Correction: Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis

[This corrects the article DOI: 10.2196/52782.].

Assessing the impact of haemodynamic monitoring with CardioMEMS on heart failure patients: a cost-benefit analysis

AIMS

The objective of this study was to perform a cost-benefit analysis of the CardioMEMS HF System (Abbott Laboratories, Abbott Park, IL, USA) in a heart failure (HF) clinic in Spain by evaluating the real-time remote monitoring of pulmonary artery pressures, which has been shown to reduce HF-related hospitalizations and improve the quality of life for selected HF patients. Particularly, the study aimed to determine the value of CardioMEMS in Southern Europe, where healthcare costs are significantly lower and its effectiveness remains uncertain.

METHODS AND RESULTS

This single-centre study enrolled all consecutive HF patients (N = 43) who had been implanted with a pulmonary artery pressure sensor (CardioMEMS HF System); 48.8% were females, aged 75.5 ± 7.0 years, with both reduced and preserved left ventricular ejection fraction; 67.4% of them were in New York Heart Association Class III. The number of HF hospitalizations in the year before and the year after the sensor implantation was compared. Quality-adjusted life years gained based on a literature review of previous studies were calculated. The rate of HF hospitalizations was significantly lower at 1 year compared with the year before CardioMEMS implantation (0.25 vs. 1.10 events/patient-year, hazard ratio 0.22, P = 0.001). At the end of the first year, the usual management outperformed the CardioMEMS HF System. By the end of the second year, the CardioMEMS system is estimated to reduce costs compared with usual management (net benefits of €346).

CONCLUSIONS

Based on the results, we suggest that remote monitoring of pulmonary artery pressure with the CardioMEMS HF System represents a midterm and long-term efficient strategy in a healthcare setting in Southern Europe.

Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis

Background

The health care system is undergoing a shift toward a more patient-centered approach for individuals with chronic and complex conditions, which presents a series of challenges, such as predicting hospital needs and optimizing resources. At the same time, the exponential increase in health data availability has made it possible to apply advanced statistics and artificial intelligence techniques to develop decision-support systems and improve resource planning, diagnosis, and patient screening. These methods are key to automating the analysis of large volumes of medical data and reducing professional workloads.

Objective

This article aims to present a machine learning model and a case study in a cohort of patients with highly complex conditions. The object was to predict mortality within the following 4 years and early mortality over 6 months following diagnosis. The method used easily accessible variables and health care resource utilization information.

Methods

A classification algorithm was selected among 6 models implemented and evaluated using a stratified cross-validation strategy with k=10 and a 70/30 train-test split. The evaluation metrics used included accuracy, recall, precision, F1-score, and area under the receiver operating characteristic (AUROC) curve.

Results

The model predicted patient death with an 87% accuracy, recall of 87%, precision of 82%, F1-score of 84%, and area under the curve (AUC) of 0.88 using the best model, the Extreme Gradient Boosting (XGBoost) classifier. The results were worse when predicting premature deaths (following 6 months) with an 83% accuracy (recall=55%, precision=64% F1-score=57%, and AUC=0.88) using the Gradient Boosting (GRBoost) classifier.

Conclusions

This study showcases encouraging outcomes in forecasting mortality among patients with intricate and persistent health conditions. The employed variables are conveniently accessible, and the incorporation of health care resource utilization information of the patient, which has not been employed by current state-of-the-art approaches, displays promising predictive power. The proposed prediction model is designed to efficiently identify cases that need customized care and proactively anticipate the demand for critical resources by health care providers.

CauRuler: Causal irredundant association rule miner for complex patient trajectory modelling

BACKGROUND AND OBJECTIVES

Discovering causal associations between variables is one of the main goals of clinical trials, with the ultimate aim of identifying the causes of specific health status. Prior knowledge of causal paths could help ensure patients do not develop the resultant conditions. In recent years, thanks to the enormous amount of health data stored with the support of digital tools, attempts have been made to employ Machine Learning to infer causality. Those methodologies suffer from some deficiencies in controlling cofounders when analysing causality, as well as providing causal rules general enough to be useful in healthcare practice. Conversely, this work presents and evaluates CauRuler, a new approach to deal with causality from association rules. The proposed approach uses a pruning strategy to reduce the association rule set, which does not compromise the causality learning capability of the algorithm. This behaviour makes the algorithm suitable for exploiting large health databases with thousands of patients and medical instances. CauRuler can control a larger number of confounders than other proposals, bringing robustness to causal analysis and avoiding the identification of spurious associations. Additionally, the method generalizes causality using anti-monotone properties to obtain complex and general causal paths. The method can target correct causal associations in complex medical databases with retrospective data.

METHOD

CauRuler extends association rule mining with an irredundancy property so that the set of rules learnt is reduced in size and generalized. General association rules, conformed by fewer items, enable controlling more confounding variables to verify, with more statistical evidence on available data, if they represent causal paths in patient disease trajectories.

RESULTS

CauRuler has been tested on a complex real medical database (3,5 M visits to the primary care services between 2019 and 2020, and controlling over 15.000 different variables including diagnoses and demographic and other clinical patient data). The reduction of the rule set achieved by the pruning strategy goes from 7.732 to 2.240 rules, from which 46 have been found to have causality relationships in the patient trajectories, and generalized to 14 rules tested as true causal relationships thanks to the confounding analysis. These rules have been validated by clinicians with the support of a graphical map. The obtained causal paths control in average of 906 confounder variables, retrieving robust results.

CONCLUSIONS

Causal relationships enable predicting causal paths between health conditions according to patient trajectories. Knowing these causal paths is crucial for understanding and preventing the appearance or worsening of diseases in patients. CauRuler, with high demanding thresholds, has proven its efficiency and effectiveness in targeting previously known causal associations between diagnoses, reaching consensus in the medical community. Softening these thresholds should help target interesting general causal paths.

Impact of Mass Workplace COVID-19 Rapid Testing on Health and Healthcare Resource Savings

Background: The epidemiological situation generated by COVID-19 has cast into sharp relief the delicate balance between public health priorities and the economy, with businesses obliged to toe the line between employee health and continued production. In an effort to detect as many cases as possible, isolate contacts, cut transmission chains, and limit the spread of the virus in the workplace, mass testing strategies have been implemented in both public health and industrial contexts to minimize the risk of disruption in activity. Objective: To evaluate the economic impact of the mass workplace testing strategy as carried out by a large automotive company in Catalonia in terms of health and healthcare resource savings. Methodology: Analysis of health costs and impacts based on the estimation of the mortality and morbidity avoided because of screening, and the resulting savings in healthcare costs. Results: The economic impact of the mass workplace testing strategies (using both PCR and RAT tests) was approximately €10.44 per test performed or €5575.49 per positive detected; 38% of this figure corresponds to savings derived from better use of health resources (hospital beds, ICU beds, and follow-up of infected cases), while the remaining 62% corresponds to improved health rates due to the avoided morbidity and mortality. In scenarios with higher positivity rates and a greater impact of the infection on health and the use of health resources, these results could be up to ten times higher (€130.24 per test performed or €69,565.59 per positive detected). Conclusion: In the context of COVID-19, preventive actions carried out by the private sector to safeguard industrial production also have concomitant public benefits in the form of savings in healthcare costs. Thus, governmental bodies need to recognize the value of implementing such strategies in private settings and facilitate them through, for example, subsidies.

A Cost-Benefit Analysis of the COVID-19 Asymptomatic Mass Testing Strategy in the North Metropolitan Area of Barcelona

BACKGROUND

The epidemiological situation generated by COVID-19 has highlighted the importance of applying non-pharmacological measures in the management of the epidemic. Mass screening of the asymptomatic general population has been established as a priority strategy by carrying out diagnostic tests to detect possible cases, isolate contacts, cut transmission chains and thus limit the spread of the virus.

OBJECTIVE

To evaluate the economic impact of mass COVID-19 screenings of an asymptomatic population during the first and second wave of the epidemic in Catalonia, Spain.

METHODOLOGY

Cost-Benefit Analysis based on the estimated total costs of mass screening versus health gains and associated health costs avoided.

RESULTS

Excluding the value of monetized health, the Benefit-Cost ratio was estimated at 0.45, a low value that would seem to advise against mass screening policies. However, if monetized health is included, the ratio is close to 1.20, reversing the interpretation. In other words, the monetization of health is the critical element that tips the scales in favour of the desirability of screening. Results show that the interventions with the highest return are those that maximize the percentage of positives detected.

CONCLUSION

Efficient management of resources for the policy of mass screening in asymptomatic populations can generate high social returns. The positivity rate critically determines its desirability. Likewise, precocity in the detection of cases will cut more transmissions in the chain of contagion and increase the economic return of these interventions. Maximizing the value of resources depends on screening strategies being accompanied by contact-tracing and specific in their focus, targeting, for example, high-risk subpopulations with the highest rate of expected positives.