Deep into Laboratory: An Artificial Intelligence Approach to Recommend Laboratory Tests

被引:13
|
作者
Islam, Md. Mohaimenul [1 ,2 ,3 ]
Poly, Tahmina Nasrin [1 ,2 ,3 ]
Yang, Hsuan-Chia [1 ,2 ,3 ]
Li, Yu-Chuan [1 ,2 ,3 ,4 ,5 ]
机构
[1] Taipei Med Univ, Grad Inst Biomed Informat, Coll Med Sci & Technol, Taipei 110, Taiwan
[2] Taipei Med Univ, Int Ctr Hlth Informat Technol ICHIT, Taipei 110, Taiwan
[3] Taipei Med Univ, Wan Fang Hosp, Res Ctr Big Data & Meta Anal, Taipei 116, Taiwan
[4] Wan Fang Hosp, Dept Dermatol, Taipei 116, Taiwan
[5] Taipei Med Univ, TMU Res Ctr Canc Translat Med, Taipei 110, Taiwan
关键词
laboratory test; deep learning; artificial intelligence; recommendation system; clinical decision support system; PRIMARY-CARE; HEALTH; PHYSICIANS; DEMAND; TRENDS; COST;
D O I
10.3390/diagnostics11060990
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Laboratory tests are performed to make effective clinical decisions. However, inappropriate laboratory test ordering hampers patient care and increases financial burden for healthcare. An automated laboratory test recommendation system can provide rapid and appropriate test selection, potentially improving the workflow to help physicians spend more time treating patients. The main objective of this study was to develop a deep learning-based automated system to recommend appropriate laboratory tests. A retrospective data collection was performed at the National Health Insurance database between 1 January 2013, and 31 December 2013. We included all prescriptions that had at least one laboratory test. A total of 1,463,837 prescriptions from 530,050 unique patients was included in our study. Of these patients, 296,541 were women (55.95%), the range of age was between 1 and 107 years. The deep learning (DL) model achieved a higher area under the receiver operating characteristics curve (AUROC micro = 0.98, and AUROC macro = 0.94). The findings of this study show that the DL model can accurately and efficiently identify laboratory tests. This model can be integrated into existing workflows to reduce under- and over-utilization problems.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] An Interdisciplinary Laboratory for Teaching Artificial Intelligence and Manufacturing
    Van Til, Robert P.
    Sengupta, Sankar
    Srodawa, Ronald J.
    Dessert, Patrick E.
    Wagner, Christian C.
    INTERNATIONAL JOURNAL OF ENGINEERING EDUCATION, 2000, 16 (06) : 516 - 523
  • [22] ARTIFICIAL-INTELLIGENCE WITHIN THE CHEMICAL LABORATORY
    WINKEL, P
    ANNALES DE BIOLOGIE CLINIQUE, 1994, 52 (04) : 277 - 282
  • [23] Robotics, imaging, and artificial intelligence in the catheterisation laboratory
    Beyar, Rafael
    Davies, Justin E.
    Cook, Christopher
    Dudek, Dariusz
    Cummins, Paul A.
    Bruining, Nico
    EUROINTERVENTION, 2021, 17 (07) : 537 - 549
  • [24] WEAR OF ARTIFICIAL JOINT MATERIALS IN LABORATORY TESTS
    MCKELLOP, H
    CLARKE, I
    ACTA ORTHOPAEDICA SCANDINAVICA, 1988, 59 (03): : 349 - 352
  • [25] Laboratory tests in rheumatology: A rational approach
    Suresh, Ernest
    CLEVELAND CLINIC JOURNAL OF MEDICINE, 2019, 86 (03) : 198 - +
  • [26] INTERPRETING LABORATORY TESTS - A BASIC APPROACH
    ROCK, RC
    GERIATRICS, 1984, 39 (01) : 49 - &
  • [27] Clinical Laboratory Employees' Attitudes Toward Artificial Intelligence
    Ardon, Orly
    Schmidt, Robert L.
    LABORATORY MEDICINE, 2020, 51 (06) : 649 - 654
  • [28] The NOMAD laboratory: from data sharing to artificial intelligence
    Draxl, Claudia
    Scheffler, Matthias
    JOURNAL OF PHYSICS-MATERIALS, 2019, 2 (03):
  • [29] Making an impact - Artificial intelligence at the jet propulsion laboratory
    Chien, S
    DeCoste, D
    Doyle, R
    Stolorz, P
    AI MAGAZINE, 1997, 18 (01) : 103 - 122
  • [30] AN ARTIFICIAL-INTELLIGENCE ROBOTIC SYSTEM FOR THE ANALYTICAL LABORATORY
    ISENHOUR, TL
    MARSHALL, JC
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 1992, 204 : 163 - ANYL