Utility of Machine Learning, Natural Language Processing, and Artificial Intelligence in Predicting Hospital Readmissions After Orthopaedic Surgery: A Systematic Review and Meta-Analysis
Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent...
Uložené v:
| Vydané v: | JBJS reviews Ročník 12; číslo 8 |
|---|---|
| Hlavní autori: | , , , , , , , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
01.08.2024
|
| Predmet: | |
| ISSN: | 2329-9185, 2329-9185 |
| On-line prístup: | Zistit podrobnosti o prístupe |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent to which natural language processing, machine learning, and artificial intelligence (AI) can help improve the predictability of hospital readmissions after orthopaedic and spine surgeries.
This is a systematic review and meta-analysis. PubMed, Embase and Google Scholar were searched, up until August 30, 2023, for studies that explore the use of AI, natural language processing, and machine learning tools for the prediction of readmission rates after orthopedic procedures. Data regarding surgery type, patient population, readmission outcomes, advanced models utilized, comparison methods, predictor sets, the inclusion of perioperative predictors, validation method, size of training and testing sample, accuracy, and receiver operating characteristics (C-statistic), among other factors, were extracted and assessed.
A total of 26 studies were included in our final dataset. The overall summary C-statistic showed a mean of 0.71 across all models, indicating a reasonable level of predictiveness. A total of 15 articles (57%) were attributed to the spine, making it the most commonly explored orthopaedic field in our study. When comparing accuracy of prediction models between different fields, models predicting readmissions after hip/knee arthroplasty procedures had a higher prediction accuracy (mean C-statistic = 0.79) than spine (mean C-statistic = 0.7) and shoulder (mean C-statistic = 0.67). In addition, models that used single institution data, and those that included intraoperative and/or postoperative outcomes, had a higher mean C-statistic than those utilizing other data sources, and that include only preoperative predictors. According to the Prediction model Risk of Bias Assessment Tool, the majority of the articles in our study had a high risk of bias.
AI tools perform reasonably well in predicting readmissions after orthopaedic procedures. Future work should focus on standardizing study methodologies and designs, and improving the data analysis process, in an attempt to produce more reliable and tangible results.
Level III. See Instructions for Authors for a complete description of levels of evidence. |
|---|---|
| AbstractList | Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent to which natural language processing, machine learning, and artificial intelligence (AI) can help improve the predictability of hospital readmissions after orthopaedic and spine surgeries.BACKGROUNDNumerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent to which natural language processing, machine learning, and artificial intelligence (AI) can help improve the predictability of hospital readmissions after orthopaedic and spine surgeries.This is a systematic review and meta-analysis. PubMed, Embase and Google Scholar were searched, up until August 30, 2023, for studies that explore the use of AI, natural language processing, and machine learning tools for the prediction of readmission rates after orthopedic procedures. Data regarding surgery type, patient population, readmission outcomes, advanced models utilized, comparison methods, predictor sets, the inclusion of perioperative predictors, validation method, size of training and testing sample, accuracy, and receiver operating characteristics (C-statistic), among other factors, were extracted and assessed.METHODSThis is a systematic review and meta-analysis. PubMed, Embase and Google Scholar were searched, up until August 30, 2023, for studies that explore the use of AI, natural language processing, and machine learning tools for the prediction of readmission rates after orthopedic procedures. Data regarding surgery type, patient population, readmission outcomes, advanced models utilized, comparison methods, predictor sets, the inclusion of perioperative predictors, validation method, size of training and testing sample, accuracy, and receiver operating characteristics (C-statistic), among other factors, were extracted and assessed.A total of 26 studies were included in our final dataset. The overall summary C-statistic showed a mean of 0.71 across all models, indicating a reasonable level of predictiveness. A total of 15 articles (57%) were attributed to the spine, making it the most commonly explored orthopaedic field in our study. When comparing accuracy of prediction models between different fields, models predicting readmissions after hip/knee arthroplasty procedures had a higher prediction accuracy (mean C-statistic = 0.79) than spine (mean C-statistic = 0.7) and shoulder (mean C-statistic = 0.67). In addition, models that used single institution data, and those that included intraoperative and/or postoperative outcomes, had a higher mean C-statistic than those utilizing other data sources, and that include only preoperative predictors. According to the Prediction model Risk of Bias Assessment Tool, the majority of the articles in our study had a high risk of bias.RESULTSA total of 26 studies were included in our final dataset. The overall summary C-statistic showed a mean of 0.71 across all models, indicating a reasonable level of predictiveness. A total of 15 articles (57%) were attributed to the spine, making it the most commonly explored orthopaedic field in our study. When comparing accuracy of prediction models between different fields, models predicting readmissions after hip/knee arthroplasty procedures had a higher prediction accuracy (mean C-statistic = 0.79) than spine (mean C-statistic = 0.7) and shoulder (mean C-statistic = 0.67). In addition, models that used single institution data, and those that included intraoperative and/or postoperative outcomes, had a higher mean C-statistic than those utilizing other data sources, and that include only preoperative predictors. According to the Prediction model Risk of Bias Assessment Tool, the majority of the articles in our study had a high risk of bias.AI tools perform reasonably well in predicting readmissions after orthopaedic procedures. Future work should focus on standardizing study methodologies and designs, and improving the data analysis process, in an attempt to produce more reliable and tangible results.CONCLUSIONAI tools perform reasonably well in predicting readmissions after orthopaedic procedures. Future work should focus on standardizing study methodologies and designs, and improving the data analysis process, in an attempt to produce more reliable and tangible results.Level III. See Instructions for Authors for a complete description of levels of evidence.LEVEL OF EVIDENCELevel III. See Instructions for Authors for a complete description of levels of evidence. Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent to which natural language processing, machine learning, and artificial intelligence (AI) can help improve the predictability of hospital readmissions after orthopaedic and spine surgeries. This is a systematic review and meta-analysis. PubMed, Embase and Google Scholar were searched, up until August 30, 2023, for studies that explore the use of AI, natural language processing, and machine learning tools for the prediction of readmission rates after orthopedic procedures. Data regarding surgery type, patient population, readmission outcomes, advanced models utilized, comparison methods, predictor sets, the inclusion of perioperative predictors, validation method, size of training and testing sample, accuracy, and receiver operating characteristics (C-statistic), among other factors, were extracted and assessed. A total of 26 studies were included in our final dataset. The overall summary C-statistic showed a mean of 0.71 across all models, indicating a reasonable level of predictiveness. A total of 15 articles (57%) were attributed to the spine, making it the most commonly explored orthopaedic field in our study. When comparing accuracy of prediction models between different fields, models predicting readmissions after hip/knee arthroplasty procedures had a higher prediction accuracy (mean C-statistic = 0.79) than spine (mean C-statistic = 0.7) and shoulder (mean C-statistic = 0.67). In addition, models that used single institution data, and those that included intraoperative and/or postoperative outcomes, had a higher mean C-statistic than those utilizing other data sources, and that include only preoperative predictors. According to the Prediction model Risk of Bias Assessment Tool, the majority of the articles in our study had a high risk of bias. AI tools perform reasonably well in predicting readmissions after orthopaedic procedures. Future work should focus on standardizing study methodologies and designs, and improving the data analysis process, in an attempt to produce more reliable and tangible results. Level III. See Instructions for Authors for a complete description of levels of evidence. |
| Author | Khan, Adam Z da Silva Etges, Ana Paula Beck Best, Matthew J Warner, Jon J P Sanders, Brett Costouros, John G Jones, Porter Fares, Mohamad Y Simon, Jason E Zhang, Benjamin Fedorka, Catherine J Haas, Derek A Zhang, Xiaoran Liu, Harry H Olson, Jeffrey J Kirsch, Jacob M Abboud, Joseph A |
| Author_xml | – sequence: 1 givenname: Mohamad Y orcidid: 0000-0001-8228-3953 surname: Fares fullname: Fares, Mohamad Y organization: Rothman Institute, Thomas Jefferson University Hospital, Philadelphia, Pennsylvania – sequence: 2 givenname: Harry H orcidid: 0009-0006-2637-4336 surname: Liu fullname: Liu, Harry H organization: Avant-garde Health, Boston, Massachusetts – sequence: 3 givenname: Ana Paula Beck orcidid: 0000-0002-6411-3480 surname: da Silva Etges fullname: da Silva Etges, Ana Paula Beck organization: Avant-garde Health, Boston, Massachusetts – sequence: 4 givenname: Benjamin orcidid: 0000-0003-2546-6790 surname: Zhang fullname: Zhang, Benjamin organization: Brigham and Women's Hospital, Boston, Massachusetts – sequence: 5 givenname: Jon J P orcidid: 0000-0002-2563-6318 surname: Warner fullname: Warner, Jon J P organization: Department of Orthopaedic Surgery, Harvard Medical School, Boston Shoulder Institute, Massachusetts General Hospital, Boston, Massachusetts – sequence: 6 givenname: Jeffrey J orcidid: 0000-0003-2176-1522 surname: Olson fullname: Olson, Jeffrey J organization: Hartford Healthcare, Hartford, Connecticut – sequence: 7 givenname: Catherine J orcidid: 0000-0002-8566-912 surname: Fedorka fullname: Fedorka, Catherine J organization: Cooper Bone and Joint Institute, Cooper University Hospital, Camden, New Jersey – sequence: 8 givenname: Adam Z orcidid: 0000-0002-7251-6503 surname: Khan fullname: Khan, Adam Z organization: Department of Orthopaedic Surgery, Southern California Permanente Medical Group, Panorama City, California – sequence: 9 givenname: Matthew J orcidid: 0000-0002-4401-2834 surname: Best fullname: Best, Matthew J organization: Department of Orthopaedic Surgery, Johns Hopkins Hospital, Johns Hopkins University School of Medicine, Baltimore, Maryland – sequence: 10 givenname: Jacob M orcidid: 0000-0002-1368-3512 surname: Kirsch fullname: Kirsch, Jacob M organization: Department of Orthopaedic Surgery, New England Baptist Hospital, Tufts University School of Medicine, Boston, Massachusetts – sequence: 11 givenname: Jason E orcidid: 0000-0002-1229-9586 surname: Simon fullname: Simon, Jason E organization: Department of Orthopaedic Surgery, Massachusetts General Hospital/Newton-Wellesley Hospital, Boston, Massachusetts – sequence: 12 givenname: Brett surname: Sanders fullname: Sanders, Brett organization: Center for Sports Medicine and Orthopaedics, Chattanooga, Tennessee – sequence: 13 givenname: John G orcidid: 0000-0003-4939-6192 surname: Costouros fullname: Costouros, John G organization: Institute for Joint Restoration and Research, California Shoulder Center, Menlo Park, California – sequence: 14 givenname: Xiaoran orcidid: 0000-0002-4180-6567 surname: Zhang fullname: Zhang, Xiaoran organization: Avant-garde Health, Boston, Massachusetts – sequence: 15 givenname: Porter orcidid: 0009-0004-5618-5750 surname: Jones fullname: Jones, Porter organization: Avant-garde Health, Boston, Massachusetts – sequence: 16 givenname: Derek A orcidid: 0000-0001-5395-7306 surname: Haas fullname: Haas, Derek A organization: Avant-garde Health, Boston, Massachusetts – sequence: 17 givenname: Joseph A orcidid: 0000-0002-3845-7220 surname: Abboud fullname: Abboud, Joseph A organization: Rothman Institute, Thomas Jefferson University Hospital, Philadelphia, Pennsylvania |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/39172864$$D View this record in MEDLINE/PubMed |
| BookMark | eNpN0EtP3DAQAGCroioU-AG9IB97IFs_EjvuLUW0gJaHdkt7XHmdcTDKOlvbaZW_1l-HeUmcPPJ8M6OZj2jHDx4Q-kTJjFEivlx8u1jOFr9-z1g5I4TI6h3aY5ypQtG62nkT76LDGO8zoVwwKsgHtMsVlawW5R76f5tc79KEB4svtblzHvAcdPDOd8f4Sqcx6B7Pte9G3QG-CYOBGJ-S2re4CclZZ1w25z5B37sOvAHsfKbQOpMyxWdD3LqUzQJ0u3G5fvARNzZBwNch3Q1b_WjxcgwdhOkrbvByigk2OuXfBfx18O9p3CUkXTRe91N08QC9t7qPcPjy7qPb76c_T86K-fWP85NmXhheyqqoqjWXtuXKUmqVKImoq7KsudEl45ZQYqVolTRaroWitObUtLyuJKg1qa21bB99fu67DcOfEWJa5RVM3lV7GMa44kQJJpUgNNOjFzquN9CutsFtdJhWr_dmD1Fuh8s |
| CitedBy_id | crossref_primary_10_1016_j_jham_2025_100257 crossref_primary_10_1302_2633_1462_66_BJO_2024_0257_R1 crossref_primary_10_1007_s10143_025_03783_9 |
| ContentType | Journal Article |
| Contributor | Armstrong, April D Gottschalk, Michael B Mazzocca, Augustus O'Donnell, Evan A Updegrove, Gary F Stieler, Evan Woodmass, Jarret Belniak, Robert M Wagner, Eric R MacDonald, Peter Makhni, Eric C Srikumaran, Uma |
| Contributor_xml | – sequence: 1 givenname: April D surname: Armstrong fullname: Armstrong, April D – sequence: 2 givenname: Robert M surname: Belniak fullname: Belniak, Robert M – sequence: 3 givenname: Michael B surname: Gottschalk fullname: Gottschalk, Michael B – sequence: 4 givenname: Eric C surname: Makhni fullname: Makhni, Eric C – sequence: 5 givenname: Augustus surname: Mazzocca fullname: Mazzocca, Augustus – sequence: 6 givenname: Peter surname: MacDonald fullname: MacDonald, Peter – sequence: 7 givenname: Evan A surname: O'Donnell fullname: O'Donnell, Evan A – sequence: 8 givenname: Uma surname: Srikumaran fullname: Srikumaran, Uma – sequence: 9 givenname: Evan surname: Stieler fullname: Stieler, Evan – sequence: 10 givenname: Gary F surname: Updegrove fullname: Updegrove, Gary F – sequence: 11 givenname: Eric R surname: Wagner fullname: Wagner, Eric R – sequence: 12 givenname: Jarret surname: Woodmass fullname: Woodmass, Jarret |
| Copyright | Copyright © 2024 by The Journal of Bone and Joint Surgery, Incorporated. |
| Copyright_xml | – notice: Copyright © 2024 by The Journal of Bone and Joint Surgery, Incorporated. |
| CorporateAuthor | Avant-Garde Health and Codman Society Value-Based Care Group |
| CorporateAuthor_xml | – name: Avant-Garde Health and Codman Society Value-Based Care Group |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.2106/JBJS.RVW.24.00075 |
| 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 |
| EISSN | 2329-9185 |
| ExternalDocumentID | 39172864 |
| Genre | Meta-Analysis Systematic Review Journal Article |
| GroupedDBID | 0R~ 53G AAAAV AAAXR AAFTM AAGIX AAHPQ AAIQE AAMOA AAQKA AASCR AAXQO ABASU ABDIG ABJNI ABPMR ABPXF ABVCZ ABXVJ ABZZY ACBKD ACEWG ACGFS ACILI ACLDA ACNWC ACXJB ACZKN ADGGA ADHPY ADKSD ADSXY AFBFQ AFDTB AFMFG AFUWQ AHOMT AHQNM AIJEX AINUH AJCLO AJIOK AJNWD AJZMW AKCTQ AKULP ALKUP ALMA_UNASSIGNED_HOLDINGS ALMTX AMJPA AMKUR AMNEI AOHHW AOQMC BOWHD BQLVK BYPQX C45 CGR CUY CVF DIWNM EBS ECM EEVPB EIF ERAAH FCALG GNXGY GQDEL HLJTE IKREB IKYAY NPM O9- OGEVE OPUJH OVD OVDNE OVIDH OVLEI OXXIT RLZ TEORI TJB TSPGW W1K 7X8 |
| ID | FETCH-LOGICAL-c3475-55b37fd39f11f96406854483ca423f010f76d97ca7b6911831cd3857e9b08fff2 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001292444800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2329-9185 |
| IngestDate | Mon Sep 08 12:11:20 EDT 2025 Sat Oct 25 06:00:14 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| License | Copyright © 2024 by The Journal of Bone and Joint Surgery, Incorporated. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3475-55b37fd39f11f96406854483ca423f010f76d97ca7b6911831cd3857e9b08fff2 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Undefined-3 |
| ORCID | 0000-0002-2563-6318 0000-0002-1229-9586 0000-0002-6411-3480 0000-0001-8228-3953 0000-0002-4180-6567 0009-0004-5618-5750 0000-0003-2176-1522 0009-0006-2637-4336 0000-0002-1368-3512 0000-0002-3845-7220 0000-0003-2546-6790 0000-0002-4401-2834 0000-0002-8566-912 0000-0002-7251-6503 0000-0003-4939-6192 0000-0001-5395-7306 |
| PMID | 39172864 |
| PQID | 3096279601 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3096279601 pubmed_primary_39172864 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-08-01 |
| PublicationDateYYYYMMDD | 2024-08-01 |
| PublicationDate_xml | – month: 08 year: 2024 text: 2024-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | JBJS reviews |
| PublicationTitleAlternate | JBJS Rev |
| PublicationYear | 2024 |
| SSID | ssj0001362160 |
| Score | 2.301786 |
| SecondaryResourceType | review_article |
| Snippet | Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| SubjectTerms | Artificial Intelligence Humans Machine Learning Natural Language Processing Orthopedic Procedures - adverse effects Patient Readmission - statistics & numerical data |
| Title | Utility of Machine Learning, Natural Language Processing, and Artificial Intelligence in Predicting Hospital Readmissions After Orthopaedic Surgery: A Systematic Review and Meta-Analysis |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/39172864 https://www.proquest.com/docview/3096279601 |
| Volume | 12 |
| WOSCitedRecordID | wos001292444800002&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/eLvHCXMwpV3JTsMwELXYDlxYxL5pkDgSiOM4driggkCAaEGUpbfK8QJcUqAFiV_j6xg7KXBBQuKSS-Is8vjlzeI3hGwpqhVVzkapKXSUFgniYGEk2rIyijOTK1WEZhOi1ZKdTn5ZB9z6dVnlEBMDUJue9jHyXRb7NjHIt-n-03Pku0b57GrdQmOUjDOkMn5hio78jrEgOtOwURh5Q47rWvIqsYl-TrZ7dnDW3rm6vdtJvIB2LPjvJDP8bI6n__uaM2SqppnQqOxilozYco583Ax8Jew79Bw0QxGlhVpf9X4bWipIcMB5HcGEeg9BOKlKE25W6U3A6Q8hT3gs8VKf7_EV1DBsRAK-PB-NyEfj-tDwrcjh4mXwgE66vxba1X7sPWhA-0tNGqpURXhc0w5UNNRMmSc3x0fXhydR3bsh0iwVPOK8YMIZljtKXZ4hbZAcPUGmFfI3h06gE5nJhVaiyBBvJaPaMMmFzYtYOueSBTJW9kq7RCA1VHNrXWqyAhHG5RbHpdTwONaOW75MNodT0cXP8gkPVdrea7_7PRnLZLGaz-5TJeLRRWsRiczSlT-MXiWTCXKZqu5vjYw7RAa7Tib02-Cx_7IRjA6PrcvmJ_fZ5UE |
| 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=Utility+of+Machine+Learning%2C+Natural+Language+Processing%2C+and+Artificial+Intelligence+in+Predicting+Hospital+Readmissions+After+Orthopaedic+Surgery%3A+A+Systematic+Review+and+Meta-Analysis&rft.jtitle=JBJS+reviews&rft.au=Fares%2C+Mohamad+Y&rft.au=Liu%2C+Harry+H&rft.au=da+Silva+Etges%2C+Ana+Paula+Beck&rft.au=Zhang%2C+Benjamin&rft.date=2024-08-01&rft.issn=2329-9185&rft.eissn=2329-9185&rft.volume=12&rft.issue=8&rft_id=info:doi/10.2106%2FJBJS.RVW.24.00075&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2329-9185&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2329-9185&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2329-9185&client=summon |