Table 1 Empirical Analysis of diseases prediction in healthcare system
From: Toward a smart health: big data analytics and IoT for real-time miscarriage prediction
References | Outcomes | Methods | Real-time Dataset | Advantages | Disadvantages |
|---|---|---|---|---|---|
[25] | Heart disease | j48, Naïve Bayes, REPTREE and CART | No | -Result shows that prediction accuracy is 99% -j48, REPTREE, and CART gave a prediction model of 89 cases with a risk factor positive for heart attacks | Tasks like heart attack still complex to predict |
[26] | Chronic disease | Fog Computing | Yes Sensors | -Monitor patients suffering from chronic diseases -Big number of data -Sort out context-sensitive data | not readily available software and complexity of the architecture |
[27] | Prognosis of coma | ARIMA Autoregressive integrated moving average | No electroencephalogram dataset | -Early prognosis -The use of biological signals and context data -The use of the response loop | Not suitable for real-time dataset |
[16] | Breast Cancer Prediction | C4.5, Naïve Bayes,SVM and K-NN | No Wisconsin Breast Cancer Dataset | -A comparison of four machine learning algorithms -The highest accuracy a xchieved is 97,13% using SVM | Small dataset |
[17] | Breast Cancer Prediction | C4.5, Naïve Bayes,SVM and K-NN | No Wisconsin Breast Cancer Dataset | -Hybrid Model using the fusion of SVM, NB and C4.5 -The highest accuracy Achieved is 97,31% | Small dataset |
[7] | Miscarriage Prediction | K-means centroid clustering | Yes Healthcare sensors Mobile phone | -An E-monitoring system -The use of IoT and Predictive analytics -Doctors and patients are involved in the treatment of the disease | More factors need to be included |
[23] | Miscarriage Prediction | Prospective register based study | No Data from Registration | -Evaluate dependency between miscarriage, maternal age and miscarriage recurrence | A focused number of Pregnant women |
[19] | Location prediction | Proposed model | No History of trajectories | -The use of mobile user covered by a personal communication systems network | Not applicable on new cases |
[28] | Medical Emergency Response | Proposed Model | Yes IoT sensors | -The capability of processing WBAN sensory data from multiple users -Real–time responses in case of emergencies | Security and privacy must be highlighted to avoid any ethical issues |