Improving pre-bariatric surgery diagnosis of hiatal hernia using machine learning models.

Bariatric patients have a high prevalence of hiatal hernia (HH). HH imposes various difficulties in performing laparoscopic bariatric surgery. Preoperative evaluation is generally inaccurate, establishing the need for better preoperative assessment. To utilize machine learning ability to improve pre...

Descripción completa

Detalles Bibliográficos
Publicado en:Minimally Invasive Therapy & Allied Technologies Vol. 31; no. 5; pp. 760 - 768
Autores principales: Assaf, Dan, Rayman, Shlomi, Segev, Lior, Neuman, Yair, Zippel, Douglas, Goitein, David
Formato: research tables/charts Journal Article
Publicado: Taylor & Francis Ltd Jun2022
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=157509038&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 157509038
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        13645706
        J4S
      jtl: Minimally Invasive Therapy & Allied Technologies
      issn: 13645706
      maglogo: Y
    pubinfo:
      dt: Jun2022
      vid: 31
      iid: 5
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        157509038
        149506400
        157509038
        157509038
        10.1080/13645706.2021.1901120
        157509038
      ppf: 760
      ppct: 8
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Improving pre-bariatric surgery diagnosis of hiatal hernia using machine learning models.
      aug:
        au:
          Assaf, Dan
          Rayman, Shlomi
          Segev, Lior
          Neuman, Yair
          Zippel, Douglas
          Goitein, David
        affil: Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
      sug:
        subj:
          Bariatric Surgery
          Hernia, Diaphragmatic Diagnosis
          Machine Learning Utilization
          Preoperative Period
          Length of Stay
          Human
          Male
          Female
          Adult
          Middle Age
          Israel
          Anthropometry
          Decision Trees
          Hospitalization
          Retrospective Design
          Data Analysis Software
          ROC Curve
          Sensitivity and Specificity
          Descriptive Statistics
          Adult: 19-44 years
          Middle Aged: 45-64 years
          Male
          Female
      ab: Bariatric patients have a high prevalence of hiatal hernia (HH). HH imposes various difficulties in performing laparoscopic bariatric surgery. Preoperative evaluation is generally inaccurate, establishing the need for better preoperative assessment. To utilize machine learning ability to improve preoperative diagnosis of HH. Machine learning (ML) prediction models were utilized to predict preoperative HH diagnosis using data from a prospectively maintained database of bariatric procedures performed in a high-volume bariatric surgical center between 2012 and 2015. We utilized three optional ML models to improve preoperative contrast swallow study (SS) prediction, automatic feature selection was performed using patients' features. The prediction efficacy of the models was compared to SS. During the study period, 2482 patients underwent bariatric surgery. All underwent preoperative SS, considered the baseline diagnostic modality, which identified 236 (9.5%) patients with presumed HH. Achieving 38.5% sensitivity and 92.9% specificity. ML models increased sensitivity up to 60.2%, creating three optional models utilizing data and patient selection process for this purpose. Implementing machine learning derived prediction models enabled an increase of up to 1.5 times of the baseline diagnostic sensitivity. By harnessing this ability, we can improve traditional medical diagnosis, increasing the sensitivity of preoperative diagnostic workout.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N