This document summarizes a student project on predicting heart failure patient survival using machine learning algorithms. The team will predict survival based on creatinine and ejection fraction levels, using classification algorithms. They cite several references on using machine learning to predict mortality and hospitalization in heart failure patients. The document discusses challenges in developing machine learning models and addressing missing data. It explains that predicting risk and determining accuracy are benefits of using machine learning for this problem. The team aims to determine survival probability and selected this topic due to the global impact of heart failure. Future work may apply the techniques to other disease datasets.
1. SECTION: PC-I
COURSE CODE: CSE 411
SUBJECT: Computer Architecture & Organization
COURSE TEACHER: Ms. Chowdhury Abida Anjum Era
Team [1971]
Fahim Imtiaz Shawon
ID: 201-15-3172
Al- Basit
ID: 191-15-12512
KM Mehedi Hasan
ID : 201-15-13804
Predict survival by creatinine and ejection fraction in heart failure patients
using machine learning algorithms.
Md.Abul Hayat
ID : 201-15-3154
2. Reference
1. [1] Chicco, D. and Jurman, G., 2020. Machine learning can predict survival of tients with heart failure from serum creatinine
and ejection fraction alone. BMC medical informatics and decision making, 20(1), pp.1-16.
2. [2] Oladimeji, O.O. and Oladimeji, O., 2020. Predicting survival of heart failure patients using classification algorithms. JITCE
(Journal of Information Technology and Computer Engineering), 4(02), pp.90-94.
3. [3 Haque, M.E., Uddin, S., Islam, M.A., Khanom, A., Suman, A. and Paul, M., 2022. Analysis and prediction of heart stroke from
ejection fraction and serum creatinine using LSTM deep learning approach. arXiv preprint arXiv:2209.13799.
4. [4] Angraal, S., Mortazavi, B.J., Gupta, A., Khera, R., Ahmad, T., Desai, N.R., Jacoby, D.L., Masoudi, F.A., Spertus, J.A. and
Krumholz, H.M., 2020. Machine learning prediction of mortality and hospitalization in heart failure with preserved ejection
fraction. JACC: Heart Failure, 8(1), pp.12-21.
5. [5] Woolley, R.J., Ceelen, D., Ouwerkerk, W., Tromp, J., Figarska, S.M., Anker, S.D., Dickstein, K., Filippatos, G., Zannad, F., Metra,
M. and Ng, L., 2021. Machine learning based on biomarker profiles identifies distinct subgroups of heart failure with preserved
ejection fraction. European journal of heart failure, 23(6), pp.983-991.]
6. [6] Mishra, S., 2022. A Comparative Study for Time-to-Event Analysis and Survival Prediction for Heart Failure Condition using
Machine Learning Techniques. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 4(3), pp.115-134.
7. [7] Ishaq, A., Sadiq, S., Umer, M., Ullah, S., Mirjalili, S., Rupapara, V. and Nappi, M., 2021. Improving the prediction of heart
failure patients’ survival using SMOTE and effective data mining techniques. IEEE access, 9, pp.39707-39716.
3. Domain
• we used for binary survival classification ("Survival prediction
classifiers").
• The logistic regression technique we used to predict survival and
conduct feature ranking as a function of follow-up time is then
described ("Stratified logistic regression" part).
4. Why should we use Machine Learning?
•Predicting risk
•Challenges in developing a machine learning algorithm.
•Approaches to missing data.
•Accuracy can be determined.
5. Why we are selecting this topic?
Heart failure is a life-threatening disease, and its solution should be
seen as a global health priority. Heart failure remains among the
most common and morbid health conditions. In every year it
taking an estimated 17.9 million lives. An estimated 02–1 out of
every 1,000 cases of heart failure each year occur in people in their
20s. By using machine learning algorithm we will be able to
determine the survival probability of a heart attack patient
6. Future Work
In the future, we intend to apply our machine learning technique to
different datasets of cardiovascular heart disorders and other
illnesses (cervical cancer, neuroblastoma, breast cancer, and
amyotrophic lateral sclerosis).