PMID- 34211109
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240402
IS  - 2398-6352 (Electronic)
IS  - 2398-6352 (Linking)
VI  - 4
IP  - 1
DP  - 2021 Jul 1
TI  - Early prediction of diagnostic-related groups and estimation of hospital cost by 
      processing clinical notes.
PG  - 103
LID - 10.1038/s41746-021-00474-9 [doi]
LID - 103
AB  - As healthcare providers receive fixed amounts of reimbursement for given services 
      under DRG (Diagnosis-Related Groups) payment, DRG codes are valuable for cost 
      monitoring and resource allocation. However, coding is typically performed 
      retrospectively post-discharge. We seek to predict DRGs and DRG-based case mix 
      index (CMI) at early inpatient admission using routine clinical text to estimate 
      hospital cost in an acute setting. We examined a deep learning-based natural 
      language processing (NLP) model to automatically predict per-episode DRGs and 
      corresponding cost-reflecting weights on two cohorts (paid under Medicare 
      Severity (MS) DRG or All Patient Refined (APR) DRG), without human coding 
      efforts. It achieved macro-averaged area under the receiver operating 
      characteristic curve (AUC) scores of 0.871 (SD 0.011) on MS-DRG and 0.884 (0.003) 
      on APR-DRG in fivefold cross-validation experiments on the first day of ICU 
      admission. When extended to simulated patient populations to estimate average 
      cost-reflecting weights, the model increased its accuracy over time and obtained 
      absolute CMI error of 2.40 (1.07%) and 12.79% (2.31%), respectively on the first 
      day. As the model could adapt to variations in admission time, cohort size, and 
      requires no extra manual coding efforts, it shows potential to help estimating 
      costs for active patients to support better operational decision-making in 
      hospitals.
FAU - Liu, Jinghui
AU  - Liu J
AUID- ORCID: 0000-0002-7945-4165
AD  - School of Computing and Information Systems, The University of Melbourne, 
      Melbourne, VIC, Australia.
AD  - Australian e-Health Research Centre, CSIRO, Brisbane, QLD, Australia.
FAU - Capurro, Daniel
AU  - Capurro D
AUID- ORCID: 0000-0002-9256-1256
AD  - School of Computing and Information Systems, The University of Melbourne, 
      Melbourne, VIC, Australia.
AD  - Centre for Digital Transformation of Health, Melbourne Medical School, The 
      University of Melbourne, Melbourne, VIC, Australia.
FAU - Nguyen, Anthony
AU  - Nguyen A
AUID- ORCID: 0000-0002-6215-6954
AD  - Australian e-Health Research Centre, CSIRO, Brisbane, QLD, Australia.
FAU - Verspoor, Karin
AU  - Verspoor K
AUID- ORCID: 0000-0002-8661-1544
AD  - School of Computing and Information Systems, The University of Melbourne, 
      Melbourne, VIC, Australia. karin.verspoor@rmit.edu.au.
AD  - Centre for Digital Transformation of Health, Melbourne Medical School, The 
      University of Melbourne, Melbourne, VIC, Australia. karin.verspoor@rmit.edu.au.
AD  - School of Computing Technologies, RMIT University, Melbourne, VIC, Australia. 
      karin.verspoor@rmit.edu.au.
LA  - eng
GR  - 1134919/Department of Health | National Health and Medical Research Council 
      (NHMRC)/
PT  - Journal Article
DEP - 20210701
PL  - England
TA  - NPJ Digit Med
JT  - NPJ digital medicine
JID - 101731738
PMC - PMC8249417
COIS- K.V. reports grants from National Health and Medical Research Council, grants 
      from Australian Research Council, during the conduct of the study; personal fees 
      from Pfizer, outside the submitted work. J.L, D.C., and A.N. have none to 
      declare.
EDAT- 2021/07/03 06:00
MHDA- 2021/07/03 06:01
PMCR- 2021/07/01
CRDT- 2021/07/02 06:28
PHST- 2021/01/11 00:00 [received]
PHST- 2021/06/08 00:00 [accepted]
PHST- 2021/07/02 06:28 [entrez]
PHST- 2021/07/03 06:00 [pubmed]
PHST- 2021/07/03 06:01 [medline]
PHST- 2021/07/01 00:00 [pmc-release]
AID - 10.1038/s41746-021-00474-9 [pii]
AID - 474 [pii]
AID - 10.1038/s41746-021-00474-9 [doi]
PST - epublish
SO  - NPJ Digit Med. 2021 Jul 1;4(1):103. doi: 10.1038/s41746-021-00474-9.