적외선 체열검사를 이용한 요천추 방사통의 통증 심각도 기계학습 분류 알고리즘

Abstract

Pain is subjective and varies among individuals. Doctors determine pain severity based on a patient’s self-reported symptoms. In such situations, language barrier may prevent patients from expressing their accurately, which cause doctors to underestimate degree. Moreover, patients’ descriptions of can eligibility for secondary benefits, as in the case compensation traffic or industrial accidents. Therefore, perform multiclass prediction lumbar radiculopathy, authors applied digital infrared thermographic imaging (DITI) machine-learning (ML) algorithm. The DITI dataset included data healthy population with radiculopathy herniated discs at L3/4, L4/5, L5/S1 levels. 1000 was split into training test datasets 7:3 ratio evaluate model’s performance. For dataset, average accuracy, precision, recall, F1 score were 0.82, 0.76, 0.72, 0.74, respectively. these values 0.77, 0.71, 0.75, 0.73, Applying ML algorithm pain-severity classification using images will aid treatment lumbosacral allow providers monitor therapeutic effect interventions through an assessment physiological evidence.