Fahmida Haque1, Mamun Bin Ibne Reaz1, Muhammad Enamul Hoque Chowdhury2, Geetika Srivastava3, Sawal Hamid Md Ali1, Ahmad Ashrif A Bakar1, Mohammad Arif Sobhan Bhuiyan4. 1. Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Selangor, Malaysia. 2. Department of Electrical Engineering, Qatar University, Doha 2713, Qatar. 3. Department of Physics and Electronics, Dr. Ram Manohar Lohia Avadh University, Ayodhya 224001, India. 4. Department Electrical and Electronic Engineering, Xiamen University Malaysia, Bandar Sunsuria, Sepang 43900, Selangor, Malaysia.
Abstract
BACKGROUND: Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature. METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms. RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs. CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.
BACKGROUND:Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabeticpatients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature. METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms. RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs. CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabeticpatients.
Authors: Georgios Baskozos; Andreas C Themistocleous; Harry L Hebert; Mathilde M V Pascal; Jishi John; Brian C Callaghan; Helen Laycock; Yelena Granovsky; Geert Crombez; David Yarnitsky; Andrew S C Rice; Blair H Smith; David L H Bennett Journal: BMC Med Inform Decis Mak Date: 2022-05-29 Impact factor: 3.298
Authors: Fahmida Haque; Mamun B I Reaz; Muhammad E H Chowdhury; Serkan Kiranyaz; Sawal H M Ali; Mohammed Alhatou; Rumana Habib; Ahmad A A Bakar; Norhana Arsad; Geetika Srivastava Journal: Comput Intell Neurosci Date: 2022-04-25
Authors: Nakib Hayat Chowdhury; Mamun Bin Ibne Reaz; Fahmida Haque; Shamim Ahmad; Sawal Hamid Md Ali; Ahmad Ashrif A Bakar; Mohammad Arif Sobhan Bhuiyan Journal: Diagnostics (Basel) Date: 2021-12-03