Patrizia Ferroni1, Fabio Massimo Zanzotto2, Noemi Scarpato1, Silvia Riondino3,4, Umberto Nanni5, Mario Roselli4, Fiorella Guadagni1,3,4. 1. San Raffaele Roma Open University, Rome, Italy (PF, NS, FG). 2. Department of Enterprise Engineering, University of Rome "Tor Vergata," Rome, Italy (FMZ). 3. BioBIM (InterInstitutional Multidisciplinary Biobank, IRCCS San Raffaele Pisana, Rome, Italy (SR, FG). 4. Department of Systems Medicine, Medical Oncology, University of Rome "Tor Vergata," Rome, Italy (SR, MR). 5. Department of Computer, Control, and Management Engineering Antonio Ruberti, Sapienza University, Rome, Italy (UN).
Abstract
OBJECTIVE: To design a precision medicine approach aimed at exploiting significant patterns in data, in order to produce venous thromboembolism (VTE) risk predictors for cancer outpatients that might be of advantage over the currently recommended model (Khorana score). DESIGN: Multiple kernel learning (MKL) based on support vector machines and random optimization (RO) models were used to produce VTE risk predictors (referred to as machine learning [ML]-RO) yielding the best classification performance over a training (3-fold cross-validation) and testing set. RESULTS: Attributes of the patient data set ( n = 1179) were clustered into 9 groups according to clinical significance. Our analysis produced 6 ML-RO models in the training set, which yielded better likelihood ratios (LRs) than baseline models. Of interest, the most significant LRs were observed in 2 ML-RO approaches not including the Khorana score (ML-RO-2: positive likelihood ratio [+LR] = 1.68, negative likelihood ratio [-LR] = 0.24; ML-RO-3: +LR = 1.64, -LR = 0.37). The enhanced performance of ML-RO approaches over the Khorana score was further confirmed by the analysis of the areas under the Precision-Recall curve (AUCPR), and the approaches were superior in the ML-RO approaches (best performances: ML-RO-2: AUCPR = 0.212; ML-RO-3-K: AUCPR = 0.146) compared with the Khorana score (AUCPR = 0.096). Of interest, the best-fitting model was ML-RO-2, in which blood lipids and body mass index/performance status retained the strongest weights, with a weaker association with tumor site/stage and drugs. CONCLUSIONS: Although the monocentric validation of the presented predictors might represent a limitation, these results demonstrate that a model based on MKL and RO may represent a novel methodological approach to derive VTE risk classifiers. Moreover, this study highlights the advantages of optimizing the relative importance of groups of clinical attributes in the selection of VTE risk predictors.
OBJECTIVE: To design a precision medicine approach aimed at exploiting significant patterns in data, in order to produce venous thromboembolism (VTE) risk predictors for cancer outpatients that might be of advantage over the currently recommended model (Khorana score). DESIGN: Multiple kernel learning (MKL) based on support vector machines and random optimization (RO) models were used to produce VTE risk predictors (referred to as machine learning [ML]-RO) yielding the best classification performance over a training (3-fold cross-validation) and testing set. RESULTS: Attributes of the patient data set ( n = 1179) were clustered into 9 groups according to clinical significance. Our analysis produced 6 ML-RO models in the training set, which yielded better likelihood ratios (LRs) than baseline models. Of interest, the most significant LRs were observed in 2 ML-RO approaches not including the Khorana score (ML-RO-2: positive likelihood ratio [+LR] = 1.68, negative likelihood ratio [-LR] = 0.24; ML-RO-3: +LR = 1.64, -LR = 0.37). The enhanced performance of ML-RO approaches over the Khorana score was further confirmed by the analysis of the areas under the Precision-Recall curve (AUCPR), and the approaches were superior in the ML-RO approaches (best performances: ML-RO-2: AUCPR = 0.212; ML-RO-3-K: AUCPR = 0.146) compared with the Khorana score (AUCPR = 0.096). Of interest, the best-fitting model was ML-RO-2, in which blood lipids and body mass index/performance status retained the strongest weights, with a weaker association with tumor site/stage and drugs. CONCLUSIONS: Although the monocentric validation of the presented predictors might represent a limitation, these results demonstrate that a model based on MKL and RO may represent a novel methodological approach to derive VTE risk classifiers. Moreover, this study highlights the advantages of optimizing the relative importance of groups of clinical attributes in the selection of VTE risk predictors.
Entities:
Keywords:
cancer; clinical decision support systems; machine learning; random optimization; venous thromboembolism
Authors: Nicole M Kuderer; Marek S Poniewierski; Eva Culakova; Gary H Lyman; Alok A Khorana; Ingrid Pabinger; Giancarlo Agnelli; Howard A Liebman; Eric Vicaut; Guy Meyer; Frances A Shepherd Journal: Oncologist Date: 2017-09-26
Authors: Andrew E Grothen; Bethany Tennant; Catherine Wang; Andrea Torres; Bonny Bloodgood Sheppard; Glenn Abastillas; Marina Matatova; Jeremy L Warner; Donna R Rivera Journal: JCO Clin Cancer Inform Date: 2020-11
Authors: Fiorella Guadagni; Silvia Riondino; Vincenzo Formica; Girolamo Del Monte; Anna Maria Morelli; Jessica Lucchetti; Antonella Spila; Roberta D'Alessandro; David Della-Morte; Patrizia Ferroni; Mario Roselli Journal: World J Gastroenterol Date: 2017-07-28 Impact factor: 5.742
Authors: Hendrikus J A van Os; Lucas A Ramos; Adam Hilbert; Matthijs van Leeuwen; Marianne A A van Walderveen; Nyika D Kruyt; Diederik W J Dippel; Ewout W Steyerberg; Irene C van der Schaaf; Hester F Lingsma; Wouter J Schonewille; Charles B L M Majoie; Silvia D Olabarriaga; Koos H Zwinderman; Esmee Venema; Henk A Marquering; Marieke J H Wermer Journal: Front Neurol Date: 2018-09-25 Impact factor: 4.003
Authors: David W Bates; David Levine; Ania Syrowatka; Masha Kuznetsova; Kelly Jean Thomas Craig; Angela Rui; Gretchen Purcell Jackson; Kyu Rhee Journal: NPJ Digit Med Date: 2021-03-19