PMID- 34542990
OWN - NLM
STAT- MEDLINE
DCOM- 20220224
LR  - 20230927
IS  - 1536-7355 (Electronic)
IS  - 1076-1608 (Linking)
VI  - 28
IP  - 2
DP  - 2022 Mar 1
TI  - A Machine Learning Approach for Predicting Sustained Remission in Rheumatoid 
      Arthritis Patients on Biologic Agents.
PG  - e334-e339
LID - 10.1097/RHU.0000000000001720 [doi]
AB  - METHODS: In this longitudinal study, patients with RA who started a biological 
      disease-modifying antirheumatic drug (bDMARD) in a tertiary care center were 
      analyzed. Demographic and clinical characteristics were collected at treatment 
      baseline, 12-month, and 24-month follow-up. A wrapper feature selection algorithm 
      was used to determine an attribute core set. Four different ML algorithms, 
      namely, LR, random forest, K-nearest neighbors, and extreme gradient boosting, 
      were then trained and validated with 10-fold cross-validation to predict 24-month 
      sustained DAS28 (Disease Activity Score on 28 joints) remission. The performances 
      of the algorithms were then compared assessing accuracy, precision, and recall. 
      RESULTS: Our analysis included 367 patients (female 323/367, 88%) with mean age +/- 
      SD of 53.7 +/- 12.5 years at bDMARD baseline. Sustained DAS28 remission was 
      achieved by 175 (47.2%) of 367 patients. The attribute core set used to train 
      algorithms included acute phase reactant levels, Clinical Disease Activity Index, 
      Health Assessment Questionnaire-Disability Index, as well as several clinical 
      characteristics. Extreme gradient boosting showed the best performance (accuracy, 
      72.7%; precision, 73.2%; recall, 68.1%), outperforming random forest (accuracy, 
      65.9%; precision, 65.6%; recall, 59.3%), LR (accuracy, 64.9%; precision, 62.6%; 
      recall, 61.9%), and K-nearest neighbors (accuracy, 63%; precision, 61.5%; recall, 
      54.8%). CONCLUSIONS: We showed that ML models can be used to predict sustained 
      remission in RA patients on bDMARDs. Furthermore, our method only relies on a few 
      easy-to-collect patient attributes. Our results are promising but need to be 
      tested on longitudinal cohort studies.
CI  - Copyright (c) 2021 Wolters Kluwer Health, Inc. All rights reserved.
FAU - Venerito, Vincenzo
AU  - Venerito V
AD  - From the Rheumatology Unit, Department of Emergency and Organ Transplantations, 
      University of Bari "Aldo Moro," Bari, Italy.
FAU - Angelini, Orazio
AU  - Angelini O
FAU - Fornaro, Marco
AU  - Fornaro M
AD  - From the Rheumatology Unit, Department of Emergency and Organ Transplantations, 
      University of Bari "Aldo Moro," Bari, Italy.
FAU - Cacciapaglia, Fabio
AU  - Cacciapaglia F
AD  - From the Rheumatology Unit, Department of Emergency and Organ Transplantations, 
      University of Bari "Aldo Moro," Bari, Italy.
FAU - Lopalco, Giuseppe
AU  - Lopalco G
AD  - From the Rheumatology Unit, Department of Emergency and Organ Transplantations, 
      University of Bari "Aldo Moro," Bari, Italy.
FAU - Iannone, Florenzo
AU  - Iannone F
AD  - From the Rheumatology Unit, Department of Emergency and Organ Transplantations, 
      University of Bari "Aldo Moro," Bari, Italy.
LA  - eng
PT  - Journal Article
PL  - United States
TA  - J Clin Rheumatol
JT  - Journal of clinical rheumatology : practical reports on rheumatic & 
      musculoskeletal diseases
JID - 9518034
RN  - 0 (Antirheumatic Agents)
RN  - 0 (Biological Factors)
SB  - IM
MH  - *Antirheumatic Agents/therapeutic use
MH  - *Arthritis, Rheumatoid/diagnosis/drug therapy
MH  - Biological Factors/therapeutic use
MH  - Female
MH  - Humans
MH  - Longitudinal Studies
MH  - Machine Learning
MH  - Remission Induction
MH  - Treatment Outcome
COIS- The authors declare no conflict of interest.
EDAT- 2021/09/21 06:00
MHDA- 2022/02/25 06:00
CRDT- 2021/09/20 14:49
PHST- 2021/09/21 06:00 [pubmed]
PHST- 2022/02/25 06:00 [medline]
PHST- 2021/09/20 14:49 [entrez]
AID - 00124743-202203000-00013 [pii]
AID - 10.1097/RHU.0000000000001720 [doi]
PST - ppublish
SO  - J Clin Rheumatol. 2022 Mar 1;28(2):e334-e339. doi: 10.1097/RHU.0000000000001720.