Machine Learning for Healthcare Applications. Группа авторов

95.8333333 97.8947368 Drink 95.5555556 97.8723404 97.8947368 98.9473684 Screen 96.7032967 97.8494624 97.826087 96.8421053 Calories 97.3494624 97.9381443 97.8494624 98.9690722

Table 2.4 Recall of the model.

Health status	Model 1	Model 2
Recall:Phase-I	Recall:Phase-II	Recall:Phase-I	Recall:Phase-II
Sleep	93.4782609	94.7368421	94.5652174	95.8333333
Smoke	95.6989247	97.8723404	97.8723404	97.8947368
Drink	93.4782609	96.8421053	97.8947368	98.9473684
Screen	95.6521739	95.7894737	95.7446809	97.8723404
Calories	95.78941737	98.9583333	96.8085106	98.9690722

Figure 2.5 Recall: Model-I vs Model-II.

Table 2.4 shows the Recall comparison between the model-1 and model-2.

Figure 2.5 shows the Recall comparison between the two models which are proposed in this chapter and it is observed the model-II gives more accuracy than the model-I.

       2.5.1.4 F1-Score

      The F1-score is the harmonic mean of precision and recall. Below equation used to calculate the F1-score.

Figure 2.6 shows the F1-score comparison between the two models which are proposed in this chapter and it is observed the model-II gives more accuracy than the model-I. Table 2.5 shows the F1-Score comparison between the model-1 and model-2.

Table 2.5 F1-score of the model.

Health status	Model 1	Model 2
F1-score:Phase-I	F1-score:Phase-II	F1-score:Phase-I	F1-score:Phase-II
Sleep	94.50549	96.25668	95.08197	96.84211
Smoke	95.69892	96.84211	96.84211	97.89474
Drink	94.50549	97.3545	97.89474	98.94737
Screen	96.17486	96.80851	96.77419	97.3545
Calories	96.80851	98.4456	97.3262	98.96907

Figure 2.6 Recall: Model-I vs Model-II.

2.6 Conclusion

      In this chapter, we have proposed an architecture based on machine learning algorithms. Basically, we focus on a challenging problem of predicting the overall health status of an individual based on their daily life activities and measures. The proposed system predicts the overall health status of a person and future diseases using machine learning techniques. To demonstrate the proposed model, we have created a web-based application. The proposed model helps the user to understand their health status by submitting their details. For training and testing we used the synthetic data, in the future we need to test the proposed model using the real data by collecting from the users. In this work, we attempted a general healthcare problem and a lot more has to be done in the future. The future work is to predict the diseases based on the overall health status estimation using the models proposed in this chapter.

References

      1. Bjartveit, K. and Tverdal, A., Health consequences of smoking 1–4 cigarettes per day. Tobacco Control, 14, 5, 315–320, 2005.

      2. Weng, C.-H., Huang, T.C.-K., Han, R.-P., Disease prediction with different types of neural network classifiers. Telematics Inf., 33, 2, 277–292, 2016.

      3. Alpaydın, E., Introduction to Machine Learning, 2nd edition, the MIT press, Cambridge, Massachusetts, 2010.

      4. Harris, J.A. and Benedict, F.G., A Biometric Study of Human Basal Metabolism. Proc. Natl. Acad. Sci. U.S.A., 4, 12, 370–373, 1918.

      5. Hirshkowitz, M., Whiton, K., Albert, S.M., Alessi, C., Bruni, O., DonCarlos, L., Hillard, P.J.A., National Sleep Foundation’s sleep time duration recommendations: Methodology and results summary. Sleep Health, 1, 1, 40–43, 2015.

6. Hung, C.-Y., Chen, W.-C., Lai, P.-T., Lin, C.-H., Lee, C.-C., Comparing deep neural network and other machine learning algorithms for stroke