Progression and identification of heart disease risk factors in diabetic patients from electronic health records

Sharen Lee, Fung Ping Christina Leung, Wing Tak Wong, Carlin Chang, Tong Liu, Gary Tse

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

With an aging population and the increasing sedentary lifestyle, there is a rising prevalence of diabetes mellitus. The systemic nature of the disease results in high morbidity and mortality, ultimately worsening the burden of resource consumption upon the healthcare system. Cardiovascular disease is one of the major complications of diabetes mellitus, and it is a major contributing factor to the morbidity and mortality of patients with diabetes mellitus. Under progressive macrovascular and microvascular changes, major adverse cardiovascular events can manifest in both episodic and chronic manners. Acute myocardial infarction is a classical example of episodic cardiovascular complications, while heart failure and arrhythmias are common long-term sequelae in patients who suffer from metabolic syndrome.

The key to improving the prognosis of patients with diabetes mellitus in the face of cardiovascular complications is early diagnosis and intervention. Therefore, it is critical to identify the group of high-risk patients early through the use of clinical, biochemical, electrocardiographic, and echocardiographic markers. These markers are often a reflection of the risk factors that these patients possess and are correlated with the underlying pathogenesis. Therefore, when considered in combination, the use of these risk markers can illustrate the overall cardiovascular risk profile of this patient group.

With the advancement in technology, it is increasingly common for medical data to be documented as individualized electronic healthcare records to allow healthcare professionals to have a well-rounded understanding of patients' health over time. Given the holistic nature of electronic healthcare records, it is a useful source of information for the identification of prognostic markers. Since diabetes mellitus is a chronic condition, cardiovascular disease predictors can be identified through the dynamic changes in the patient condition and parameters over time, therefore facilitating the diagnosis of cardiovascular complications development early.

Original languageEnglish
Title of host publicationInternet of Things and Machine Learning for Type I and Type II Diabetes
Subtitle of host publicationUse Cases
Pages283-288
Number of pages6
ISBN (Electronic)9780323956864
DOIs
Publication statusPublished - 1 Jan 2024

Keywords

  • Atrial fibrillation
  • Cardiovascular disease
  • Diabetes mellitus
  • Electronic health records
  • Machine learning

Fingerprint

Dive into the research topics of 'Progression and identification of heart disease risk factors in diabetic patients from electronic health records'. Together they form a unique fingerprint.

Cite this