Birst, Jennifer

Introduction/Background: Patients with heart failure and those waiting for a heart transplant often experience a significant decrease in their ability to perform daily activities and exercise, leading to a lower quality of life. Although exercise-based cardiac rehabilitation (EBCR) is a possible treatment option, its effectiveness has not been well measured, resulting in limited adoption. Research Questions/Hypothesis: Could physical rehabilitation before receiving a heart transplant improve functional status and better outcomes? Goals/Aims: Our objective is to evaluate the effect of pre-transplant physical therapy on the standardized improvement of AM-PAC scores, measured from the earliest pre-transplant assessment to the most recent pre-transplant evaluation. Our second objective is to assess the impact of the latest Pre-Transplant AM-PAC Score on the number of hospital-free days following transplantation. Methods: We conducted a retrospective study on 91 heart transplant patients who received Impella support from January 2019 to April 2023, approved by the Mayo Clinic Institutional Review Board. We collected data on demographics, AMPAC scores, and outcomes at three time points. Continuous variables were compared using the T-test or Mann-Whitney test, and categorical variables using the Chi-square or Fisher's exact test. We used a linear regression model to investigate the relationship between rehabilitation duration and AMPAC scores. Quantile regression was preferred due to the non-normal distribution of the outcome, hospital-free days. Results: We conducted a linear regression analysis and found a statistically significant association between increased hours spent in PT and greater improvement. After one hour of physical therapy, there was an average increase of 1.07 (95% CI 0.1, 2; p=0.03) in AMPAC scoore. We also compared the change in the AMPAC score with hospital-free days, and it was statistically significant in quantile regression analysis, indicating an increase of 0.28 (95% CI 0.2, 0.55; P=0.03) points in the AMPAC Score, corresponding to an additional hospital-free day. Conclusion: Increased hours spent in physical therapy show a significant positive association with greater improvement in standardized AM-PAC Mobility scores and hospital-free days. These findings encourage increasing uptake and support of cardiac rehabilitation programs.

Abstract Introduction Delirium occurrence is common and preventive strategies are resource intensive. Screening tools can prioritize patients at risk. Using machine learning, we can capture time and treatment effects that pose a challenge to delirium prediction. We aim to develop a delirium prediction model that can be used as a screening tool. Methods From the eICU Collaborative Research Database (eICU-CRD) and the Medical Information Mart for Intensive Care version III (MIMIC-III) database, patients with one or more Confusion Assessment Method-Intensive Care Unit (CAM-ICU) values and intensive care unit (ICU) length of stay greater than 24 h were included in our study. We validated our model using 21 quantitative clinical parameters and assessed performance across a range of observation and prediction windows, using different thresholds and applied interpretation techniques. We evaluate our models based on stratified repeated cross-validation using 3 algorithms, namely Logistic Regression, Random Forest, and Bidirectional Long Short-Term Memory (BiLSTM). BiLSTM represents an evolution from recurrent neural network-based Long Short-Term Memory, and with a backward input, preserves information from both past and future. Model performance is measured using Area Under Receiver Operating Characteristic, Area Under Precision Recall Curve, Recall, Precision (Positive Predictive Value), and Negative Predictive Value metrics. Results We evaluated our results on 16 546 patients (47% female) and 6294 patients (44% female) from eICU-CRD and MIMIC-III databases, respectively. Performance was best in BiLSTM models where, precision and recall changed from 37.52% (95% confidence interval [CI], 36.00%–39.05%) to 17.45 (95% CI, 15.83%–19.08%) and 86.1% (95% CI, 82.49%–89.71%) to 75.58% (95% CI, 68.33%–82.83%), respectively as prediction window increased from 12 to 96 h. After optimizing for higher recall, precision and recall changed from 26.96% (95% CI, 24.99%–28.94%) to 11.34% (95% CI, 10.71%–11.98%) and 93.73% (95% CI, 93.1%–94.37%) to 92.57% (95% CI, 88.19%–96.95%), respectively. Comparable results were obtained in the MIMIC-III cohort. Conclusions Our model performed comparably to contemporary models using fewer variables. Using techniques like sliding windows, modification of threshold to augment recall and feature ranking for interpretability, we addressed shortcomings of current models.