Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

When Predictive Models Collide

When Predictive Models Collide commentaries 1 2 3 Peter D. Stetson, MD, MA ; Michael N. Cantor, MD, MA ; and Mithat Gonen, PhD PREDICTIVE MODELS RISING “multimorbid”), with the potential for contradictory or even detrimental recommendations when each model No trend is more visible in medicine than integrating is applied individually, rather than taking into account machine learning and artificial intelligence (AI) into the overall clinical context. Recent, high-profile ex- clinical care. Terms like “random forests” and “con- amples of conflicting guidelines include the differ- volutional neural networks” that were previously the ences among the Veterans Administration, American domain of computer science PhDs are now part of the Diabetes Association, and American Society of Clinical vocabulary of both C-suite administrators and front- Endocrinologists for managing diabetes and the US line clinicians. As the high-performance storage and Preventive Services Task Force, American Congress computing power that underlie these models become of Obstetricians, and American College of Surgeons a commodity, both the supply and demand for predictive recommendations for mammography. models based on machine learning will only increase. Advances in genomics and patient-generated health One approach to managing these conflicts is identi- data will enrich predictive models, but will also increase fying and targeting http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JCO Clinical Cancer Informatics Wolters Kluwer Health

When Predictive Models Collide

Download PDF
4 pages

Loading next page...
 
/lp/wolters-kluwer-health/when-predictive-models-collide-6RzrG49nWD

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Wolters Kluwer Health
Copyright
(C) 2020 American Society of Clinical Oncology
ISSN
2473-4276
DOI
10.1200/CCI.20.00024
Publisher site
See Article on Publisher Site

Abstract

commentaries 1 2 3 Peter D. Stetson, MD, MA ; Michael N. Cantor, MD, MA ; and Mithat Gonen, PhD PREDICTIVE MODELS RISING “multimorbid”), with the potential for contradictory or even detrimental recommendations when each model No trend is more visible in medicine than integrating is applied individually, rather than taking into account machine learning and artificial intelligence (AI) into the overall clinical context. Recent, high-profile ex- clinical care. Terms like “random forests” and “con- amples of conflicting guidelines include the differ- volutional neural networks” that were previously the ences among the Veterans Administration, American domain of computer science PhDs are now part of the Diabetes Association, and American Society of Clinical vocabulary of both C-suite administrators and front- Endocrinologists for managing diabetes and the US line clinicians. As the high-performance storage and Preventive Services Task Force, American Congress computing power that underlie these models become of Obstetricians, and American College of Surgeons a commodity, both the supply and demand for predictive recommendations for mammography. models based on machine learning will only increase. Advances in genomics and patient-generated health One approach to managing these conflicts is identi- data will enrich predictive models, but will also increase fying and targeting

Journal

JCO Clinical Cancer Informatics – Wolters Kluwer Health

Published: Jun 16, 2020

References

  • Oncologist use and perception of large panel next-generation tumor sequencing
    Schram AM; Reales D; Galle J
  • Nodal staging score: A tool to assess adequate staging of node-negative colon cancer
    Gonen M; Schrag D; Weiser MR
  • A preoperative nomogram for disease recurrence following radical prostatectomy for prostate cancer
    Kattan MW; Eastham JA; Stapleton AM
  • Lifetime risk for development of atrial fibrillation: The Framingham Heart Study
    Lloyd-Jones DM; Wang TJ; Leip EP
  • Combination of prostate-specific antigen, clinical stage, and Gleason score to predict pathological stage of localized prostate cancer
    Partin AW; Kattan MW; Subong EN
  • Dynamic contrast-enhanced MRI model selection for predicting tumor aggressiveness in papillary thyroid cancers
    Paudyal R; Lu Y; Hatzoglou V
  • Multi-institutional development and external validation of a nomogram to predict recurrence after curative resection of pancreatic neuroendocrine tumors
    Pulvirenti A; Javed AA; Landoni L
  • Radiomics-based prediction of microsatellite instability in colorectal cancer at initial computed tomography evaluation
    Golia Pernicka JS; Gagniere J; Chakraborty J
  • Concordance rate between clinicians and Watson for oncology among patients with advanced gastric cancer: Early, real-world experience in Korea
    Choi YI; Chung JW; Kim KO
  • Assessing concordance with Watson for oncology, a cognitive computing decision support system for colon cancer treatment in Korea
    Lee WS; Ahn SM; Chung JW
  • Watson for oncology and breast cancer treatment recommendations: Agreement with an expert multidisciplinary tumor board
    Somashekhar SP; Sepulveda MJ; Puglielli S
  • Concordance study between IBM Watson for oncology and clinical practice for patients with cancer in China
    Zhou N; Zhang CT; Lv HY
  • Gene expression assay and Watson for oncology for optimization of treatment in ER-positive, HER2-negative breast cancer
    Kim YY; Oh SJ; Chun YS
  • Clinical practice guidelines and quality of care for older patients with multiple comorbid diseases: Implications for pay for performance
    Boyd CM; Darer J; Boult C
  • When clinical practice guidelines collide: Finding a way forward
    Greenfield S; Kaplan SH
  • Personalized estimates of benefit from preventive care guidelines: A proof of concept
    Taksler GB; Keshner M; Fagerlin A
  • Explainable artificial intelligence for safe intraoperative decision support
    Gordon L; Grantcharov T; Rudzicz F
  • Explainable machine-learning predictions for the prevention of hypoxaemia during surgery
    Lundberg SM; Nair B; Vavilala MS
  • explAIner: A visual analytics framework for interactive and explainable machine learning
    Spinner T; Schlegel U; Schafer H
  • Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models
    Zhang J; Wang Y; Molino P
  • Artificial intelligence in health care: Insights from an educational forum
    Barbour AB; Frush JM; Gatta LA
  • Assessing the performance of prediction models: A framework for traditional and novel measures
    Steyerberg EW; Vickers AJ; Cook NR
  • A lesson in implementation: A pre-post study of providers' experience with artificial intelligence-based clinical decision support
    Romero-Brufau S; Wyatt KD; Boyum P
  • Artificial intelligence and clinical decision support for radiologists and referring providers
    Bizzo BC; Almeida RR; Michalski MH