BACKGROUND: 20%-25% of patients with primary hyperparathyroidism will have multigland disease (MGD). Preoperatative imaging can be inaccurate or unnecessary in MGD. Identification of MGD could direct the need for imaging and inform operative approach. The purpose of this study is to use machine learning (ML) methods to predict MGD. METHODS: Retrospective review of a prospective database. The ML platform, Waikato Environment for Knowledge Analysis, was used, and we selected models for (1) overall accuracy and (2) preferential identification of MGD. A review of imaging studies was performed on a cohort predicted to have MGD. RESULTS: 2010 patients met inclusion criteria: 1532 patients had single adenoma (SA) (76%) and 478 had MGD (24%). After testing many algorithms, we selected two different models for potential integration as clinical decision-support tools. The best overall accuracy was achieved using a boosted tree classifier, RandomTree: 94.1% accuracy; 94.1% sensitivity, 83.8% specificity, 94.1% positive predictive value, and 0.984 area under the receiver operating characteristics curve. To maximize positive predictive value of MGD prediction, a rule-based classifier, JRip, with cost-sensitive learning was used and achieved 100% positive predictive value for MGD. Imaging reviewed from the cohort of 34 patients predicted to have MGD by the cost-sensitive model revealed 39 total studies performed: 28 sestamibi scans and 11 ultrasounds. Only 8 (29%) sestamibi scans and 4 (36%) ultrasounds were correct. CONCLUSIONS: ML methods can help distinguish MGD early in the clinical evaluation of primary hyperparathyroidism, guiding further workup and surgical planning.
BACKGROUND: 20%-25% of patients with primary hyperparathyroidism will have multigland disease (MGD). Preoperatative imaging can be inaccurate or unnecessary in MGD. Identification of MGD could direct the need for imaging and inform operative approach. The purpose of this study is to use machine learning (ML) methods to predict MGD. METHODS: Retrospective review of a prospective database. The ML platform, Waikato Environment for Knowledge Analysis, was used, and we selected models for (1) overall accuracy and (2) preferential identification of MGD. A review of imaging studies was performed on a cohort predicted to have MGD. RESULTS: 2010 patients met inclusion criteria: 1532 patients had single adenoma (SA) (76%) and 478 had MGD (24%). After testing many algorithms, we selected two different models for potential integration as clinical decision-support tools. The best overall accuracy was achieved using a boosted tree classifier, RandomTree: 94.1% accuracy; 94.1% sensitivity, 83.8% specificity, 94.1% positive predictive value, and 0.984 area under the receiver operating characteristics curve. To maximize positive predictive value of MGD prediction, a rule-based classifier, JRip, with cost-sensitive learning was used and achieved 100% positive predictive value for MGD. Imaging reviewed from the cohort of 34 patients predicted to have MGD by the cost-sensitive model revealed 39 total studies performed: 28 sestamibi scans and 11 ultrasounds. Only 8 (29%) sestamibi scans and 4 (36%) ultrasounds were correct. CONCLUSIONS: ML methods can help distinguish MGD early in the clinical evaluation of primary hyperparathyroidism, guiding further workup and surgical planning.
Authors: William R Hendee; Gary J Becker; James P Borgstede; Jennifer Bosma; William J Casarella; Beth A Erickson; C Douglas Maynard; James H Thrall; Paul E Wallner Journal: Radiology Date: 2010-08-24 Impact factor: 11.105
Authors: Scott M Wilhelm; Tracy S Wang; Daniel T Ruan; James A Lee; Sylvia L Asa; Quan-Yang Duh; Gerard M Doherty; Miguel F Herrera; Janice L Pasieka; Nancy D Perrier; Shonni J Silverberg; Carmen C Solórzano; Cord Sturgeon; Mitchell E Tublin; Robert Udelsman; Sally E Carty Journal: JAMA Surg Date: 2016-10-01 Impact factor: 14.766
Authors: Olov Norlén; Anthony Glover; Nisar Zaidi; Adam Aniss; Mark Sywak; Stan Sidhu; Leigh Delbridge Journal: World J Surg Date: 2015-08 Impact factor: 3.352