of lab results, vitals, medications, comorbidities, and admit/discharge settings. These data served as the input to an XGBoost model v1.7.6, which was then used to predict the number of days until the next readmission. Our model achieved remarkable results, with a precision score of 0.74 (±0.03), a recall score of 0.75 (±0.02), and an overall accuracy of approximately 82% (±5%). Notably, the model demonstrated a high accuracy rate of 78.39% in identifying the patients readmitted within 30 days and 80.81% accuracy for those with readmissions exceeding six months. The model was able to outperform the LACE plus score; of the people who were readmitted within 30 days, only 47.70 percent had a LACE plus score greater than 70, and, for people with greater than 6 months, only 10.09 percent had a LACE plus score less than 30. Furthermore, our analysis revealed that the patients with a higher comorbidity burden and lower-than-normal hemoglobin levels were associated with increased readmission rates. This study opens new doors to the world of differential patient care, helping both clinical decision makers and healthcare providers make more informed and effective decisions. This model is comparatively more robust and can potentially substitute the LACE plus score in cardiovascular and cerebrovascular settings for predicting the readmission risk.

Evaluation of the Impact of Discharge Clinic Follow-Up Interventions on 30-Day Readmission Rates

Care transition programs can result in cost avoidance and decreased resource utilization. This project aimed to determine whether implementation of a discharge clinic, referral to a community paramedicine program, or a second postdischarge call affected 30-day readmission rates. This single-center retrospective exploratory design study included 727 discharged patients without access to a primary care provider who were scheduled for a discharge clinic transitions appointment. Readmission rates were 17.7% for those who completed a discharge appointment and 24.7% for those who did not; 4% for those completing a second postdischarge call and 26% for those who did not; and 11.1% for those referred to a community paramedicine program and 24.9% for those not referred. A completed discharge clinic appointment resulted in 36% lower odds of readmission. A completed discharge clinic appointment was effective in reducing 30-day readmission rates as was a follow-up call.

[The general practitioner model in Switzerland described using the example of the doctor network mediX luzern]

The majority of the Swiss population is insured in a general practitioner model. mediX luzern is a network of primary care practices providing guidance and care for those insured with the general practitioner model on their patient path. The network is committed to constant quality optimization in its member practices. Interdisciplinary and interprofessional collaboration is promoted inside and outside the practice, and the interfaces between outpatient and inpatient care are optimized. In joint quality circles, medical practice guidelines and patient health information are developed. All practices are required to be certified by the Equam Foundation. The culture of error is actively encouraged as part of quality management by practicing critical incidence reporting. Lastly, research questions are discussed and data is collected in collaboration with academic centers and institutes for primary care, in particular in Zurich and Lucerne. These quality management efforts and the formation of group practices, which enable part-time work, promote the next generation of general practitioners. Even though cantons and universities provide support, further efforts will be necessary in the future to be able to continue to shape primary care services according to the population's needs.

A validation study of the high acuity readmission risk pediatric screen (HARRPS) tool©: Predicting readmission risk within the pediatric population

BACKGROUND

The initial research study of the High Acuity Readmission Risk Pediatric Screen (HARRPS) Tool © focused on using retrospective data to apply weighted values to the questions within the tool, identify overall risk score, and attribute risk categories (low, moderate, high risk) to the overall risk score. This study focused on validating the data from the initial study, as well as cross examining the need to include admission diagnosis within the tool.

METHOD

Study was a single-centered, retrospective chart review study using a different subset of patients from the initial study. Pediatric patients with thirty-day readmissions were compared to pediatric patients without a thirty-day readmission over a twelve-month period. Utilized same statistical software and methodology from initial study to identify if readmission risk probability could be replicated with a different population.

RESULTS

The initial study performed in 2018 demonstrated a c-statistic score/ area under the curve (AUC) of 0.68 [95% CI: 0.67, 0.69]. In addition, the initial study demonstrated as risk score increases, the probability of readmission gradually increased until a patient had a risk score of seven or greater, at which point readmission risk plateaued. This resulted in low, moderate, and high readmission risk categories. The current study performed using data from 2019 demonstrated an improved c-statistic score / AUC of 0.83 [95% CI: 0.80, 0.87] with admission diagnosis included, and a c-statistic score / AUC of 0.80 [95% CI: 0.76, 0.83] without the admission diagnosis included. The analysis of overall risk score demonstrated a substantial difference in how to interpret final readmission risk scores. Both the initial study and validation study were consistent in demonstrating a risk score of three or less was associated with low readmission risk. However, in the validation study, there was no substantial difference between moderate or high risk, leading to updating the tool from 3 risk categories into 2 risk categories of low risk and at risk of readmission.

CONCLUSION

Based on the finding from the validation study, the admission diagnosis was removed from the HARRPS Tool© as the difference in c-statistic score was nominal, and the risk categories were changed from three categories (low, moderate, high risk) to two categories of low risk (score 0-2) and at risk of readmission for a score of 3+. The ability of the HARRPS Tool© to predict readmission risk preforms best with a c-statistic = 0.80, outperforming the following tools: LACE (0.65), LACE -SDH (0.67), LACE + (0.61), Epic's readmission risk model (0.69), and SQLAPE ® (0.71) (Ryan, et al., 2021; Hwang, et al., 2021).

Electronic health record-based readmission risk model performance for patients undergoing outpatient parenteral antibiotic therapy (OPAT)

BACKGROUND

Outpatient Parenteral Antibiotic Therapy (OPAT) provides coordinated services to deliver parenteral antibiotics outside of the acute care setting. However, the reduction in monitoring and supervision may impact the risks of readmission to the hospital. While identifying those at greatest risk of hospital readmission through use of computer decision support systems could aid in its prevention, validation of such tools in this patient population is lacking.

OBJECTIVE

The primary aim of this study is to determine the ability of the electronic health record-embedded EPIC Unplanned Readmission Model 1 to predict all-cause 30-day hospital unplanned readmissions in discharged patients receiving OPAT through the Duke University Heath System (DUHS) OPAT program. We then explored the impact of OPAT-specific variables on model performance.

METHODS

This retrospective cohort study included patients ≥ 18 years of age discharged to home or skilled nursing facility between July 1, 2019 -February 1, 2020 with OPAT care initiated inpatient and coordinated by the DUHS OPAT program and with at least one Epic readmission score during the index hospitalization. Those with a planned duration of OPAT < 7 days, receiving OPAT administered in a long-term acute care facility (LTAC), or ongoing renal replacement therapy were excluded. The relationship between the primary outcome (unplanned readmission during 30-day post-index discharge) and Epic readmission scores during the index admission (discharge and maximum) was examined using multivariable logistic regression models adjusted for additional predictors. The performance of the models was assessed with the scaled Brier score for overall model performance, the area under the receiver operating characteristics curve (C-index) for discrimination ability, calibration plot for calibration, and Hosmer-Lemeshow goodness-of-fit test for model fit.

RESULTS

The models incorporating maximum or discharge Epic readmission scores showed poor discrimination ability (C-index 0.51, 95% CI 0.45 to 0.58 for both models) in predicting 30-day unplanned readmission in the Duke OPAT cohort. Incorporating additional OPAT-specific variables did not improve the discrimination ability (C-index 0.55, 95% CI 0.49 to 0.62 for the max score; 0.56, 95% CI 0.49 to 0.62 for the discharge score). Although models for predicting 30-day unplanned OPAT-related readmission performed slightly better, discrimination ability was still poor (C-index 0.54, 95% CI 0.45 to 0.62 for both models).

CONCLUSION

EPIC Unplanned Readmission Model 1 scores were not useful in predicting either all-cause or OPAT-related 30-day unplanned readmission in the DUHS OPAT cohort. Further research is required to assess other predictors that can distinguish patients with higher risks of 30-day unplanned readmission in the DUHS OPAT patients.

The use of machine learning and artificial intelligence within pediatric critical care

The field of pediatric critical care has been hampered in the era of precision medicine by our inability to accurately define and subclassify disease phenotypes. This has been caused by heterogeneity across age groups that further challenges the ability to perform randomized controlled trials in pediatrics. One approach to overcome these inherent challenges include the use of machine learning algorithms that can assist in generating more meaningful interpretations from clinical data. This review summarizes machine learning and artificial intelligence techniques that are currently in use for clinical data modeling with relevance to pediatric critical care. Focus has been placed on the differences between techniques and the role of each in the clinical arena. The various forms of clinical decision support that utilize machine learning are also described. We review the applications and limitations of machine learning techniques to empower clinicians to make informed decisions at the bedside. IMPACT: Critical care units generate large amounts of under-utilized data that can be processed through artificial intelligence. This review summarizes the machine learning and artificial intelligence techniques currently being used to process clinical data. The review highlights the applications and limitations of these techniques within a clinical context to aid providers in making more informed decisions at the bedside.