This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR mHealth and uHealth, is properly cited. The complete bibliographic information, a link to the original publication on http://mhealth.jmir.org/, as well as this copyright and license information must be included.
Carpal tunnel syndrome (CTS) is a medical condition caused by compression of the median nerve in the carpal tunnel due to aging or overuse of the hand. The symptoms include numbness of the fingers and atrophy of the thenar muscle. Thenar atrophy recovers slowly postoperatively; therefore, early diagnosis and surgery are important. While physical examinations and nerve conduction studies are used to diagnose CTS, problems with the diagnostic ability and equipment, respectively, exist. Despite research on a CTS-screening app that uses a tablet and machine learning, problems with the usage rate of tablets and data collection for machine learning remain.
To make data collection for machine learning easier and more available, we developed a screening app for CTS using a smartphone and an anomaly detection algorithm, aiming to examine our system as a useful screening tool for CTS.
In total, 36 participants were recruited, comprising 36 hands with CTS and 27 hands without CTS. Participants controlled the character in our app using their thumbs. We recorded the position of the thumbs and time; generated screening models that classified CTS and non-CTS using anomaly detection and an autoencoder; and calculated the sensitivity, specificity, and area under the curve (AUC).
Participants with and without CTS were classified with 94% sensitivity, 67% specificity, and an AUC of 0.86. When dividing the data by direction, the model with data in the same direction as the thumb opposition had the highest AUC of 0.99, 92% sensitivity, and 100% specificity.
Our app could reveal the difficulty of thumb opposition for patients with CTS and screen for CTS with high sensitivity and specificity. The app is highly accessible because of the use of smartphones and can be easily enhanced by anomaly detection.
Carpal tunnel syndrome (CTS) is a medical condition caused by compression of the median nerve in the carpal tunnel due to aging or hand overuse [
Physical findings, such as the Tinel sign or Phalen test, may be used; however, their sensitivity and specificity are not high [
In recent years, cameras and sensors in mobile devices have become smaller and more sophisticated and can now measure the state of the user. Various studies have been conducted on the use of mobile devices to acquire physical information and diagnose diseases [
To address these concerns, we developed a screening app for CTS using a smartphone and an anomaly detection algorithm [
This study was approved by the Institutional Review Board of Tokyo Medical and Dental University. Written informed consent was provided by all participants.
We recruited 21 preoperative patients (36 hands) with CTS at the Tokyo Medical and Dental University Hospital as the CTS group and 15 healthy volunteers (27 hands) at an osteopathic clinic as the non-CTS group from July 2018 to May 2019. Experienced hand surgeons diagnosed CTS based on symptoms, physical findings such as the Tinel sign and Phalen test, x-ray images of the hands, and NCSs measured by Neuropack X1 (Nihon Kohden). Patients were classified based on the Bland classification [
We used a Huawei P10 Lite (Huawei Technologies) phone and developed the app using Unity software (Unity Technologies). We also created a finger guide, which was attached to the back of the smartphone to fix the position of the fingers other than the thumb (
A finger guide attached to the back of the smartphone to fix the position of the fingers other than the thumb.
In this app, the player controlled a rabbit character with their thumb and collected vegetables (carrots, radishes, or eggplants) that appeared on the screen (screen A in
The images of the app. A rabbit character and vegetables were displayed in the green circle. Vegetables were located at the center or edge of the circle, and markers were also displayed when the vegetables were located at the edge (A). Vegetables appeared in 12 numbered directions, and the numbers were reversed depending on whether the player used the left (B) or right (C) hand.
The images of the app while playing the game. The player touched and controlled a rabbit character with the thumb of each hand to collect vegetables. Vegetables appeared in one of 12 directions (A). When each vegetable was collected, the next appeared alternately at the center of the circle (B) or in another direction (C).
We used 2-tailed Student
To generate a screening model that classified participants as CTS and non-CTS, we analyzed data sets using anomaly detection and an autoencoder (AE) [
An image demonstrating how the autoencoder works. In our model, the input layer was 600 dimensions, the intermediate layer was 10 dimensions, and the output layer was 600 dimensions.
First, we calculated the distance to the center of the screen from the coordinate data and converted this into a value from 0 to 1. In our proposed model, the first lap was only played as practice for the participants to get used to the app, and only the second-lap data were used for the analysis. Next, a grayscale image was generated by arranging the pixel values with the vertical axis set as each direction and the horizontal axis set as time (
Grayscale image generated by the pixel values with the vertical axis set as each direction and the horizontal axis set as time. The intensity of the pixel was defined by the distance between the thumb and the center; the greater the distance, the lighter the intensity. Pixels of the frames when the thumb reached the circumference (vegetables) were white, and all pixels to the right of the frames were set to be filled with black. The vertical axis was set as 12 directions and the horizontal axis was set at a fixed time (50 frames).
We used the data from 12 hands in the non-CTS group for the training of the AE and validated them with the data from the 36 hands in the CTS group and 15 hands in the non-CTS group that were not used for the training. The reconstruction error of the AE was calculated using the mean square error of the difference between the input and output. By training the AE on non-CTS data only, we could detect patients with CTS because the reconstruction error was smaller for non-CTS data and larger for CTS data. We generated a receiver operating characteristic (ROC) curve by adjusting the cutoff value of the mean square error and calculated the area under the curve (AUC). The optimal cutoff value was set at the point where the Youden index was at its maximum in the ROC curve. Furthermore, to investigate which directional movements contribute to the diagnosis of CTS, we also generated modified screening models that classified CTS and non-CTS using data from only 4 consecutive directions of the 12 directions and calculated the AUC in the same way as above.
The characteristics of the participants are summarized in
Characteristics of participants in the CTS and non-CTS groups.
Characteristic | Non-CTSa | CTS | ||
Participants, n | 15 | 21 | N/Ab | |
Age (years), mean (SD) | 63.5 (17.6) | 64.3 (12.2) | .87 | |
Sex (female), n | 12 | 16 | .63 | |
Hand dominance (right), n | 15 | 21 | >.99 | |
Hands, n | 27 | 36 | N/A | |
Side (right), n | 15 | 17 | .69 | |
|
N/A | |||
Grade 1 | N/A | 5 | ||
Grade 2 | N/A | 6 | ||
Grade 3 | N/A | 15 | ||
Grade 4 | N/A | 0 | ||
Grade 5 | N/A | 9 | ||
Grade 6 | N/A | 1 |
aCTS: carpal tunnel syndrome.
bN/A: not applicable.
Representation of the average time taken to collect vegetables (A) and the average (B) and maximum (C) velocities in each direction.
The results of the screening model are shown in
The result of the screening model. People with and without CTS were classified with 94% sensitivity and 67% specificity.
True label | Predicted label, n | |
Non-CTSa | CTS | |
Non-CTS | 10 | 5 |
CTS | 2 | 34 |
aCTS: carpal tunnel syndrome.
ROC curve of the screening model. The area under the ROC curve was 0.86. The black point indicates the optimal cutoff value, and the sensitivity and specificity at that point were 0.94 and 0.67, respectively. ROC: receiver operating characteristic.
The results of the modified screening models are shown in
The index of the modified screening models.
Directiona | Sensitivity, % | Specificity, % | AUCb |
1-4 | 78 | 73 | 0.85 |
2-5 | 89 | 93 | 0.96 |
3-6 | 83 | 80 | 0.87 |
4-7 | 100 | 87 | 0.92 |
5-8 | 94 | 73 | 0.86 |
6-9 | 89 | 80 | 0.86 |
7-10 | 86 | 87 | 0.92 |
8-11 | 92 | 100 | 0.99 |
9-12 | 92 | 100 | 0.98 |
10-1 | 92 | 87 | 0.94 |
11-2 | 92 | 80 | 0.86 |
12-3 | 73 | 73 | 0.79 |
aDirections are based on screens B and C of
bAUC: area under the curve.
In this study, we developed a smartphone app with a high ability to screen for CTS. The app could diagnose CTS with 94% sensitivity and 67% specificity and was almost equal to a tablet app in a previous study, which diagnosed CTS with 93% sensitivity and 73% specificity [
In the modified screening models, the model using data from directions 8 to 11 had the highest AUC of 0.99 and could diagnose CTS with 92% sensitivity and 100% specificity; this was better than the screening model that used data in all directions. This result suggests that thumb movement from directions 8 to 11 is different between the CTS and non-CTS groups, contributing to the diagnosis of CTS. Reaching directions 8 to 11 requires a movement similar to thumb opposition, as in screen B of
We used a similar app as in the previous study [
This study has some limitations. First, the varied sizes of the participants’ hands were not considered. Healthy people with small hands who struggled to reach each direction may have been misdiagnosed with CTS. Second, because smartphone sizes vary, the level of difficulty depends on the model. Therefore, it is desirable to adjust the size of the circle in the game before playing according to the size of each player's fingers and the smartphone. Third, we used an inexpensive finger guide on the back of the smartphone to fix the hand. If special equipment is required, few people will be able to use our system. It would be better to use readily available equipment, such as fall prevention devices for smartphones, instead. Fourth, while we obtained good results in this study, there is still room for further improvement in machine learning. In order to take advantage of anomaly detection, it is desirable to collect more samples. Finally, our system diagnosed only the presence of CTS. In future work, we will improve our system by collecting more data sets to enable estimation of the severity of CTS.
We developed an app for screening patients with CTS that revealed the difficulty of thumb opposition for patients with CTS and could screen for CTS with high sensitivity and specificity. The app can be used by many people because it is smartphone based, and the machine learning is easy to enhance using anomaly detection. In future work, we will enhance our system by collecting more data sets to enable estimation of the severity of CTS.
autoencoder
area under the curve
carpal tunnel syndrome
nerve conduction study
receiver operating characteristic
This research was supported by JST AIP-PRISM JPMJCR18Y2 and JST PRESTO JPMJPR17J4. The authors thank the staff and patients at Sajima Osteopathic Hospital.
None declared.