Prediction of myocardial infarction using K-medoid clustering algorithm

Umamaheswari, M.; Devi, P. Isakki

doi:10.1109/itcosp.2017.8303128

Cited by 8 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the attributes on the above criteria will increase the scope of prediction. In [11] clustering technique is used along with feature selection technique but the evaluation of the model was not provided. In this work statistical evaluation metrics were considered.…”

Section: Comparing Results Of Three Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Risk Assessment of Myocardial Infarction for Diabetics through Multi-Aspects Computing

Reddy¹,

Sethi²,

Rajender³

2020

EAI Endorsed Transactions on Pervasive Health and Technology

View full text Add to dashboard

Section: Comparing Results Of Three Algorithmsmentioning

confidence: 99%

“…In case of data without noise the values of accuracy, PPV, sensitivity and specificity obtained were 95.22%, 98.43%, 95.49% and 94.19% respectively. Umamaheswari and Isakki [11] performed k-medoid clustering technique to predict myocardial infarction. They used dataset gathered from UCI machine learning (ML) repository.…”

Section: Literature Surveymentioning

confidence: 99%

Risk Assessment of Myocardial Infarction for Diabetics through Multi-Aspects Computing

Reddy¹,

Sethi²,

Rajender³

2020

EAI Endorsed Transactions on Pervasive Health and Technology

View full text Add to dashboard

“…Clustering was performed using the K-means algorithm. The clustering results were further used to predict heart disease [32].…”

Section: Clustering Used In Healthcare Systemsmentioning

confidence: 99%

A Novel Data-Driven Adaptive Technique to Generate a Physician Visiting Schedule for Better Patient Experience

2022

View full text Add to dashboard

This paper proposes an adaptive data-driven novel technique for generating physician's schedules exploring the trade-off between physician waiting time and patient experience. Generally, in hospitals fix time slots are assigned to the patients, without differentiating patients into different categories. Some patients are referral patients who need less time, others are first-time visitors who need more time than referral patients. Some are serious patients who take even more time, so a fixed time slot can increase the waiting time both at the doctor and the patient level. So, there is a need to categorize patients according to their treatment which could help in improving the waiting time of doctors and as well of the patients. This technique trains the patient's data according to their specific category based on the time doctors usually spend on them. This can help in generating a schedule that will minimize the waiting of patients and at the same time improve the hospital performance by scheduling maximum patients ensuring that the same patient's get the best experience. To achieve this a data-driven scheduling algorithm (DDSA) is proposed which uses probability distribution, clustering and doctor's scheduling algorithm to classify patients into different categories. The data is collected through the RFID machines. The patients are given cluster head time for the treatment. Different patient categories are given different treatment times. Then patient and doctor commutative waiting times are calculated. The system applies different set-up times to allow hospital management to trade-off between doctor and patient waiting times. The average waiting time for each patient using DDSA comes out to be seven minutes. Hence, this technique can help hospitals across the globe in improving their performance and patient experience.

show abstract

“…They have used the Fuzzy C-means technique for grouping the students. Umamaheswari et al [21] proposed K-means clustering technique for Myocardial Infarction Prediction. The system discovered and extracted hidden information from historical heart disease data sets.…”

Section: Review Of Literaturementioning

confidence: 99%

A New Hybrid Hard-Fuzzy (K-Mfcm) Data Clustering Method for Finding Cluster Centroid

Jafar¹

2018

ijarcs

View full text Add to dashboard

Data mining is a collection of methods used to extract useful information from large data bases. Cluster Analysis refers to the grouping of a set of data points into clusters. Most widely used partitioning methods are K-means and Fuzzy c-means (FCM) algorithms. However, they suffer from the difficulties such as random selection of initial centre values and handling outlier data points. Most of the existing clustering methods use the Euclidean distance metric. The modified fuzzy c-means algorithm (MFCM) is efficient in handling outlier data points. In this paper, a new hybrid algorithm is proposed to solve the limitations of the traditional clustering methods. The hybrid K-MFCM algorithm is tested on four real world bench mark data sets from UCI machine learning repository with various distance metrics including Euclidean, City Block and Chessboard. The cluster centroid values of hybrid algorithm are calculated for various data sets. The experimental results show that the hybrid algorithm gives good results in terms of objective function value and better fuzzy cluster validity results for chessboard distance metric than other distance metrics.

show abstract

Prediction of myocardial infarction using K-medoid clustering algorithm

Cited by 8 publications

References 1 publication

Risk Assessment of Myocardial Infarction for Diabetics through Multi-Aspects Computing

Risk Assessment of Myocardial Infarction for Diabetics through Multi-Aspects Computing

A Novel Data-Driven Adaptive Technique to Generate a Physician Visiting Schedule for Better Patient Experience

A New Hybrid Hard-Fuzzy (K-Mfcm) Data Clustering Method for Finding Cluster Centroid

Contact Info

Product

Resources

About