Studies in health technology and informatics · 2024
Digitalizing Handwritten Digits of Patients with Parkinson's Disease Utilizing Consumer Hardware and Open-Source Software.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Gundler Christopher, Wiederhold Alexander Johannes, Pötter-Nerger Monika
Аннотация
INTRODUCTION: Parkinson's disease represents a burdensome condition with complex manifestations. A licensed, standardized paper-based questionnaire is completed by both patients and physicians to monitor the progression and state of the disease. However, integrating the obtained scores into digital systems still poses a challenge.
METHODS: Paper-based handwriting is intuitive and an efficient mode of human-computer interaction. Accordingly, we transformed a consumer-grade tablet into a device where an exact digital copy of the disease-specific questionnaire can be filled with the supplied pen. Utilizing a small convolutional neural network directly on the device and trained on MNIST data, we translated the handwritten digits to appropriate LOINC codes and made them accessible through a FHIR-compatible HTTP interface.
RESULTS: When evaluating the usability from a patient-centric point of view, the System Usability Score revealed an excellent rating (SUS = 83.01) from the participants. However, we identified some challenges associated with the magnetic pen and the flat design of the device.
CONCLUSION: In setups where certified medical devices are not required, consumer hardware can be used to map handwritten digits of patients to appropriate medical standards without manual intervention through healthcare professionals.
METHODS: Paper-based handwriting is intuitive and an efficient mode of human-computer interaction. Accordingly, we transformed a consumer-grade tablet into a device where an exact digital copy of the disease-specific questionnaire can be filled with the supplied pen. Utilizing a small convolutional neural network directly on the device and trained on MNIST data, we translated the handwritten digits to appropriate LOINC codes and made them accessible through a FHIR-compatible HTTP interface.
RESULTS: When evaluating the usability from a patient-centric point of view, the System Usability Score revealed an excellent rating (SUS = 83.01) from the participants. However, we identified some challenges associated with the magnetic pen and the flat design of the device.
CONCLUSION: In setups where certified medical devices are not required, consumer hardware can be used to map handwritten digits of patients to appropriate medical standards without manual intervention through healthcare professionals.