Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards

Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. Observational cohort study. Five hospitals, from No...

Full description

Saved in:
Bibliographic Details
Published in:Critical care medicine Vol. 44; no. 2; pp. 368 - 374
Main Authors: Churpek, Matthew M, Yuen, Trevor C, Winslow, Christopher, Meltzer, David O, Kattan, Michael W, Edelson, Dana P
Format: Journal Article
Language:English
Published: United States 01.02.2016
Subjects:
ISSN:1530-0293
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. Observational cohort study. Five hospitals, from November 2008 until January 2013. Hospitalized ward patients None Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]). In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.
AbstractList OBJECTIVEMachine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database.DESIGNObservational cohort study.SETTINGFive hospitals, from November 2008 until January 2013.PATIENTSHospitalized ward patientsINTERVENTIONSNoneMEASUREMENTS AND MAIN RESULTSDemographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]).CONCLUSIONSIn this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.
Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. Observational cohort study. Five hospitals, from November 2008 until January 2013. Hospitalized ward patients None Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]). In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.
Author Winslow, Christopher
Kattan, Michael W
Yuen, Trevor C
Edelson, Dana P
Meltzer, David O
Churpek, Matthew M
Author_xml – sequence: 1
  givenname: Matthew M
  surname: Churpek
  fullname: Churpek, Matthew M
  organization: 1Department of Medicine, University of Chicago, Chicago, IL. 2Department of Medicine, NorthShore University HealthSystem, Evanston, IL. 3Department of Quantitative Health Sciences, Cleveland Clinic, Cleveland, OH
– sequence: 2
  givenname: Trevor C
  surname: Yuen
  fullname: Yuen, Trevor C
– sequence: 3
  givenname: Christopher
  surname: Winslow
  fullname: Winslow, Christopher
– sequence: 4
  givenname: David O
  surname: Meltzer
  fullname: Meltzer, David O
– sequence: 5
  givenname: Michael W
  surname: Kattan
  fullname: Kattan, Michael W
– sequence: 6
  givenname: Dana P
  surname: Edelson
  fullname: Edelson, Dana P
BackLink https://www.ncbi.nlm.nih.gov/pubmed/26771782$$D View this record in MEDLINE/PubMed
BookMark eNpNkE1LxDAQhoMo7of-A5EcvXRN0qZJj1I_YYsiisclTWZ3I91kTVrBo__cLK7gMDDM8LwzvDNBh847QOiMkhkllbis62ZG_gXlgh6gMeU5yQir8hGaxPie5gUX-TEasVIIKiQbo-9m6HqrwfUQcO03WxVs9A77JW6UXlsHeA4qOOtWuIF-7U3EypmEus8kst6pDj_DKkCMqcFLH_BTAGN1v5PUnXVWJ-Qa0gHrg9pJcMp-DfhNBRNP0NFSdRFO93WKXm9vXur7bP5491BfzTNdiLzMkqUWSFEwzkq5pK3iKpdcMFKQKtmk3EjSVjIHY1irucx1lSYV19wIaUpgU3Txu3cb_McAsV9sbNTQdcqBH-KCipLISjJZJPR8jw7tBsxiG-xGha_F39vYD4RQcLk
CitedBy_id crossref_primary_10_2196_59520
crossref_primary_10_1016_j_ijmedinf_2020_104248
crossref_primary_10_1016_j_ijmedinf_2021_104643
crossref_primary_10_1016_j_amjcard_2019_06_032
crossref_primary_10_1016_j_ijnurstu_2025_105094
crossref_primary_10_1016_j_tox_2023_153431
crossref_primary_10_7861_clinmed_2022_0349
crossref_primary_10_1177_14799731231198865
crossref_primary_10_3389_fmed_2021_621861
crossref_primary_10_1097_MCC_0000000000001160
crossref_primary_10_1002_cpt_1034
crossref_primary_10_1016_j_jad_2022_07_045
crossref_primary_10_18632_oncotarget_24468
crossref_primary_10_1093_ajhp_zxab237
crossref_primary_10_1097_CCM_0000000000002105
crossref_primary_10_1097_ACO_0000000000000657
crossref_primary_10_1007_s10877_022_00874_6
crossref_primary_10_1002_clc_23541
crossref_primary_10_1016_j_ccc_2023_02_001
crossref_primary_10_1097_ALN_0000000000003843
crossref_primary_10_1111_nicc_70063
crossref_primary_10_1111_jocs_16060
crossref_primary_10_1371_journal_pone_0179641
crossref_primary_10_2196_44483
crossref_primary_10_1371_journal_pone_0318502
crossref_primary_10_1038_s41598_022_16195_2
crossref_primary_10_1001_jamanetworkopen_2024_38986
crossref_primary_10_1016_j_jacc_2018_03_521
crossref_primary_10_4187_respcare_08397
crossref_primary_10_1097_MLR_0000000000001140
crossref_primary_10_1109_ACCESS_2021_3070618
crossref_primary_10_1007_s41666_023_00128_3
crossref_primary_10_1016_j_resplu_2024_100628
crossref_primary_10_1186_s13049_020_00791_0
crossref_primary_10_1016_j_msksp_2025_103321
crossref_primary_10_1097_CCM_0000000000006845
crossref_primary_10_2196_medinform_8680
crossref_primary_10_7326_M19_0872
crossref_primary_10_1038_s41598_020_73740_7
crossref_primary_10_1186_s40635_020_00302_6
crossref_primary_10_3389_fmed_2021_810195
crossref_primary_10_3389_fonc_2022_816427
crossref_primary_10_1002_clc_23688
crossref_primary_10_1007_s11606_018_4335_8
crossref_primary_10_1371_journal_pone_0316452
crossref_primary_10_1016_j_jcrc_2019_09_024
crossref_primary_10_1136_bmjqs_2022_015275
crossref_primary_10_1016_j_prrv_2021_06_002
crossref_primary_10_1016_j_bpa_2020_12_013
crossref_primary_10_1186_s12877_025_05688_0
crossref_primary_10_1186_s12933_023_01741_7
crossref_primary_10_1213_ANE_0000000000005952
crossref_primary_10_3389_fpubh_2025_1505541
crossref_primary_10_1097_CCM_0000000000004982
crossref_primary_10_1097_CCM_0000000000003891
crossref_primary_10_1016_j_jcrc_2018_07_009
crossref_primary_10_1038_s41598_017_10558_w
crossref_primary_10_1016_j_mayocpiqo_2025_100663
crossref_primary_10_1097_PCC_0000000000001184
crossref_primary_10_1186_s12885_022_09217_9
crossref_primary_10_1590_0034_7167_2021_0570
crossref_primary_10_1186_s13256_022_03385_9
crossref_primary_10_1007_s11831_023_09915_y
crossref_primary_10_1097_CCM_0000000000004966
crossref_primary_10_1016_j_gerinurse_2025_103530
crossref_primary_10_1016_j_jtcvs_2024_11_003
crossref_primary_10_1007_s12012_021_09708_4
crossref_primary_10_1097_AIA_0000000000000479
crossref_primary_10_3389_fonc_2020_00832
crossref_primary_10_1177_08850666231166349
crossref_primary_10_1186_s13054_025_05484_7
crossref_primary_10_1186_s12872_022_02960_8
crossref_primary_10_1016_j_resuscitation_2019_04_007
crossref_primary_10_1016_j_jcjq_2018_04_014
crossref_primary_10_1111_nicc_70172
crossref_primary_10_1109_ACCESS_2020_3047186
crossref_primary_10_1016_j_jss_2018_03_028
crossref_primary_10_1177_10760296231171082
crossref_primary_10_3389_fnut_2022_740898
crossref_primary_10_1038_s41598_022_17916_3
crossref_primary_10_1088_1742_6596_1964_6_062076
crossref_primary_10_3390_diagnostics11071299
crossref_primary_10_1097_CCM_0000000000005837
crossref_primary_10_2196_26646
crossref_primary_10_25259_SNI_312_2023
crossref_primary_10_1007_s12672_025_03298_1
crossref_primary_10_1371_journal_pone_0205836
crossref_primary_10_1111_jnu_13001
crossref_primary_10_1016_j_asoc_2020_106612
crossref_primary_10_1186_s13054_018_2194_7
crossref_primary_10_1016_j_surg_2021_08_031
crossref_primary_10_1038_s41598_019_40192_7
crossref_primary_10_4103_jpcc_jpcc_21_25
crossref_primary_10_1177_23337214241279531
crossref_primary_10_1016_j_ijpharm_2022_122203
crossref_primary_10_1016_j_resuscitation_2021_08_024
crossref_primary_10_3389_fpsyt_2022_936283
crossref_primary_10_3390_s22166104
crossref_primary_10_1177_20552076241233135
crossref_primary_10_3390_jcm10071425
crossref_primary_10_1016_j_jtumed_2025_05_007
crossref_primary_10_1002_pros_24233
crossref_primary_10_1016_j_ijoa_2024_104288
crossref_primary_10_1371_journal_pone_0264184
crossref_primary_10_1007_s00330_020_07534_w
crossref_primary_10_1016_j_jbi_2020_103410
crossref_primary_10_1016_j_ejso_2022_08_034
crossref_primary_10_1038_s41598_020_77548_3
crossref_primary_10_1080_10255842_2024_2427118
crossref_primary_10_1161_CIRCEP_117_005499
crossref_primary_10_1155_2022_8044550
crossref_primary_10_1038_s41598_025_06723_1
crossref_primary_10_1016_j_jbi_2020_103528
crossref_primary_10_1001_jamanetworkopen_2019_7447
crossref_primary_10_1097_SAP_0000000000004016
crossref_primary_10_1016_j_puhe_2025_105744
crossref_primary_10_1016_j_resuscitation_2018_05_013
crossref_primary_10_1093_jamia_ocaa295
crossref_primary_10_1093_jamia_ocaa296
crossref_primary_10_3389_fcvm_2022_964894
crossref_primary_10_3390_brainsci12091232
crossref_primary_10_1097_PCC_0000000000002414
crossref_primary_10_1007_s00395_023_00982_7
crossref_primary_10_1097_CCE_0000000000001116
crossref_primary_10_1016_j_ijnurstu_2022_104411
crossref_primary_10_1016_j_urolonc_2021_08_007
crossref_primary_10_1007_s00404_021_05994_z
crossref_primary_10_1093_jamia_ocac109
crossref_primary_10_1097_CCE_0000000000000023
crossref_primary_10_1097_CCE_0000000000001232
crossref_primary_10_1016_j_resuscitation_2018_05_007
crossref_primary_10_1186_s12879_023_08547_8
crossref_primary_10_1055_s_0044_1780508
crossref_primary_10_1097_TP_0000000000003700
crossref_primary_10_1136_bmjopen_2023_082540
crossref_primary_10_1097_CCM_0000000000002648
crossref_primary_10_1093_jamiaopen_ooae033
crossref_primary_10_1016_j_bja_2021_07_016
crossref_primary_10_1097_CCE_0000000000000031
crossref_primary_10_3390_children5030038
crossref_primary_10_1016_j_bja_2024_10_045
crossref_primary_10_1016_j_heliyon_2024_e32655
crossref_primary_10_1161_JAHA_118_008678
crossref_primary_10_1007_s12065_023_00836_0
crossref_primary_10_1186_s13098_021_00711_x
crossref_primary_10_1186_s12872_024_03723_3
crossref_primary_10_1097_MCC_0000000000000945
crossref_primary_10_1097_CCM_0000000000003803
crossref_primary_10_1016_j_aucc_2024_09_011
crossref_primary_10_1016_j_ijmedinf_2018_01_001
crossref_primary_10_1016_j_resuscitation_2019_06_045
crossref_primary_10_7717_peerj_11988
crossref_primary_10_3389_fneur_2022_791547
crossref_primary_10_1038_s41591_025_03609_7
crossref_primary_10_1016_j_bpa_2020_09_003
crossref_primary_10_1007_s10877_017_0054_7
crossref_primary_10_3390_jcm8091336
crossref_primary_10_15829_1560_4071_2021_4618
crossref_primary_10_1016_j_ajem_2022_10_011
crossref_primary_10_1016_j_ijnurstu_2023_104623
crossref_primary_10_1016_j_jcrc_2018_02_010
crossref_primary_10_1016_j_medine_2024_07_004
crossref_primary_10_1164_rccm_202002_0347OC
crossref_primary_10_1016_j_ijmedinf_2021_104572
crossref_primary_10_1016_j_cmpb_2019_06_010
crossref_primary_10_3389_fmed_2025_1564545
crossref_primary_10_3390_biomedinformatics5030052
crossref_primary_10_1001_jamanetworkopen_2019_20733
crossref_primary_10_3389_fmed_2021_629671
crossref_primary_10_1186_s12912_021_00742_9
crossref_primary_10_1097_EA9_0000000000000014
crossref_primary_10_1016_j_compbiomed_2018_07_018
crossref_primary_10_1016_j_ijrobp_2018_08_010
crossref_primary_10_2147_COPD_S379700
crossref_primary_10_1007_s00134_017_4806_0
crossref_primary_10_1097_CCM_0000000000002620
crossref_primary_10_3389_fphar_2022_1027230
crossref_primary_10_1371_journal_pone_0224502
crossref_primary_10_3389_fonc_2023_1117420
crossref_primary_10_3390_jcm12051755
crossref_primary_10_1016_j_jcrc_2023_154353
crossref_primary_10_1136_bmjopen_2018_027750
crossref_primary_10_1186_s12911_020_01144_8
crossref_primary_10_1001_jamanetworkopen_2020_5191
crossref_primary_10_1097_NCQ_0000000000000600
crossref_primary_10_1097_CCE_0000000000001161
crossref_primary_10_1007_s10877_024_01235_1
crossref_primary_10_1016_j_jclinane_2023_111194
crossref_primary_10_2147_PPA_S294402
crossref_primary_10_3389_fmed_2022_1043589
crossref_primary_10_1016_j_amjsurg_2019_03_005
crossref_primary_10_1002_phar_2147
crossref_primary_10_1016_j_resuscitation_2020_05_044
crossref_primary_10_1161_JAHA_119_013924
crossref_primary_10_1186_s40560_025_00814_x
crossref_primary_10_1177_1460458219894494
crossref_primary_10_3389_fpubh_2022_940905
crossref_primary_10_1371_journal_pone_0220640
crossref_primary_10_3390_jpm10030104
crossref_primary_10_1016_j_jclinepi_2020_03_002
crossref_primary_10_1007_s12551_018_0495_3
crossref_primary_10_12788_jhm_3151
crossref_primary_10_1016_j_jclinepi_2020_03_005
crossref_primary_10_1016_j_resplu_2020_100046
crossref_primary_10_2196_16349
crossref_primary_10_2196_30798
crossref_primary_10_1001_jamanetworkopen_2019_19396
crossref_primary_10_1097_CCE_0000000000000897
crossref_primary_10_2196_28209
crossref_primary_10_1097_CCM_0000000000006277
crossref_primary_10_1097_NUR_0000000000000644
crossref_primary_10_1177_1460458218813600
crossref_primary_10_2196_40474
crossref_primary_10_3390_biomedicines13010090
crossref_primary_10_3389_fpubh_2021_754348
crossref_primary_10_1038_s41598_023_42657_2
crossref_primary_10_1007_s12029_020_00544_3
crossref_primary_10_1186_s13613_019_0524_9
crossref_primary_10_1016_j_cnc_2021_05_010
crossref_primary_10_1177_1060028020959042
crossref_primary_10_1016_j_bja_2018_07_032
crossref_primary_10_3389_fonc_2025_1502404
crossref_primary_10_3748_wjg_v28_i32_4681
crossref_primary_10_3389_fneur_2025_1512297
crossref_primary_10_1089_end_2018_0035
crossref_primary_10_1007_s44254_023_00031_5
crossref_primary_10_1097_CCM_0000000000002926
crossref_primary_10_3390_jcm14124026
crossref_primary_10_1159_000543646
crossref_primary_10_4187_respcare_07500
crossref_primary_10_1016_j_resuscitation_2016_02_011
crossref_primary_10_1097_MD_0000000000035082
crossref_primary_10_1186_s12913_020_05148_y
crossref_primary_10_1007_s11739_022_02988_w
crossref_primary_10_1007_s12016_020_08805_6
crossref_primary_10_1097_DCC_0000000000000584
crossref_primary_10_2196_46807
crossref_primary_10_3390_jcm11195815
crossref_primary_10_1007_s10462_018_9625_3
crossref_primary_10_1007_s00586_025_08785_1
crossref_primary_10_1111_epi_17320
crossref_primary_10_1038_s41440_022_01081_1
crossref_primary_10_1007_s10462_021_09982_2
crossref_primary_10_3389_fneur_2020_539509
crossref_primary_10_1097_CCM_0000000000006243
crossref_primary_10_3389_fneur_2022_981752
crossref_primary_10_1097_MEG_0000000000002424
crossref_primary_10_1177_0044118X241227563
crossref_primary_10_1038_s41598_021_85157_x
crossref_primary_10_1186_s12890_022_02031_w
crossref_primary_10_1093_jamia_ocab111
crossref_primary_10_1002_acr_25013
crossref_primary_10_1007_s13311_020_00846_1
crossref_primary_10_1097_SLA_0000000000002665
crossref_primary_10_3390_medicina61091543
crossref_primary_10_1186_s13054_023_04609_0
crossref_primary_10_1186_s12911_020_01245_4
crossref_primary_10_1007_s00268_019_05087_8
crossref_primary_10_1186_s12905_025_03584_8
crossref_primary_10_1186_s12871_021_01543_y
crossref_primary_10_1016_j_iccn_2025_104101
crossref_primary_10_1007_s00438_024_02217_3
crossref_primary_10_1016_j_medin_2024_06_014
crossref_primary_10_1016_j_aucc_2016_06_002
crossref_primary_10_1016_j_cct_2022_106767
crossref_primary_10_1016_j_cmpb_2021_106395
crossref_primary_10_1016_j_resuscitation_2020_11_020
crossref_primary_10_1530_ERP_18_0081
crossref_primary_10_3390_ijms23137132
crossref_primary_10_1097_CCM_0000000000001800
crossref_primary_10_1097_PCC_0000000000002965
crossref_primary_10_1007_s00134_018_5384_5
crossref_primary_10_4187_respcare_07405
crossref_primary_10_1016_j_surg_2018_06_022
crossref_primary_10_1002_nav_21929
crossref_primary_10_1155_2022_7896218
crossref_primary_10_3389_fpubh_2022_978338
crossref_primary_10_1016_j_jbi_2018_10_008
crossref_primary_10_3390_diagnostics13213380
crossref_primary_10_1164_rccm_202007_2700OC
crossref_primary_10_1007_s10877_019_00415_8
crossref_primary_10_1007_s10877_021_00753_6
crossref_primary_10_1016_j_resuscitation_2024_110161
crossref_primary_10_1186_s12911_023_02323_z
crossref_primary_10_1097_CCM_0000000000006137
crossref_primary_10_1007_s10877_021_00666_4
crossref_primary_10_1097_CCM_0000000000005286
crossref_primary_10_1186_s13054_019_2485_7
crossref_primary_10_1007_s00784_022_04742_0
crossref_primary_10_3389_fmed_2022_942356
crossref_primary_10_1016_j_ejim_2017_09_018
crossref_primary_10_1097_CRD_0000000000000708
crossref_primary_10_1186_s12890_020_1089_y
crossref_primary_10_3389_fpubh_2022_939758
crossref_primary_10_1016_j_ejrad_2024_111508
crossref_primary_10_1186_s12884_022_04631_0
crossref_primary_10_1111_echo_14220
crossref_primary_10_3390_ijerph20085575
crossref_primary_10_1186_s13054_024_04860_z
crossref_primary_10_3390_ijerph17030897
crossref_primary_10_1186_s40560_017_0261_9
crossref_primary_10_1016_j_medine_2019_03_010
crossref_primary_10_1080_02564602_2021_1936224
crossref_primary_10_1016_j_jclinepi_2019_02_004
crossref_primary_10_1007_s11886_023_01964_w
crossref_primary_10_1016_j_medin_2019_03_011
crossref_primary_10_1016_j_resuscitation_2021_04_013
crossref_primary_10_2196_24246
crossref_primary_10_1097_CCM_0000000000003168
crossref_primary_10_1038_s41598_021_99628_8
crossref_primary_10_1016_j_ejim_2017_09_031
crossref_primary_10_1186_s13054_023_04437_2
crossref_primary_10_3390_medicina56090455
crossref_primary_10_1038_s41746_018_0029_1
crossref_primary_10_1093_ajcp_aqx078
crossref_primary_10_1002_ams2_70083
crossref_primary_10_1016_j_jss_2023_05_015
crossref_primary_10_1016_j_resplu_2021_100193
crossref_primary_10_1016_j_jpeds_2020_02_039
crossref_primary_10_1016_j_resplu_2021_100089
crossref_primary_10_1111_acem_14190
crossref_primary_10_1016_j_acra_2025_07_008
crossref_primary_10_1590_0034_7167_2021_0570pt
crossref_primary_10_1016_j_ejim_2021_12_024
crossref_primary_10_1016_S2213_2600_17_30187_X
crossref_primary_10_1097_CCM_0000000000006333
crossref_primary_10_1177_10760296241285565
crossref_primary_10_3390_healthcare11071008
crossref_primary_10_1016_j_chest_2018_04_037
crossref_primary_10_1371_journal_pone_0225229
crossref_primary_10_1177_1403494817736944
crossref_primary_10_1016_j_jhin_2021_02_025
crossref_primary_10_1111_jocn_17396
crossref_primary_10_1016_j_csbj_2021_10_025
crossref_primary_10_1111_jdi_13937
crossref_primary_10_1038_s41598_024_66952_8
crossref_primary_10_1108_IDD_02_2019_0013
crossref_primary_10_1186_s13756_021_00928_5
crossref_primary_10_1001_jamanetworkopen_2022_51849
crossref_primary_10_2196_29982
crossref_primary_10_1016_j_jval_2022_03_022
crossref_primary_10_1016_j_jenvman_2020_110956
crossref_primary_10_1097_PEC_0000000000001858
crossref_primary_10_1513_AnnalsATS_201710_787OC
crossref_primary_10_1016_j_iswa_2023_200197
crossref_primary_10_1016_j_ijmedinf_2018_05_006
crossref_primary_10_3389_fcvm_2022_928948
crossref_primary_10_3390_forecast7030051
crossref_primary_10_1371_journal_pone_0199246
crossref_primary_10_1371_journal_pone_0206662
crossref_primary_10_1177_0194599818823200
crossref_primary_10_1097_CCM_0000000000003123
crossref_primary_10_1111_anae_16007
crossref_primary_10_1038_s41598_023_38858_4
crossref_primary_10_1016_j_chest_2022_02_001
crossref_primary_10_1177_03611981221141435
crossref_primary_10_1371_journal_pone_0169772
crossref_primary_10_1093_milmed_usx164
crossref_primary_10_2174_0118749445304699240416074458
crossref_primary_10_1097_HCO_0000000000000812
crossref_primary_10_1016_j_bjao_2022_100002
crossref_primary_10_1093_eurheartj_ehz902
crossref_primary_10_1016_j_bulcan_2021_12_005
crossref_primary_10_1186_s12911_022_02052_9
crossref_primary_10_1016_j_radonc_2025_111139
crossref_primary_10_2196_48244
crossref_primary_10_36930_40340711
crossref_primary_10_1007_s10439_020_02639_1
crossref_primary_10_1016_j_artmed_2018_05_005
crossref_primary_10_3389_fonc_2022_1049305
crossref_primary_10_1097_PTS_0000000000001069
crossref_primary_10_1016_j_ajem_2019_04_006
crossref_primary_10_1016_j_cmpb_2021_106568
crossref_primary_10_1136_bmj_m3216
crossref_primary_10_1038_s41598_022_05445_y
crossref_primary_10_1080_10106049_2022_2106315
crossref_primary_10_1097_CCM_0000000000004236
crossref_primary_10_1111_ijcp_13685
crossref_primary_10_1515_dx_2024_0034
crossref_primary_10_1097_CCM_0000000000003148
crossref_primary_10_1097_CCE_0000000000000515
crossref_primary_10_2196_jmir_6025
crossref_primary_10_1183_13993003_01755_2019
crossref_primary_10_3389_fpubh_2022_947204
crossref_primary_10_1371_journal_pone_0262895
crossref_primary_10_1159_000546397
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1097/CCM.0000000000001571
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
EISSN 1530-0293
EndPage 374
ExternalDocumentID 26771782
Genre Multicenter Study
Journal Article
Observational Study
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NIA NIH HHS
  grantid: K24 AG031326
– fundername: NCATS NIH HHS
  grantid: UL1 TR000430
– fundername: NHLBI NIH HHS
  grantid: K08 HL121080
– fundername: NCRR NIH HHS
  grantid: UL1 RR024999
GroupedDBID ---
.-D
.3C
.55
.GJ
.XZ
.Z2
01R
0R~
1J1
354
3O-
40H
4Q1
4Q2
4Q3
53G
5GY
5RE
5VS
6J9
6PF
71W
77Y
7O~
AAAAV
AAAXR
AAGIX
AAHPQ
AAIQE
AAJCS
AAMOA
AAMTA
AAQKA
AAQQT
AARTV
AASCR
AASOK
AASXQ
AAUEB
AAWTL
AAXQO
AAYEP
AAYOK
ABASU
ABBUW
ABDIG
ABJNI
ABOCM
ABPPZ
ABVCZ
ABXVJ
ABXYN
ABZAD
ABZZY
ACCJW
ACDDN
ACDOF
ACEWG
ACGFO
ACGFS
ACIJW
ACILI
ACLDA
ACOAL
ACWDW
ACWRI
ACXJB
ACXNZ
ACZKN
ADFPA
ADGGA
ADHPY
ADNKB
AE3
AE6
AEBDS
AEETU
AENEX
AFBFQ
AFDTB
AFEXH
AFFNX
AFMBP
AFNMH
AFSOK
AFUWQ
AGINI
AHOMT
AHQNM
AHQVU
AHRYX
AHVBC
AI.
AIJEX
AINUH
AJCLO
AJIOK
AJNWD
AJNYG
AJZMW
AKCTQ
AKULP
ALKUP
ALMA_UNASSIGNED_HOLDINGS
ALMTX
AMJPA
AMKUR
AMNEI
AOHHW
AOQMC
BOYCO
BQLVK
BS7
BYPQX
C45
CGR
CS3
CUY
CVF
DIWNM
DU5
DUNZO
E.X
EBS
ECM
EEVPB
EIF
EJD
ERAAH
EX3
F2K
F2L
F2M
F2N
F5P
FCALG
FL-
FW0
GNXGY
GQDEL
H0~
HLJTE
HZ~
IKREB
IKYAY
IN~
IPNFZ
J5H
JF9
JG8
JK3
JK8
K-A
K-F
K8S
KD2
KMI
L-C
L7B
M18
N4W
N9A
NEJ
NPM
N~7
N~B
N~M
O9-
OAG
OAH
OB4
OBH
OCUKA
ODA
ODMTH
ODZKP
OHH
OHT
OHYEH
OL1
OLB
OLG
OLH
OLU
OLV
OLY
OLZ
ONV
OPUJH
ORVUJ
OUVQU
OVD
OVDNE
OVIDH
OVLEI
OVOZU
OWBYB
OWU
OWV
OWW
OWX
OWY
OWZ
OXXIT
P-K
P2P
PONUX
R58
RIG
RLZ
S4R
S4S
T8P
TEORI
TSPGW
V2I
VH1
VVN
W3M
WOQ
WOW
X3V
X3W
X7M
XXN
XYM
YCJ
YFH
YOC
YOJ
ZCG
ZFV
ZGI
ZXP
ZY1
ZZMQN
~9M
7X8
ABPXF
ADKSD
ADSXY
ID FETCH-LOGICAL-c4736-157be04425268f1ba5a38572040953015d80b983edd2bc583c9d8095c5d78d6e2
IEDL.DBID 7X8
ISICitedReferencesCount 450
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=00003246-201602000-00016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Oct 02 17:44:35 EDT 2025
Thu Apr 03 07:11:09 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4736-157be04425268f1ba5a38572040953015d80b983edd2bc583c9d8095c5d78d6e2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ObjectType-Undefined-3
PMID 26771782
PQID 1760898284
PQPubID 23479
PageCount 7
ParticipantIDs proquest_miscellaneous_1760898284
pubmed_primary_26771782
PublicationCentury 2000
PublicationDate 2016-Feb
20160201
PublicationDateYYYYMMDD 2016-02-01
PublicationDate_xml – month: 02
  year: 2016
  text: 2016-Feb
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Critical care medicine
PublicationTitleAlternate Crit Care Med
PublicationYear 2016
References 25102315 - Ann Am Thorac Soc. 2014 Sep;11(7):1130-5
23295778 - Resuscitation. 2013 Apr;84(4):465-70
21169824 - Crit Care Med. 2011 Mar;39(3):469-73
22777999 - Biom J. 2012 Sep;54(5):657-73
25532820 - BMC Med Res Methodol. 2014;14:137
25068389 - Am J Respir Crit Care Med. 2014 Sep 15;190(6):606-10
25466337 - Lancet Respir Med. 2015 Jan;3(1):42-52
14610404 - J Urol. 2003 Dec;170(6 Pt 2):S6-9; discussion S10
20935559 - Crit Care Med. 2011 Jan;39(1):65-72
8254858 - JAMA. 1993 Dec 22-29;270(24):2957-63
22447632 - J Hosp Med. 2012 May-Jun;7(5):388-95
24361673 - Resuscitation. 2014 Mar;85(3):418-23
25637693 - Resuscitation. 2015 Apr;89:99-105
22052772 - Chest. 2012 May;141(5):1170-6
22026551 - BMC Med Res Methodol. 2011;11:143
1959406 - Chest. 1991 Dec;100(6):1619-36
9618776 - Stat Med. 1998 May 30;17(10):1169-86
20959788 - Crit Care Med. 2011 Jan;39(1):34-9
23440923 - J Hosp Med. 2013 May;8(5):236-42
11588210 - QJM. 2001 Oct;94(10):521-6
25089847 - Am J Respir Crit Care Med. 2014 Sep 15;190(6):649-55
11185421 - Artif Intell Med. 2000 Aug;20(1):59-75
22479598 - PLoS One. 2012;7(3):e34312
References_xml – reference: 22026551 - BMC Med Res Methodol. 2011;11:143
– reference: 24361673 - Resuscitation. 2014 Mar;85(3):418-23
– reference: 21169824 - Crit Care Med. 2011 Mar;39(3):469-73
– reference: 25089847 - Am J Respir Crit Care Med. 2014 Sep 15;190(6):649-55
– reference: 1959406 - Chest. 1991 Dec;100(6):1619-36
– reference: 11185421 - Artif Intell Med. 2000 Aug;20(1):59-75
– reference: 25532820 - BMC Med Res Methodol. 2014;14:137
– reference: 25466337 - Lancet Respir Med. 2015 Jan;3(1):42-52
– reference: 23295778 - Resuscitation. 2013 Apr;84(4):465-70
– reference: 25102315 - Ann Am Thorac Soc. 2014 Sep;11(7):1130-5
– reference: 25637693 - Resuscitation. 2015 Apr;89:99-105
– reference: 20959788 - Crit Care Med. 2011 Jan;39(1):34-9
– reference: 22052772 - Chest. 2012 May;141(5):1170-6
– reference: 11588210 - QJM. 2001 Oct;94(10):521-6
– reference: 20935559 - Crit Care Med. 2011 Jan;39(1):65-72
– reference: 14610404 - J Urol. 2003 Dec;170(6 Pt 2):S6-9; discussion S10
– reference: 22777999 - Biom J. 2012 Sep;54(5):657-73
– reference: 25068389 - Am J Respir Crit Care Med. 2014 Sep 15;190(6):606-10
– reference: 9618776 - Stat Med. 1998 May 30;17(10):1169-86
– reference: 22479598 - PLoS One. 2012;7(3):e34312
– reference: 22447632 - J Hosp Med. 2012 May-Jun;7(5):388-95
– reference: 23440923 - J Hosp Med. 2013 May;8(5):236-42
– reference: 8254858 - JAMA. 1993 Dec 22-29;270(24):2957-63
SSID ssj0014573
Score 2.6415987
Snippet Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different...
OBJECTIVEMachine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 368
SubjectTerms Age Factors
Cohort Studies
Diagnostic Techniques and Procedures
Heart Arrest - mortality
Humans
Intensive Care Units - organization & administration
Logistic Models
Machine Learning - utilization
Models, Statistical
Neural Networks (Computer)
Risk Assessment
ROC Curve
Socioeconomic Factors
Support Vector Machine
Survival Analysis
Time Factors
Vital Signs
Title Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards
URI https://www.ncbi.nlm.nih.gov/pubmed/26771782
https://www.proquest.com/docview/1760898284
Volume 44
WOSCitedRecordID wos00003246-201602000-00016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA7qinjx_VhfRPAatm3aJjmJVBcvXRZR3FvJq4sg7bpV7_5zJ23WPQmCpfRQ2lKmk_SbzDfzIXTliiUZD0sSyFKRmBtLFC0p0UrHKuaCWSFbsQk2GvHJRIz9glvjaZWLObGdqE2t3Rr5IGRpwAXEB_H17I041SiXXfUSGquoRwHKOK9mk2UWIU4YXZTLCTbIsrxrV-i3MGHh78Cy_cEMt__7ajtoy0NLfNP5wi5asdUe2sh98nwffbXFto6Naec4-9EfxHWJ85ZSabHvtjrFeSss3WBZGbh0SUzHD3baMWcrDHAXj-fu8Y46jX2H0Vd86xg2L961MOyAMfGzK-46QE_Du8fsnngFBqJjRlMCFlI2iGFcRykvQyUTSXnidG1cmzowoOGBEpxaYyKlE061gDMi0Ylh3KQ2OkRrVV3ZY4R1GkgbGcqNa9LmwizloKeQqTWAgVQfXS6MW4CHu7SFrGz90RRL8_bRUfeFilnXiqOIUgbxKI9O_nD3KdoEtOMp12eoV8L4tudoXX--vzTzi9Z14Dga59-N2tAi
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multicenter+Comparison+of+Machine+Learning+Methods+and+Conventional+Regression+for+Predicting+Clinical+Deterioration+on+the+Wards&rft.jtitle=Critical+care+medicine&rft.au=Churpek%2C+Matthew+M&rft.au=Yuen%2C+Trevor+C&rft.au=Winslow%2C+Christopher&rft.au=Meltzer%2C+David+O&rft.date=2016-02-01&rft.eissn=1530-0293&rft.volume=44&rft.issue=2&rft.spage=368&rft_id=info:doi/10.1097%2FCCM.0000000000001571&rft_id=info%3Apmid%2F26771782&rft_id=info%3Apmid%2F26771782&rft.externalDocID=26771782