Limits...
H2RM: A Hybrid Rough Set Reasoning Model for Prediction and Management of Diabetes Mellitus.

Ali R, Hussain J, Siddiqi MH, Hussain M, Lee S - Sensors (Basel) (2015)

Bottom Line: Diabetes is a chronic disease characterized by high blood glucose level that results either from a deficiency of insulin produced by the body, or the body's resistance to the effects of insulin.Correlation-based trend analysis techniques are used to manage diabetic observations.Experimental results demonstrate that the proposed model outperforms the existing methods with 95.9% average and balanced accuracies.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Kyung Hee University, Seocheon-dong, Giheung-gu Yongin-si, Gyeonggi-do 446-701, Korea. rahmanali@oslab.khu.ac.kr.

ABSTRACT
Diabetes is a chronic disease characterized by high blood glucose level that results either from a deficiency of insulin produced by the body, or the body's resistance to the effects of insulin. Accurate and precise reasoning and prediction models greatly help physicians to improve diagnosis, prognosis and treatment procedures of different diseases. Though numerous models have been proposed to solve issues of diagnosis and management of diabetes, they have the following drawbacks: (1) restricted one type of diabetes; (2) lack understandability and explanatory power of the techniques and decision; (3) limited either to prediction purpose or management over the structured contents; and (4) lack competence for dimensionality and vagueness of patient's data. To overcome these issues, this paper proposes a novel hybrid rough set reasoning model (H2RM) that resolves problems of inaccurate prediction and management of type-1 diabetes mellitus (T1DM) and type-2 diabetes mellitus (T2DM). For verification of the proposed model, experimental data from fifty patients, acquired from a local hospital in semi-structured format, is used. First, the data is transformed into structured format and then used for mining prediction rules. Rough set theory (RST) based techniques and algorithms are used to mine the prediction rules. During the online execution phase of the model, these rules are used to predict T1DM and T2DM for new patients. Furthermore, the proposed model assists physicians to manage diabetes using knowledge extracted from online diabetes guidelines. Correlation-based trend analysis techniques are used to manage diabetic observations. Experimental results demonstrate that the proposed model outperforms the existing methods with 95.9% average and balanced accuracies.

No MeSH data available.


Related in: MedlinePlus

Correlation-based trend analysis for prognosis of diabetes mellitus. The bold-faced blue line represents scatterd line graph of the current observations, the dotted black line shows future polynomial trendline for future prediction and the light orange strap represents normal ranges of the observations.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541861&req=5

sensors-15-15921-f004: Correlation-based trend analysis for prognosis of diabetes mellitus. The bold-faced blue line represents scatterd line graph of the current observations, the dotted black line shows future polynomial trendline for future prediction and the light orange strap represents normal ranges of the observations.

Mentions: Correlation analysis is one of the important future trends prediction technique applied to numeric data [61]. We adopt this technique in our study for analyzing abnormal trends in patient observations. For correlation and trend analysis, we used MS Excel [62] as our experimentation tool. In the knowledge execution flow of H2RM, when a registered patient visits the hospital for follow-up, his observations are recorded and scattered line graphs is drawn for the current and past observations, as shown in Figure 4a–k. It is represented by the bold-faced blue line in the graph. Furthermore, a correlation-based polynomial trendline of order 3 is added to the graph to predict future trend of the observation. We also compute residue R2 value to the trendline to show accuracy of the future prediction for new encounters. The selection of polynomial trendline for future prediction is due to the fact that clinical values, always, gradually fluctuate rather than move sharply. Polynomial trendlines with order 3 have two peaks or bottom values in the regression equation.


H2RM: A Hybrid Rough Set Reasoning Model for Prediction and Management of Diabetes Mellitus.

Ali R, Hussain J, Siddiqi MH, Hussain M, Lee S - Sensors (Basel) (2015)

Correlation-based trend analysis for prognosis of diabetes mellitus. The bold-faced blue line represents scatterd line graph of the current observations, the dotted black line shows future polynomial trendline for future prediction and the light orange strap represents normal ranges of the observations.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541861&req=5

sensors-15-15921-f004: Correlation-based trend analysis for prognosis of diabetes mellitus. The bold-faced blue line represents scatterd line graph of the current observations, the dotted black line shows future polynomial trendline for future prediction and the light orange strap represents normal ranges of the observations.
Mentions: Correlation analysis is one of the important future trends prediction technique applied to numeric data [61]. We adopt this technique in our study for analyzing abnormal trends in patient observations. For correlation and trend analysis, we used MS Excel [62] as our experimentation tool. In the knowledge execution flow of H2RM, when a registered patient visits the hospital for follow-up, his observations are recorded and scattered line graphs is drawn for the current and past observations, as shown in Figure 4a–k. It is represented by the bold-faced blue line in the graph. Furthermore, a correlation-based polynomial trendline of order 3 is added to the graph to predict future trend of the observation. We also compute residue R2 value to the trendline to show accuracy of the future prediction for new encounters. The selection of polynomial trendline for future prediction is due to the fact that clinical values, always, gradually fluctuate rather than move sharply. Polynomial trendlines with order 3 have two peaks or bottom values in the regression equation.

Bottom Line: Diabetes is a chronic disease characterized by high blood glucose level that results either from a deficiency of insulin produced by the body, or the body's resistance to the effects of insulin.Correlation-based trend analysis techniques are used to manage diabetic observations.Experimental results demonstrate that the proposed model outperforms the existing methods with 95.9% average and balanced accuracies.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Kyung Hee University, Seocheon-dong, Giheung-gu Yongin-si, Gyeonggi-do 446-701, Korea. rahmanali@oslab.khu.ac.kr.

ABSTRACT
Diabetes is a chronic disease characterized by high blood glucose level that results either from a deficiency of insulin produced by the body, or the body's resistance to the effects of insulin. Accurate and precise reasoning and prediction models greatly help physicians to improve diagnosis, prognosis and treatment procedures of different diseases. Though numerous models have been proposed to solve issues of diagnosis and management of diabetes, they have the following drawbacks: (1) restricted one type of diabetes; (2) lack understandability and explanatory power of the techniques and decision; (3) limited either to prediction purpose or management over the structured contents; and (4) lack competence for dimensionality and vagueness of patient's data. To overcome these issues, this paper proposes a novel hybrid rough set reasoning model (H2RM) that resolves problems of inaccurate prediction and management of type-1 diabetes mellitus (T1DM) and type-2 diabetes mellitus (T2DM). For verification of the proposed model, experimental data from fifty patients, acquired from a local hospital in semi-structured format, is used. First, the data is transformed into structured format and then used for mining prediction rules. Rough set theory (RST) based techniques and algorithms are used to mine the prediction rules. During the online execution phase of the model, these rules are used to predict T1DM and T2DM for new patients. Furthermore, the proposed model assists physicians to manage diabetes using knowledge extracted from online diabetes guidelines. Correlation-based trend analysis techniques are used to manage diabetic observations. Experimental results demonstrate that the proposed model outperforms the existing methods with 95.9% average and balanced accuracies.

No MeSH data available.


Related in: MedlinePlus