Personalized treatment selection in routine care: Integrating machine learning and statistical algorithms to recommend cognitive behavioral or psychodynamic therapy

Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal treatment based on their pre-treatment characteristics. Methods: A disorder-heterogeneous, naturalistic sample of N = 1,379 o...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Psychotherapy research Jg. 31; H. 1; S. 33 - 51
Hauptverfasser:	Schwartz, Brian, Cohen, Zachary D., Rubel, Julian A., Zimmermann, Dirk, Wittmann, Werner W., Lutz, Wolfgang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	England Routledge 2021 Taylor & Francis Ltd
Schlagworte:	Algorithms Averages Clinical decision making Cognition Cognitive behavioral therapy Cognitive-behavioral factors Data Decision making Inference Machine learning Medical decision making Medical treatment outcome prediction outpatient psychotherapy Outpatients Patients precision medicine Psychodynamic therapy Psychotherapy random forest Statistical inference Statistics Therapists Training variable selection outcome prediction outpatient psychotherapy precision medicine random forest variable selection machine learning
ISSN:	1050-3307, 1468-4381, 1468-4381
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal treatment based on their pre-treatment characteristics. Methods: A disorder-heterogeneous, naturalistic sample of N = 1,379 outpatients treated with either cognitive behavioral therapy or psychodynamic therapy was analyzed. Based on a combination of random forest and linear regression, differential treatment response was modeled in the training data (n = 966) to indicate each individual's optimal treatment. A separate holdout dataset (n = 413) was used to evaluate personalized recommendations. Results: The difference in outcomes between patients treated with their optimal vs. non-optimal treatment was significant in the training data, but non-significant in the holdout data (b = -0.043, p = .280). However, for the 50% of patients with the largest predicted benefit of receiving their optimal treatment, the average percentage of change on the BSI in the holdout data was 52.6% for their optimal and 38.4% for their non-optimal treatment (p = .017; d = 0.33 [0.06, 0.61]). Conclusion: A treatment selection algorithm based on a combination of ML and statistical inference might improve treatment outcome for some, but not all outpatients and could support therapists' clinical decision-making.
AbstractList	Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients’ optimal treatment based on their pre-treatment characteristics. Methods: A disorder-heterogeneous, naturalistic sample of N = 1,379 outpatients treated with either cognitive behavioral therapy or psychodynamic therapy was analyzed. Based on a combination of random forest and linear regression, differential treatment response was modeled in the training data (n = 966) to indicate each individual’s optimal treatment. A separate holdout dataset (n = 413) was used to evaluate personalized recommendations. Results: The difference in outcomes between patients treated with their optimal vs. non-optimal treatment was significant in the training data, but non-significant in the holdout data (b = –0.043, p = .280). However, for the 50% of patients with the largest predicted benefit of receiving their optimal treatment, the average percentage of change on the BSI in the holdout data was 52.6% for their optimal and 38.4% for their non-optimal treatment (p = .017; d = 0.33 [0.06, 0.61]). Conclusion: A treatment selection algorithm based on a combination of ML and statistical inference might improve treatment outcome for some, but not all outpatients and could support therapists’ clinical decision-making. This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal treatment based on their pre-treatment characteristics. A disorder-heterogeneous, naturalistic sample of = 1,379 outpatients treated with either cognitive behavioral therapy or psychodynamic therapy was analyzed. Based on a combination of random forest and linear regression, differential treatment response was modeled in the training data ( = 966) to indicate each individual's optimal treatment. A separate holdout dataset ( = 413) was used to evaluate personalized recommendations. The difference in outcomes between patients treated with their optimal vs. non-optimal treatment was significant in the training data, but non-significant in the holdout data ( = -0.043, = .280). However, for the 50% of patients with the largest predicted benefit of receiving their optimal treatment, the average percentage of change on the BSI in the holdout data was 52.6% for their optimal and 38.4% for their non-optimal treatment ( = .017; = 0.33 [0.06, 0.61]). A treatment selection algorithm based on a combination of ML and statistical inference might improve treatment outcome for some, but not all outpatients and could support therapists' clinical decision-making. Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal treatment based on their pre-treatment characteristics. Methods: A disorder-heterogeneous, naturalistic sample of N = 1,379 outpatients treated with either cognitive behavioral therapy or psychodynamic therapy was analyzed. Based on a combination of random forest and linear regression, differential treatment response was modeled in the training data (n = 966) to indicate each individual's optimal treatment. A separate holdout dataset (n = 413) was used to evaluate personalized recommendations. Results: The difference in outcomes between patients treated with their optimal vs. non-optimal treatment was significant in the training data, but non-significant in the holdout data (b = -0.043, p = .280). However, for the 50% of patients with the largest predicted benefit of receiving their optimal treatment, the average percentage of change on the BSI in the holdout data was 52.6% for their optimal and 38.4% for their non-optimal treatment (p = .017; d = 0.33 [0.06, 0.61]). Conclusion: A treatment selection algorithm based on a combination of ML and statistical inference might improve treatment outcome for some, but not all outpatients and could support therapists' clinical decision-making.Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal treatment based on their pre-treatment characteristics. Methods: A disorder-heterogeneous, naturalistic sample of N = 1,379 outpatients treated with either cognitive behavioral therapy or psychodynamic therapy was analyzed. Based on a combination of random forest and linear regression, differential treatment response was modeled in the training data (n = 966) to indicate each individual's optimal treatment. A separate holdout dataset (n = 413) was used to evaluate personalized recommendations. Results: The difference in outcomes between patients treated with their optimal vs. non-optimal treatment was significant in the training data, but non-significant in the holdout data (b = -0.043, p = .280). However, for the 50% of patients with the largest predicted benefit of receiving their optimal treatment, the average percentage of change on the BSI in the holdout data was 52.6% for their optimal and 38.4% for their non-optimal treatment (p = .017; d = 0.33 [0.06, 0.61]). Conclusion: A treatment selection algorithm based on a combination of ML and statistical inference might improve treatment outcome for some, but not all outpatients and could support therapists' clinical decision-making.
Author	Cohen, Zachary D. Schwartz, Brian Zimmermann, Dirk Rubel, Julian A. Lutz, Wolfgang Wittmann, Werner W.
Author_xml	– sequence: 1 givenname: Brian orcidid: 0000-0003-4695-4953 surname: Schwartz fullname: Schwartz, Brian email: schwartzb@uni-trier.de organization: University of Trier – sequence: 2 givenname: Zachary D. orcidid: 0000-0002-4883-1028 surname: Cohen fullname: Cohen, Zachary D. organization: University of California – sequence: 3 givenname: Julian A. orcidid: 0000-0002-9625-6611 surname: Rubel fullname: Rubel, Julian A. organization: Justus-Liebig-University Giessen – sequence: 4 givenname: Dirk orcidid: 0000-0002-8764-6343 surname: Zimmermann fullname: Zimmermann, Dirk organization: University of Trier – sequence: 5 givenname: Werner W. surname: Wittmann fullname: Wittmann, Werner W. organization: University of Mannheim – sequence: 6 givenname: Wolfgang orcidid: 0000-0002-5141-3847 surname: Lutz fullname: Lutz, Wolfgang organization: University of Trier
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32463342$$D View this record in MEDLINE/PubMed
BookMark	eNqFkctuFDEQRVsoiDzgE0CW2LCZ4Ee3uxs2QRGPSJFgAWurxl2ecdRtD2VP0PA9-dC4NTObLGBlq-rcW9K959VJiAGr6rXgl4J3_L3gDVeKt5eSyzJqdS9F_6w6E7XuFrXqxEn5F2YxQ6fVeUp3nIu24_xFdapkrZWq5Vn18AMpxQCj_4sDy4SQJwyZJRzRZh8D84FR3GYfkFkg_MBuQsYVQZms2AR2PW9GBArzAMLAUi7LlL2FkcG4iuTzekosR0Zo41T8B2bjKvjs75EtcQ33PlKBI7FN2tl1HHYBJm9ZXiPBZveyeu5gTPjq8F5Uv758_nn9bXH7_evN9afbha01zwvR943uG946bZdL12jkvdAatJBaOo0gamc7ha7uUEntLGo38J73EroeBVcX1bu974bi7y2mbCafLI4jBIzbZGTN26bjTasK-vYJehe3VHKcqbaWvZJKF-rNgdouJxzMhvwEtDPH_AvwcQ9YiikROmP9nF4MmcCPRnAzt22ObZu5bXNou6ibJ-rjgf_prvY6H1ykCf5EGgeTYTdGcgTB-mTUvy0eAXoIw8A
CitedBy_id	crossref_primary_10_1007_s10488_023_01340_4 crossref_primary_10_1080_10503307_2025_2517567 crossref_primary_10_1016_j_jad_2023_02_021 crossref_primary_10_1007_s41811_020_00094_3 crossref_primary_10_1038_s41598_024_71854_w crossref_primary_10_1080_10503307_2021_1916120 crossref_primary_10_1016_j_beth_2022_11_004 crossref_primary_10_3390_electronics14061110 crossref_primary_10_1080_10503307_2023_2269297 crossref_primary_10_3389_fpubh_2023_1102434 crossref_primary_10_1177_20552076211060659 crossref_primary_10_1002_cpp_2876 crossref_primary_10_1146_annurev_clinpsy_071720_014821 crossref_primary_10_1038_s41598_025_00916_4 crossref_primary_10_1017_S0033291724003118 crossref_primary_10_3389_fpsyt_2023_1236551 crossref_primary_10_1001_jamanetworkopen_2024_23241 crossref_primary_10_1055_a_1215_1541 crossref_primary_10_1016_j_brat_2025_104752 crossref_primary_10_1055_a_2450_9882 crossref_primary_10_3389_fpsyt_2021_613085 crossref_primary_10_1055_a_2170_7467 crossref_primary_10_1002_wps_20882 crossref_primary_10_1007_s10488_023_01302_w crossref_primary_10_1080_00273171_2022_2146638 crossref_primary_10_1080_10503307_2021_1930242 crossref_primary_10_1016_j_jval_2022_07_011 crossref_primary_10_1007_s10488_023_01303_9 crossref_primary_10_1007_s10488_023_01309_3 crossref_primary_10_1007_s40894_023_00228_6 crossref_primary_10_18863_pgy_1538432 crossref_primary_10_2196_41566 crossref_primary_10_1097_j_pain_0000000000003363 crossref_primary_10_1007_s11764_023_01423_z crossref_primary_10_1016_j_jad_2024_04_015 crossref_primary_10_1002_jts_22980 crossref_primary_10_1007_s00406_023_01604_y crossref_primary_10_1016_j_cbpra_2022_02_008 crossref_primary_10_1177_14727978251355786 crossref_primary_10_1016_j_chbah_2023_100008 crossref_primary_10_1055_a_2137_8561 crossref_primary_10_1016_j_brat_2025_104689 crossref_primary_10_1016_j_janxdis_2022_102611 crossref_primary_10_1016_j_brat_2023_104443 crossref_primary_10_3390_jcm14072265 crossref_primary_10_1080_10503307_2023_2182241 crossref_primary_10_1007_s10488_024_01351_9 crossref_primary_10_1001_jamapsychiatry_2025_2518 crossref_primary_10_1016_j_compbiomed_2024_108134 crossref_primary_10_1007_s10488_023_01330_6 crossref_primary_10_3390_jcm10194522 crossref_primary_10_13109_zptm_2024_70_4_370 crossref_primary_10_1093_pm_pnab102 crossref_primary_10_1080_10503307_2020_1808729 crossref_primary_10_1177_20552076221129098 crossref_primary_10_1055_a_2034_4896 crossref_primary_10_1080_10503307_2022_2161432 crossref_primary_10_1177_21677026211071043 crossref_primary_10_1080_10503307_2024_2360449 crossref_primary_10_1111_bjc_12508
Cites_doi	10.1023/A:1010933404324 10.1207/s15327752jpa6703_13 10.1001/archpsyc.1976.01770060086012 10.1080/03009740701607067 10.1002/wps.20345 10.1027/1015-5759.22.2.98 10.1186/s12888-017-1464-2 10.18637/jss.v042.i08 10.1177/0011000005285875 10.1080/10503307.2019.1662510 10.1177/2167702618815466 10.1146/annurev-clinpsy-050817-084746 10.1056/NEJMp1006304 10.1016/j.cpr.2005.07.003 10.1016/S0272-7358(99)00057-4 10.1126/science.aaa8415 10.1001/jama.2017.18391 10.1136/bmj.k4245 10.1186/s12916-015-0494-1 10.1037/cap0000096 10.1038/nmeth.4642 10.1186/1471-2105-10-213 10.1038/s41598-018-25953-0 10.1038/nmeth.4526 10.1017/S0033291718001708 10.1177/0011000006295149 10.1007/s10608-012-9476-1 10.1023/A:1020363010465 10.4324/9780203582015 10.1002/da.22731 10.1016/j.scitotenv.2018.06.389 10.1017/S0033291720000550 10.1371/journal.pone.0140771 10.1080/10503307.2018.1563312 10.1016/j.cpr.2009.08.010 10.1037/ccp0000476 10.5721/EuJRS20124535 10.1002/cpp.496 10.1176/appi.ajp.2013.12070899 10.1080/10503307.2015.1053553 10.1097/00005650-199603000-00003 10.1002/da.22755 10.1016/j.brat.2019.103438 10.1016/j.ijforecast.2018.06.001 10.1016/j.brat.2007.12.005 10.1002/jclp.20108 10.1080/10503307.2013.856046 10.1016/j.conb.2019.02.006 10.1159/000487893 10.1037/1040-3590.18.2.133 10.1001/jamapsychiatry.2016.1720 10.1016/j.brat.2020.103596 10.1016/0272-7358(88)90050-5 10.1136/gut.2003.025080 10.1371/journal.pone.0194889 10.1037/a0013075 10.1371/journal.pone.0083875 10.1056/NEJMp1606181 10.1002/da.22728 10.1017/S2045796016000020 10.1093/biomet/70.1.41 10.1126/science.185.4157.1124 10.1017/S0033291719003192 10.1055/s-0032-1321781 10.1093/bioinformatics/btr597 10.1038/nmeth.4438 10.1145/1143844.1143865 10.1080/10503307.2015.1079661
ContentType	Journal Article
Copyright	2020 Society for Psychotherapy Research 2020 2020 Society for Psychotherapy Research
Copyright_xml	– notice: 2020 Society for Psychotherapy Research 2020 – notice: 2020 Society for Psychotherapy Research
DBID	AAYXX CITATION NPM 8BJ FQK JBE 7X8
DOI	10.1080/10503307.2020.1769219
DatabaseName	CrossRef PubMed International Bibliography of the Social Sciences (IBSS) International Bibliography of the Social Sciences International Bibliography of the Social Sciences MEDLINE - Academic
DatabaseTitle	CrossRef PubMed International Bibliography of the Social Sciences (IBSS) MEDLINE - Academic
DatabaseTitleList	International Bibliography of the Social Sciences (IBSS) PubMed MEDLINE - Academic
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	fulltext_linktorsrc
Discipline	Statistics
EISSN	1468-4381
EndPage	51
ExternalDocumentID	32463342 10_1080_10503307_2020_1769219 1769219
Genre	Research Article Journal Article
GroupedDBID	--- .7I .QK 0BK 0R~ 123 29P 2DF 4.4 53G 5VS AAGDL AAGZJ AAHIA AAMFJ AAMIU AAPUL AATTQ AAZMC ABCCY ABDBF ABFIM ABIVO ABJNI ABLIJ ABLJU ABPEM ABTAI ABXUL ABXYU ABZLS ACGEJ ACGFO ACGFS ACGOD ACHQT ACTIO ACTOA ACUHS ADAHI ADCVX ADKVQ ADXPE AECIN AEFOU AEGXH AEISY AEKEX AEMXT AEOZL AEPSL AEYOC AEZRU AFRVT AGDLA AGMYJ AGRBW AHDZW AIAGR AIJEM AIYEW AJWEG AKBVH ALMA_UNASSIGNED_HOLDINGS ALQZU AQTUD AVBZW AWYRJ BEJHT BLEHA BMOTO BOHLJ CCCUG CQ1 CS3 DGFLZ DKSSO DU5 EBD EBS EMOBN ESX E~B E~C F5P G-F GTTXZ H13 HF~ HZ~ IPNFZ J.O KYCEM LJTGL M4Z NA5 NW- O9- P2P PQQKQ RIG RNANH ROSJB RSYQP RWL S-F STATR SV3 TAE TASJS TBQAZ TDBHL TEH TFH TFL TFW TNJ TNTFI TRJHH TUROJ TUS UT5 UT9 VAE WH7 ~01 ~S~ AAYXX CITATION 07M 1TA 4B3 9M8 AACLK AAIFK AASXD AAYMM ABGQD ABITY ABLUQ ABYAV ACIKQ ACVBB ADDRM ADYSH AEBKF AFLWG AFUSO BTBAK C5A CAG CKOZC COF C~T DAOCQ DEWOD DTEEQ DYOWO EJD JEUJS L7Y NPM PNGSA PPYGK RNI ROL RZO TBH THLUP UA1 8BJ FQK JBE 7X8
ID	FETCH-LOGICAL-c460t-199569507f6cbbf56e09166a61262f6ea14fc83ef48e326fce6fd09092a89e103
IEDL.DBID	TFW
ISICitedReferencesCount	77
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000541292200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1050-3307 1468-4381
IngestDate	Sun Nov 09 14:11:20 EST 2025 Sun Nov 09 09:42:43 EST 2025 Mon Jul 21 05:56:10 EDT 2025 Tue Nov 18 21:25:36 EST 2025 Sat Nov 29 04:59:38 EST 2025 Mon Oct 20 23:48:14 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	outcome prediction outpatient psychotherapy precision medicine random forest variable selection machine learning
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c460t-199569507f6cbbf56e09166a61262f6ea14fc83ef48e326fce6fd09092a89e103
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-4883-1028 0000-0002-5141-3847 0000-0002-9625-6611 0000-0002-8764-6343 0000-0003-4695-4953
PMID	32463342
PQID	2474293236
PQPubID	31397
PageCount	19
ParticipantIDs	crossref_citationtrail_10_1080_10503307_2020_1769219 proquest_miscellaneous_2407580573 proquest_journals_2474293236 informaworld_taylorfrancis_310_1080_10503307_2020_1769219 crossref_primary_10_1080_10503307_2020_1769219 pubmed_primary_32463342
PublicationCentury	2000
PublicationDate	2021-00-00
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– year: 2021 text: 2021-00-00
PublicationDecade	2020
PublicationPlace	England
PublicationPlace_xml	– name: England – name: Abingdon
PublicationTitle	Psychotherapy research
PublicationTitleAlternate	Psychother Res
PublicationYear	2021
Publisher	Routledge Taylor & Francis Ltd
Publisher_xml	– name: Routledge – name: Taylor & Francis Ltd
References	CIT0030 CIT0074 Derogatis L. R. (CIT0021) 1977 Guo S. (CIT0034) 2015 Schellberg D. (CIT0081) 1995 CIT0032 CIT0076 CIT0078 CIT0033 CIT0077 Ehlers A. (CIT0025) 2001 CIT0070 Horowitz L. M. (CIT0039) 2000 Petkovic D. (CIT0071) 2018; 23 Hunot V. (CIT0041) 2013; 10 CIT0036 CIT0035 CIT0079 CIT0038 CIT0037 CIT0083 CIT0085 CIT0040 CIT0084 CIT0043 Rathner G. (CIT0072) 1997; 45 CIT0087 CIT0042 CIT0086 CIT0001 CIT0045 CIT0089 CIT0044 CIT0088 Schepank H. (CIT0082) 1995 CIT0080 Wittmann W. W. (CIT0092) 2011; 3 Luborsky L. (CIT0052) 1996; 5 CIT0003 CIT0002 CIT0046 CIT0004 CIT0048 CIT0007 CIT0006 CIT0009 CIT0008 Klepsch R. (CIT0047) 1993 CIT0050 CIT0051 Meehl P. E. (CIT0064) 1954 CIT0010 CIT0054 Lutz W. (CIT0055) 2020 CIT0053 CIT0012 CIT0056 CIT0011 Gemeinsamer Bundesausschuss (CIT0031) 2009; 58 Beck A. T. (CIT0005) 1996 CIT0090 CIT0091 R Core Team (CIT0073) 2018 CIT0014 CIT0058 CIT0057 CIT0016 CIT0015 CIT0059 CIT0018 CIT0017 CIT0019 CIT0061 CIT0060 Rief W. (CIT0075) 1997 Chen T. (CIT0013) 2013; 2013 CIT0063 CIT0062 CIT0065 CIT0020 CIT0023 CIT0067 CIT0022 CIT0066 Lambert M. J. (CIT0049) 2013 Franke G. H. (CIT0029) 2000 CIT0069 CIT0024 CIT0068 CIT0027 CIT0026 CIT0028
References_xml	– ident: CIT0007 doi: 10.1023/A:1010933404324 – ident: CIT0004 doi: 10.1207/s15327752jpa6703_13 – ident: CIT0026 doi: 10.1001/archpsyc.1976.01770060086012 – ident: CIT0048 doi: 10.1080/03009740701607067 – ident: CIT0070 doi: 10.1002/wps.20345 – ident: CIT0033 doi: 10.1027/1015-5759.22.2.98 – ident: CIT0061 doi: 10.1186/s12888-017-1464-2 – volume: 23 start-page: 204 year: 2018 ident: CIT0071 publication-title: Pacific Symposium on Biocomputing – volume: 10 start-page: CD008704 year: 2013 ident: CIT0041 publication-title: The Cochrane Database of Systematic Reviews – start-page: 18 volume-title: Der Beeinträchtigungs-Schwere-score (BSS). Ein instrument zur Bestimmung der Schwere einer psychogenen Erkrankung year: 1995 ident: CIT0081 – ident: CIT0037 doi: 10.18637/jss.v042.i08 – ident: CIT0001 doi: 10.1177/0011000005285875 – volume-title: Der Beeinträchtigungs-Schwere-Score (BSS). Ein Instrument zur Bestimmung der Schwere einer psychogenen Erkrankung year: 1995 ident: CIT0082 – ident: CIT0069 doi: 10.1080/10503307.2019.1662510 – ident: CIT0053 doi: 10.1177/2167702618815466 – volume-title: Propensity score analysis: Statistical methods and applications year: 2015 ident: CIT0034 – volume: 45 start-page: 157 issue: 2 year: 1997 ident: CIT0072 publication-title: Zeitschrift für Klinische Psychologie, Psychiatrie und Psychotherapie – volume-title: R: A language and environment for statistical computing year: 2018 ident: CIT0073 – ident: CIT0015 doi: 10.1146/annurev-clinpsy-050817-084746 – ident: CIT0035 doi: 10.1056/NEJMp1006304 – volume-title: Beck depression inventory-II (BDI-II) year: 1996 ident: CIT0005 – volume: 58 start-page: 1399 year: 2009 ident: CIT0031 publication-title: Bundesanzeiger – ident: CIT0008 doi: 10.1016/j.cpr.2005.07.003 – volume-title: Bergin and Garfield`s handbook of psychotherapy and behavior change year: 2020 ident: CIT0055 – ident: CIT0050 doi: 10.1016/S0272-7358(99)00057-4 – volume-title: BSI. Brief Symptom Inventory - Deutsche version. Manual year: 2000 ident: CIT0029 – ident: CIT0042 doi: 10.1126/science.aaa8415 – ident: CIT0003 doi: 10.1001/jama.2017.18391 – ident: CIT0045 doi: 10.1136/bmj.k4245 – ident: CIT0051 doi: 10.1186/s12916-015-0494-1 – ident: CIT0017 doi: 10.1037/cap0000096 – volume-title: SOMS: Das Screening für somatoforme Störungen. Manual zum Fragebogen year: 1997 ident: CIT0075 – ident: CIT0009 doi: 10.1038/nmeth.4642 – ident: CIT0065 doi: 10.1186/1471-2105-10-213 – volume-title: SCL-90-R: Administration, scoring and procedures manual year: 1977 ident: CIT0021 – ident: CIT0060 doi: 10.1038/s41598-018-25953-0 – ident: CIT0010 doi: 10.1038/nmeth.4526 – ident: CIT0091 doi: 10.1017/S0033291718001708 – year: 1954 ident: CIT0064 publication-title: MN: University of Minnesota Press – ident: CIT0083 doi: 10.1177/0011000006295149 – ident: CIT0038 doi: 10.1007/s10608-012-9476-1 – ident: CIT0078 doi: 10.1023/A:1020363010465 – volume: 3 start-page: 6 issue: 3 year: 2011 ident: CIT0092 publication-title: Psychotherapie Aktuell – ident: CIT0089 doi: 10.4324/9780203582015 – ident: CIT0044 doi: 10.1002/da.22731 – ident: CIT0014 doi: 10.1016/j.scitotenv.2018.06.389 – ident: CIT0043 doi: 10.1017/S0033291720000550 – volume-title: Bergin and Garfield’s handbook of psychotherapy and behavior change year: 2013 ident: CIT0049 – ident: CIT0040 doi: 10.1371/journal.pone.0140771 – ident: CIT0016 doi: 10.1080/10503307.2018.1563312 – ident: CIT0084 – ident: CIT0023 doi: 10.1016/j.cpr.2009.08.010 – ident: CIT0020 doi: 10.1037/ccp0000476 – ident: CIT0067 doi: 10.5721/EuJRS20124535 – ident: CIT0056 doi: 10.1002/cpp.496 – ident: CIT0024 doi: 10.1176/appi.ajp.2013.12070899 – ident: CIT0057 doi: 10.1080/10503307.2015.1053553 – ident: CIT0090 doi: 10.1097/00005650-199603000-00003 – ident: CIT0019 doi: 10.1002/da.22755 – ident: CIT0058 doi: 10.1016/j.brat.2019.103438 – ident: CIT0062 doi: 10.1016/j.ijforecast.2018.06.001 – ident: CIT0068 doi: 10.1016/j.brat.2007.12.005 – ident: CIT0036 doi: 10.1002/jclp.20108 – ident: CIT0086 doi: 10.1080/10503307.2013.856046 – volume: 2013 start-page: 298183 year: 2013 ident: CIT0013 publication-title: Evidence-Based Complementary and Alternative Medicine – ident: CIT0079 doi: 10.1016/j.conb.2019.02.006 – ident: CIT0074 doi: 10.1159/000487893 – volume: 5 start-page: 260 issue: 3 year: 1996 ident: CIT0052 publication-title: The Journal of Psychotherapy Practice and Research – ident: CIT0059 doi: 10.1037/1040-3590.18.2.133 – ident: CIT0032 doi: 10.1001/jamapsychiatry.2016.1720 – volume-title: Fragebogen zu körperbezogenen Ängsten, Kognitionen und Vermeidung: AKV year: 2001 ident: CIT0025 – ident: CIT0028 doi: 10.1016/j.brat.2020.103596 – ident: CIT0076 – ident: CIT0006 doi: 10.1016/0272-7358(88)90050-5 – ident: CIT0027 doi: 10.1136/gut.2003.025080 – ident: CIT0063 doi: 10.1371/journal.pone.0194889 – ident: CIT0018 doi: 10.1037/a0013075 – ident: CIT0022 doi: 10.1371/journal.pone.0083875 – ident: CIT0066 doi: 10.1056/NEJMp1606181 – ident: CIT0011 doi: 10.1002/da.22728 – ident: CIT0030 – volume-title: Hamburger Zwangsinventar – Kurzform (HZI-K) year: 1993 ident: CIT0047 – ident: CIT0046 doi: 10.1017/S2045796016000020 – ident: CIT0077 doi: 10.1093/biomet/70.1.41 – ident: CIT0087 doi: 10.1126/science.185.4157.1124 – ident: CIT0088 doi: 10.1017/S0033291719003192 – volume-title: Das Inventar zur Erfassung interpersonaler Probleme (IIP-D). Handanweisung (2. Aufl.) year: 2000 ident: CIT0039 – ident: CIT0080 doi: 10.1055/s-0032-1321781 – ident: CIT0085 doi: 10.1093/bioinformatics/btr597 – ident: CIT0002 doi: 10.1038/nmeth.4438 – ident: CIT0012 doi: 10.1145/1143844.1143865 – ident: CIT0054 doi: 10.1080/10503307.2015.1079661
SSID	ssj0017800
Score	2.5271769
Snippet	Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend... This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal...
SourceID	proquest pubmed crossref informaworld
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	33
SubjectTerms	Algorithms Averages Clinical decision making Cognition Cognitive behavioral therapy Cognitive-behavioral factors Data Decision making Inference Machine learning Medical decision making Medical treatment outcome prediction outpatient psychotherapy Outpatients Patients precision medicine Psychodynamic therapy Psychotherapy random forest Statistical inference Statistics Therapists Training variable selection
Title	Personalized treatment selection in routine care: Integrating machine learning and statistical algorithms to recommend cognitive behavioral or psychodynamic therapy
URI	https://www.tandfonline.com/doi/abs/10.1080/10503307.2020.1769219 https://www.ncbi.nlm.nih.gov/pubmed/32463342 https://www.proquest.com/docview/2474293236 https://www.proquest.com/docview/2407580573
Volume	31
WOSCitedRecordID	wos000541292200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAWR databaseName: Taylor & Francis customDbUrl: eissn: 1468-4381 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017800 issn: 1050-3307 databaseCode: TFW dateStart: 19910701 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3LTtwwFLUoYtFNW0QfUx66lbpNlbEdP9hVVUdlg1hQdXaRx7HpSEyCkoAE39MP7bXjBFggFu0qUhI7jn1tH9vnnkvIZ22VUN6zzFAnM84ZzQxXeSa94p5WzsjKxGAT8vRULZf6LLEJu0SrDGtoPwhFxLE6dG6z6kZGHF7D2VsucXVH8ZYUmkbhT5z6Q9c8X_yazhGkygc9ggJHG0wy-vA8lcuj2emRdunTCDTORIvX_-Ef3pBXCYbC18FudsmWq_fIn7MRmd-5CiYKOnQxVg42IKxraBs01dpBoIwdw0lSm8AJEDaRl-kgBaK4ACwcBIelqAWNXzOXF0277n9vOugbCEvxDeZfwURhgnvRAGhaGDzEqtvabNYWBk-x27fk5-L7-bcfWYrikFku8j4wWQqhEXZ6YVcrXwiHEEUIg9BKUC-cmXNvFXOeK4dY0lsnfJXrXFOjtJvn7B3ZrpvafSAgnODaaM6stmhVc20ko95xUyhRqULPCB9br7RJ4jxE2rgs50kJdaz2MlR7map9Rr5Mya4GjY_nEuiHplH2cXPFD5FQSvZM2oPRjso0XHQl5RJxAaNMzMin6TF29HB6Y2rXXId3EN2poF85I-8H-5tKi6hYMMbpx38o2D55SQNfJ24vHZDtvr12h2TH3qCVtEfkhVyqo9i5_gJViSCr
linkProvider	Taylor & Francis
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQQYILFPHa0scgcQ3K2o4f3KqKVauWFYdF9Ga5jl1W6iYomyK1v4cfyth50B6qHsopUpJxHHvs-WzPfEPIR-2UUCGwzFIvM84ZzSxXeSaD4oGW3srSpmQTcj5Xp6f6ZixMdKuMa-jQEUWkuToO7rgZPbjE4TUevuUSl3cUb0mhaWT-fFygrY38-YvZj_EkQaq8YyQocL5BmSGK565ibtmnW-yld2PQZItmL_7HX2yS5z0Shf1OdV6SR756Rf58G8D5tS9h9EKHdUqXg30IywqaGrW18hC9xj7DUU84gTYQVsk100Ofi-IcsHYQY5YSHTR-zV6c182y_blaQ1tDXI2vsPwSRi8m-McbAHUDXZBYeVXZ1dJBFyx29Zp8n31ZHBxmfSKHzHGRt9GZpRAakWcQ7uwsFMIjShHCIroSNAhvpzw4xXzgyiOcDM6LUOY619Qq7ac5e0M2qrry7wgIL7i2mjOnHSrWVFvJaPDcFkqUqtATwofuM65nOY_JNi7MtCdDHZrdxGY3fbNPyKdR7FdH83GfgL6pG6ZN-yuhS4Zi2D2y24MimX7GWBvKJUIDRpmYkA_jYxzr8QDHVr6-jO8gwFORwnJC3nYKONYWgbFgjNOtB1Rsjzw9XHw9MSdH8-P35BmN7jtpt2mbbLTNpd8hT9xv1JhmN42xv7suI-0
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3LbtQwFLVQQYgND_HolAIXiW1Qxnb8YIeAERVoNIsiurNcxy4jdZIqkyK138OHcu04gS6qLmAVKYkdx762j-1zzyXkjXZKqBBYYamXBeeMFparspBB8UBrb2VtU7AJuVyqoyO9ymzCbaZVxjV0GIQi0lgdO_dZHUZGHF7j2VspcXVH8ZYUmkbhz9sInUU08sPF9-kgQapyECSocLjBNKMTz3XZXJmeroiXXg9B01S0ePAffuIhuZ9xKLwfDOcRueWbx-TXaoTml76GiYMO2xQsB1sQ1g10Ldpq4yFyxt7BQZabwBkQNomY6SFHojgBLBxEj6UkBo1fs6cnbbfuf2y20LcQ1-IbzL-GicMEf1QDoO1gcBGrLxq7WTsYXMUunpBvi0-HHz4XOYxD4bgo-0hlqYRG3BmEOz4OlfCIUYSwiK0EDcLbOQ9OMR-48ggmg_Mi1KUuNbVK-3nJnpKdpm38LgHhBddWc-a0Q7OaaysZDZ7bSolaVXpG-Nh6xmWN8xhq49TMsxTqWO0mVrvJ1T4jb6dkZ4PIx00J9N-mYfq0uxKGUCiG3ZB2f7Qjk8eLraFcIjBglIkZeT09xp4ej29s49vz-A7COxUFLGfk2WB_U2kRFgvGON37h4K9IndXHxfm68Hyy3Nyj0buTtpq2ic7fXfuX5A77icaTPcy9bDfLZEinw
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=Personalized+treatment+selection+in+routine+care%3A+Integrating+machine+learning+and+statistical+algorithms+to+recommend+cognitive+behavioral+or+psychodynamic+therapy&rft.jtitle=Psychotherapy+research&rft.au=Schwartz%2C+Brian&rft.au=Cohen%2C+Zachary+D&rft.au=Rubel%2C+Julian+A&rft.au=Zimmermann%2C+Dirk&rft.date=2021&rft.eissn=1468-4381&rft.volume=31&rft.issue=1&rft.spage=33&rft_id=info:doi/10.1080%2F10503307.2020.1769219&rft_id=info%3Apmid%2F32463342&rft.externalDocID=32463342
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1050-3307&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1050-3307&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1050-3307&client=summon