Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR mHealth and uHealth

Date Submitted: Aug 19, 2018
Open Peer Review Period: Aug 22, 2018 - Oct 14, 2018
Date Accepted: Mar 24, 2019
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

A Noninvasive, Economical, and Instant-Result Method to Diagnose and Monitor Type 2 Diabetes Using Pulse Wave: Case-Control Study

Hao Y, Cheng F, Pham M, Rein H, Patel D, Fang Y, Feng Y, Yan J, Song X, Yan H, Wang Y

A Noninvasive, Economical, and Instant-Result Method to Diagnose and Monitor Type 2 Diabetes Using Pulse Wave: Case-Control Study

JMIR Mhealth Uhealth 2019;7(4):e11959

DOI: 10.2196/11959

PMID: 31012863

PMCID: 6658300

A Noninvasive, Economical, and Instant-Result Method to Diagnose and Monitor Type 2 Diabetes Using Pulse Wave

  • Yiming Hao; 
  • Feng Cheng; 
  • Minh Pham; 
  • Hayley Rein; 
  • Devashru Patel; 
  • Yuchen Fang; 
  • Yiyi Feng; 
  • Jin Yan; 
  • Xueyang Song; 
  • Haixia Yan; 
  • Yiqin Wang

ABSTRACT

Background:

We should pay more attention to the long-term monitoring and early warning of type 2 diabetes and its complications. The traditional blood glucose tests are traumatic and cannot effectively monitor the development of diabetic complications. The development of mobile medical is changing rapidly. Therefore, we are interested in developing one new noninvasive, economical, and instant-result method to accurately diagnose and monitor type 2 diabetes and its complications.

Objective:

We sought to determine whether type 2 diabetes and its complications including hypertension and hyperlipidemia could be diagnosed and monitored by using pulse wave.

Methods:

We collected the pulse wave parameters from 50 healthy people, 139 diabetic patients without hypertension and hyperlipidemia, 133 diabetic patients with hypertension, 70 diabetic patients with hyperlipidemia, and 75 diabetic patients with hypertension and hyperlipidemia. The pulse wave parameters showing significant differences among these groups were identified. Various machine learning models such as Linear Discriminant Analysis, Support Vector Machines (SVM), and Random Forests were applied to classify control group, diabetic patients and diabetic patients with complications.

Results:

There were significant differences in several pulse wave parameters among the five groups. Parameters h3, t1, and W increase and h5 decreases when people develop diabetes. Parameter h1, h3, and h4 are found to be higher in diabetes with hypertension while h5 is lower in diabetes with hyperlipidemia. For detecting diabetes, the method with the highest out-of-sample prediction accuracy is SVM with polynomial kernel. The algorithm can detect diabetes with 96.35% accuracy. However, all the algorithms have low accuracy when predicting diabetic patients with hypertension and hyperlipidemia (below 70%).

Conclusions:

The results demonstrated that the noninvasive and convenient pulse-taking diagnosis described in this paper has the potential to become a low-cost and accurate method to monitor the development of diabetes. We are collecting more data in order to improve the accuracy for detecting hypertension and hyperlipidemia among diabetic patients. Mobile devices such as sport bands, smart watches, and other diagnosis tools are being developed based on the pulse wave method to improve the diagnosis and monitoring of diabetes, hypertension, and hyperlipidemia.


 Citation

Please cite as:

Hao Y, Cheng F, Pham M, Rein H, Patel D, Fang Y, Feng Y, Yan J, Song X, Yan H, Wang Y

A Noninvasive, Economical, and Instant-Result Method to Diagnose and Monitor Type 2 Diabetes Using Pulse Wave: Case-Control Study

JMIR Mhealth Uhealth 2019;7(4):e11959

DOI: 10.2196/11959

PMID: 31012863

PMCID: 6658300

Per the author's request the PDF is not available.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.