Implementation Experience with a 30-Day Hospital Readmission Risk Score in a Large, Integrated Health System: A Retrospective Study

Explainable machine learning for predicting conversion to neurological disease: Results from 52,939 medical records

Objective

This study assesses the application of interpretable machine learning modeling using electronic medical record data for the prediction of conversion to neurological disease.

Methods

A retrospective dataset of Cleveland Clinic patients diagnosed with Alzheimer's disease, amyotrophic lateral sclerosis, multiple sclerosis, or Parkinson's disease, and matched controls based on age, sex, race, and ethnicity was compiled. Individualized risk prediction models were created using eXtreme Gradient Boosting for each neurological disease at four timepoints in patient history. The prediction models were assessed for transparency and fairness.

Results

At timepoints 0-months, 12-months, 24-months, and 60-months prior to diagnosis, Alzheimer's disease models achieved the area under the receiver operating characteristic curve on a holdout test dataset of 0.794, 0.742, 0.709, and 0.645; amyotrophic lateral sclerosis of 0.883, 0.710, 0.658, and 0.620; multiple sclerosis of 0.922, 0.877, 0.849, and 0.781; and Parkinson's disease of 0.809, 0.738, 0.700, and 0.651, respectively.

Conclusions

The results demonstrate that electronic medical records contain latent information that can be used for risk stratification for neurological disorders. In particular, patient-reported outcomes, sleep assessments, falls data, additional disease diagnoses, and longitudinal changes in patient health, such as weight change, are important predictors.

Postsurgical Remote Patient Monitoring Outcomes and Perceptions: A Mixed-Methods Assessment

Objective

To determine how postsurgical remote patient monitoring (RPM) influences readmissions and emergency visits within 30 days of discharge after operation and to understand patient and surgeon perspectives on postsurgical RPM.

Patients and Methods

This study was conducted at a US tertiary academic medical center between April 1, 2021, and December 31, 2021. This mixed-methods evaluation included a randomized controlled trial evaluation of RPM after operation and a qualitative assessment of patients' and surgeons' perceptions of RPM's acceptability, feasibility, and effectiveness.

Results

A total of 292 patients participated in the RPM trial, and 147 were assigned to the RPM intervention. Despite a good balance between the groups, results indicated no difference in primary or secondary outcomes between the intervention and control groups. The qualitative component included 11 patients and 9 surgeons. The overarching theme for patients was that the program brought them peace of mind. Other main themes included technological issues and perceived benefits of the RPM platform. The major themes for surgeons included identifying the best patients to receive postsurgical RPM, actionable data collection and use, and improvements in data collection needed.

Conclusion

Although quantitative results indicate no difference between the groups, postsurgical RPM appears well-accepted from the patient's perspective. However, technological issues could eliminate the benefits. Hospitals seeking to implement similar programs should carefully evaluate which populations to use the program in and seek to collect actionable data.