A monitoring framework for health care processes using Generalized Additive Models and Auto-Encoders

In recent years, there has been a considerable focus on developing effective methods for monitoring health care processes. Utilizing Statistical Process Monitoring (SPM) approaches, particularly risk-adjusted control charts, has emerged as a highly promising approach for achieving robust frameworks for this aim. Considering risk-adjusted control charts, longitudinal health care process data is typically monitored by establishing a regression relationship between various risk factors (explanatory variables) and patient outcomes (response variables). While the majority of prior research has primarily employed logistic models in risk-adjusted control charts, there are more intricate health care processes that necessitate the incorporation of both parametric and nonparametric risk factors. In such scenarios, the Generalized Additive Model (GAM) proves to be a suitable choice, albeit it often introduces higher computational complexity and associated challenges. Surprisingly, there are limited instances where researchers have proposed advancements in this direction. The primary objective of this paper is to introduce an SPM framework for monitoring health care processes using a GAM over time, coupled with a novel risk-adjusted control chart driven by machine learning techniques. This control chart is implemented on a data set encompassing two stroke types: ischemic and hemorrhagic. The key focus of this study is to monitor the stability of the relationship between stroke types and predefined explanatory variables over time within this data set. Extensive simulation results, based on real data from patients with acute stroke, demonstrate the remarkable flexibility of the proposed method in terms of its detection capabilities compared to conventional approaches.

The Incidence and Characteristics of Stroke in Urban-Dwelling Iranian Women

BACKGROUND

Population-based data regarding stroke among women are scarce in developing countries. This study was designed to determine whether sex differences exist in stroke incidence, mortality, and recurrence.

METHODS

The Mashhad Stroke Incidence Study is a population-based cohort study in Iran. For a period of 1 year, all patients with stroke in 3 geographical regions in Mashhad were recruited and then followed up for 5 years. Age- and sex-specific crude incidence rates were standardized to the World Health Organization New World Population. Male-to-female incidence rate ratios were assessed for all age groups and all subtypes of first-ever stroke (FES).

RESULTS

The annual crude incidence rate of FES (per 100,000 population) was similar in men (144; 95% confidence interval [CI]: 129-160) and women (133; 95% CI: 119-149). Standardized FES annual incidence rates were 239 (95% CI: 213-267) for men and 225 (95% CI 200-253) for women, both greater than in most western countries. There were no significant differences in stroke recurrence or case-fatality between women and men during early and long-term follow-up.

CONCLUSION

The similar incidence of stroke between men and women highlights the importance of equally prioritizing adequate preventive strategies for both sexes. The greater relative incidence of stroke in women in Mashhad compared with other countries warrants improvement of primary and secondary stroke prevention.

REMOVED: Investigating misophonia: A review of the literature, clinical implications and research agenda reflecting current neuroscience and emotion research perspectives

This article has been removed: please see Elsevier Policy on Article Withdrawal (https://www.elsevier.com/about/our-business/policies/article-withdrawal). This article has been removed at the request of the authors due to errors in the author list.