A Novel Deep Learning Approach for Forecasting Myocardial Infarction Occurrences with Time Series Patient Data
Mohammad Saiduzzaman Sayed1, Mohammad Abu Tareq Rony2, Mohammad Shariful Islam3
1Department of Statistics, Jahangirnagar University, Dhaka, Bangladesh.
Insights
This study introduces a novel deep learning model, MSC-LSTM, to accurately forecast Myocardial Infarction (MI) incidence. Early prediction of heart attacks in Chittagong aids public health planning and prevention strategies.
Area of Science:
- Cardiology and Public Health
- Artificial Intelligence in Healthcare
- Time Series Forecasting
Background:
- Myocardial Infarction (MI) is a critical global health issue, with significant impact in the Chittagong Metropolitan Area.
- Challenges in MI prevention and treatment are exacerbated by an aging population and complex healthcare demands.
- Early warning systems are vital for timely epidemic management and resource allocation.
Purpose of the Study:
- To develop and evaluate a deep learning model for early forecasting of Myocardial Infarction incidence.
- To predict the prevalence of heart attacks using a novel dataset from the Chittagong Metropolitan Area.
- To improve public health strategies through accurate MI prediction.
Main Methods:
- Utilized a novel dataset of daily heart attack incidence Time Series Patient Data (January 2020 - December 2021).
- Compared traditional models (ARIMA, ETS, TBATS) and LSTM with a proposed Myocardial Sequence Classification (MSC)-LSTM model.
- Employed deep learning techniques for time series analysis and prediction.
Main Results:
- The novel MSC-LSTM model demonstrated superior performance in forecasting MI incidence.
- Achieved a minimum Mean Percentage Error (MPE) of 1.6477, outperforming other evaluated models.
- The model provides accurate predictions for future heart attack occurrences.
Conclusions:
- The MSC-LSTM model offers a promising tool for early detection and prediction of Myocardial Infarction.
- Accurate MI forecasting supports enhanced resource allocation, policy development, and public health preparedness.
- This research contributes to proactive management of heart attack burden in the Chittagong Metropolitan Area and beyond.
Abstract:
Myocardial Infarction (MI) commonly referred to as a heart attack, results from the abrupt obstruction of blood supply to a section of the heart muscle, leading to the deterioration or death of the affected tissue due to a lack of oxygen. MI, poses a significant public health concern worldwide, particularly affecting the citizens of the Chittagong Metropolitan Area. The challenges lie in both prevention and treatment, as the emergence of MI has inflicted considerable suffering among residents. Early warning systems are crucial for managing epidemics promptly, especially given the escalating disease burden in older populations and the complexities of assessing present and future demands. The primary objective of this study is to forecast MI incidence early using a deep learning model, predicting the prevalence of heart attacks in patients. Our approach involves a novel dataset collected from daily heart attack incidence Time Series Patient Data spanning January 1, 2020, to December 31, 2021, in the Chittagong Metropolitan Area. Initially, we applied various advanced models, including Autoregressive Integrated Moving Average (ARIMA), Error-Trend-Seasonal (ETS), Trigonometric seasonality, Box-Cox transformation, ARMA errors, Trend and Seasonal (TBATS), and Long Short Time Memory (LSTM). To enhance prediction accuracy, we propose a novel Myocardial Sequence Classification (MSC)-LSTM method tailored to forecast heart attack occurrences in patients using the newly collected data from the Chittagong Metropolitan Area. Comprehensive results comparisons reveal that the novel MSC-LSTM model outperforms other applied models in terms of performance, achieving a minimum Mean Percentage Error (MPE) score of 1.6477. This research aids in predicting the likely future course of heart attack occurrences, facilitating the development of thorough plans for future preventive measures. The forecasting of MI occurrences contributes to effective resource allocation, capacity planning, policy creation, budgeting, public awareness, research identification, quality improvement, and disaster preparedness.
