Predictive Monitoring-Impact in Acute Care Cardiology Trial (PM-IMPACCT): Protocol for a Randomized Controlled Trial

Implementation of a non-intensive-care unit medical emergency team improves failure to rescue rates in cardiac surgery patients

OBJECTIVE

Failure to rescue (FTR) is an emerging measure in cardiac surgery, defined as mortality after a postoperative complication. We hypothesized that establishing a medical emergency team (MET) reduced rates of FTR in adults undergoing cardiac surgery.

METHODS

All patients (N = 11,218) undergoing a The Society of Thoracic Surgeons index operation at our center (1994-2018) were stratified by pre-MET or MET era based on the 2009 institutional implementation of a MET to respond to clinical decompensation in non-intensive-care patients. Patients missing The Society of Thoracic Surgeons predicted risk of mortality were excluded from all cohorts. Risk adjusted multivariable regression analyzed the association of postoperative complications, operative mortality, and FTR by era. Nearest neighbor propensity score matching utilizing patients' The Society of Thoracic Surgeons predicted risk of mortality was performed to create balanced control and exposure groups for secondary subgroup analysis.

RESULTS

In the risk-adjusted multivariable analysis, surgery during the MET era was associated with decreased mortality (odds ratio [OR], 0.51; 95% CI, 0.45-0.77; P < .001), postoperative renal failure (OR, 0.57; 95% CI, 0.46-0.70; P < .001), reoperation (OR, 0.75; 95% CI, 0.59-0.95; P = .017), and deep sternal wound infection (OR, 0.16; 95% CI, 0.04-0.45; P = .002). Surgery performed during the MET era was associated with a decreased rate of FTR in the risk-adjusted analysis (OR, 0.46; 95% CI, 0.34-0.70; P < .001).

CONCLUSIONS

The development of an institutional MET program was associated with a decrease in major complications and FTR. These findings support the development of MET programs to improve FTR after cardiac surgery.

Machine learning applied to electronic health record data in home healthcare: A scoping review

OBJECTIVE

Despite recent calls for home healthcare (HHC) to integrate informatics, the application of machine learning in HHC is relatively unknown. Thus, this study aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the HHC setting. Our secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model.

METHODS

During March 2022 we conducted a literature search in four databases: PubMed, Embase, CINAHL, and Scopus. Inclusion criteria were 1) describing services provided in the HHC setting, 2) applying machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) using EHR data and 4) focusing on the adult population. Predictors were mapped to the Biopsychosocial Model. A risk of bias analysis was conducted using the Prediction Model Risk Of Bias Assessment Tool.

RESULTS

The final sample included 20 studies. Eighteen studies used predictors from standardized assessments integrated in the EHR. The most common outcome of interest was hospitalization (55%), followed by mortality (25%). Psychological predictors were frequently excluded (35%). Tree based algorithms were most frequently applied (75%). Most studies demonstrated high or unclear risk of bias (75%).

CONCLUSION

Future studies in HHC should consider incorporating machine learning algorithms into clinical decision support systems to identify patients at risk. Based on the Biopsychosocial model, psychological and interpersonal characteristics should be used along with biological characteristics to enhance risk prediction. To facilitate the widespread adoption of machine learning, stakeholders should encourage standardization in the HHC setting.

Beyond prediction: Off-target uses of artificial intelligence-based predictive analytics in a learning health system

Introduction

Artificial-intelligence (AI)-based predictive analytics provide new opportunities to leverage rich sources of continuous data to improve patient care through early warning of the risk of clinical deterioration and improved situational awareness.Part of the success of predictive analytic implementation relies on integration of the analytic within complex clinical workflows. Pharmaceutical interventions have off-target uses where a drug indication has not been formally studied for a different indication but has potential for clinical benefit. An analog has not been described in the context of AI-based predictive analytics, that is, when a predictive analytic has been trained on one outcome of interest but is used for additional applications in clinical practice.

Methods

In this manuscript we present three clinical vignettes describing off-target use of AI-based predictive analytics that evolved organically through real-world practice.

Results

Off-target uses included:real-time feedback about treatment effectiveness, indication of readiness to discharge, and indication of the acuity of a hospital unit.

Conclusion

Such practice fits well with the learning health system goals to continuously integrate data and experience to provide.