JMIR mHealth and uHealth (Apr 2019)

A Facial Recognition Mobile App for Patient Safety and Biometric Identification: Design, Development, and Validation

  • Jeon, Byoungjun,
  • Jeong, Boseong,
  • Jee, Seunghoon,
  • Huang, Yan,
  • Kim, Youngmin,
  • Park, Gee Ho,
  • Kim, Jungah,
  • Wufuer, Maierdanjiang,
  • Jin, Xian,
  • Kim, Sang Wha,
  • Choi, Tae Hyun

DOI
https://doi.org/10.2196/11472
Journal volume & issue
Vol. 7, no. 4
p. e11472

Abstract

Read online

BackgroundPatient verification by unique identification is an important procedure in health care settings. Risks to patient safety occur throughout health care settings by failure to correctly identify patients, resulting in the incorrect patient, incorrect site procedure, incorrect medication, and other errors. To avoid medical malpractice, radio-frequency identification (RFID), fingerprint scanners, iris scanners, and other technologies have been implemented in care settings. The drawbacks of these technologies include the possibility to lose the RFID bracelet, infection transmission, and impracticality when the patient is unconscious. ObjectiveThe purpose of this study was to develop a mobile health app for patient identification to overcome the limitations of current patient identification alternatives. The development of this app is expected to provide an easy-to-use alternative method for patient identification. MethodsWe have developed a facial recognition mobile app for improved patient verification. As an evaluation purpose, a total of 62 pediatric patients, including both outpatient and inpatient, were registered for the facial recognition test and tracked throughout the facilities for patient verification purpose. ResultsThe app was developed to contain 5 main parts: registration, medical records, examinations, prescriptions, and appointments. Among 62 patients, 30 were outpatients visiting plastic surgery department and 32 were inpatients reserved for surgery. Whether patients were under anesthesia or unconscious, facial recognition verified all patients with 99% accuracy even after a surgery. ConclusionsIt is possible to correctly identify both outpatients and inpatients and also reduce the unnecessary cost of patient verification by using the mobile facial recognition app with great accuracy. Our mobile app can provide valuable aid to patient verification, including when the patient is unconscious, as an alternative identification method.