Automated Pain Spots Recognition Algorithm Provided by a Web Service-Based Platform: Instrument Validation Study

Abstract

Background: Understanding the causes and mechanisms underlying musculoskeletal pain is crucial for developing effective treatments and improving patient outcomes. Self-report measures, such as the Pain Drawing Scale, involve individuals rating their level of pain on a scale. In this technique, individuals color the area where they experience pain, and the resulting picture is rated based on the depicted pain intensity. Analyzing pain drawings (PDs) typically involves measuring the size of the pain region. There are several studies focusing on assessing the clinical use of PDs, and now, with the introduction of digital PDs, the usability and reliability of these platforms need validation. Comparative studies between traditional and digital PDs have shown good agreement and reliability. The evolution of PD acquisition over the last 2 decades mirrors the commercialization of digital technologies. However, the pen-on-paper approach seems to be more accepted by patients, but there is currently no standardized method for scanning PDs.

Objective: The objective of this study was to evaluate the accuracy of PD analysis performed by a web platform using various digital scanners. The primary goal was to demonstrate that simple and affordable mobile devices can be used to acquire PDs without losing important information.

Methods: Two sets of PDs were generated: one with the addition of 216 colored circles and another composed of various red shapes distributed randomly on a frontal view body chart of an adult male. These drawings were then printed in color on A4 sheets, including QR codes at the corners in order to allow automatic alignment, and subsequently scanned using different devices and apps. The scanners used were flatbed scanners of different sizes and prices (professional, portable flatbed, and home printer or scanner), smartphones with varying price ranges, and 6 virtual scanner apps. The acquisitions were made under normal light conditions by the same operator.

Results: High-saturation colors, such as red, cyan, magenta, and yellow, were accurately identified by all devices. The percentage error for small, medium, and large pain spots was consistently below 20% for all devices, with smaller values associated with larger areas. In addition, a significant negative correlation was observed between the percentage of error and spot size (R=-0.237; P=.04). The proposed platform proved to be robust and reliable for acquiring paper PDs via a wide range of scanning devices.

Conclusions: This study demonstrates that a web platform can accurately analyze PDs acquired through various digital scanners. The findings support the use of simple and cost-effective mobile devices for PD acquisition without compromising the quality of data. Standardizing the scanning process using the proposed platform can contribute to more efficient and consistent PD analysis in clinical and research settings.

Keywords: accuracy; accurate; app; applications; apps; body chart; body charts; device; devices; draw; drawing; image; image processing; images; mobile phone; musculoskeletal; pain; pain drawing; picture; pictures; reliability; reliable; scale; scan; scanner; scanners; smartphone; smartphones.

Figure 1.. Pain spot detection process. (A) The 4 markers at the corners and the QR code are identified. (B) The pain drawing is aligned and scaled. (C) The areas outside the body chart are removed. (D) Pain drawings are separated from the background and eroded in order to correct the imperfections due to pen drawing. (E) Pain spot contours are identified and small holes are removed. (F) Each pain spot is analyzed to extract area and position. PS: pain spot.

Figure 2.. Representation of the artificial pain drawings generated with MATLAB. (A) A total of 216 colored circles with a 30-pixel diameter were randomly located within the area of the body chart. The colors were uniformly distributed in the RGB color cube. (B) Five body charts with randomly generated shapes. RGB: red, green, and blue.

Figure 3.. Examples of identification of pain spots from colored circles. (A) The original drawing and the output of the platform algorithm for 3 different devices are shown. The green color represents an identified pain spot. The purple circle on the bottom left corner (indicated with the thick arrow) was not identified by the iPhone (D) and Sharp scanner (B), but it was identified by the Armor phone (C). The black circle on the neck (indicated with the thin arrow) was not identified by any of the devices.

Figure 4.. Representation of the performance of the algorithm in identifying different color circles. The middle diagonal (from white to black where RGB components are equal) and the colors located close to the central diagonal are not identified by the algorithm, while colors such as red, magenta, and yellow are identified by all devices. RGB: red, green, and blue.

Figure 5.. Representation of the distribution of shapes according to their size. The 3 colors are used to represent the 3 categories that were used for further analysis The image in the legend shows the thresholds used to divide the categories (as square shapes).

Figure 6.. (A) Distribution of errors in identifying the pain spot areas expressed in percentages. The 3-color box and whisker plots for each device represent the distribution of area error for each of the 3 categories (small, medium, and large pain spots). (B) Correlation between percentage of error and spot size (the regression line is indicated as a dashed line).

Figure 7.. Distribution of errors in the location of the pain spots expressed in pixels. The 3-color box and whisker plots for each device represent the distribution of barycenter distance error for each of the 3 categories (small, medium, and large pain spots). The image of the eye shows the actual dimensions of 5 pixels in the full body chart (paper dimensions: 2048×1536 pixels).