Browsing by Author "Green, Michael"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Survival following allogeneic transplant in patients with myelofibrosis
    (American Society of Hematology, 2020-05-08) Gowin, Krisstina; Ballen, Karen; Ahn, Kwang Woo; Hu, Zhen-Huan; Ali, Haris; Arcasoy, Murat O.; Devlin, Rebecca; Coakley, Maria; Gerds, Aaron T.; Green, Michael; Gupta, Vikas; Hobbs, Gabriela; Jain, Tania; Kandarpa, Malathi; Komrokji, Rami; Kuykendall, Andrew T.; Luber, Kierstin; Masarova, Lucia; Michaelis, Laura C.; Patches, Sarah; Pariser, Ashley C.; Rampal, Raajit; Stein, Brady; Talpaz, Moshe; Verstovsek, Srdan; Wadleigh, Martha; Agrawal, Vaibhav; Aljurf, Mahmoud; Diaz, Miguel Angel; Avalos, Belinda R.; Bacher, Ulrike; Bashey, Asad; Beitinjaneh, Amer M.; Cerny, Jan; Chhabra, Saurabh; Copelan, Edward; Cutler, Corey S.; DeFilipp, Zachariah; Gadalla, Shahinaz M.; Ganguly, Siddhartha; Grunwald, Michael R.; Hashmi, Shahrukh K.; Kharfan-Dabaja, Mohamed A.; Kindwall-Keller, Tamila; Kröger, Nicolaus; Lazarus, Hillard M.; Liesveld, Jane L.; Litzow, Mark R.; Marks, David I.; Nathan, Sunita; Nishihori, Taiga; Olsson, Richard F.; Pawarod, Attaphol; Rowe, Jacob M.; Savani, Bipin N.; Savoie, Mary Lynn; Seo, Sachiko; Solh, Melhem; Tamari, Roni; Verdonck, Leo F.; Yared, Jean A.; Alyea, Edwin; Popat, Uday; Sobecks, Ronald; Scott, Bart L.; Nakamura, Ryotaro; Mesa, Ruben; Saber, Wael; Medicine, School of Medicine
    Allogeneic hematopoietic cell transplantation (HCT) is the only curative therapy for myelofibrosis (MF). In this large multicenter retrospective study, overall survival (OS) in MF patients treated with allogeneic HCT (551 patients) and without HCT (non-HCT) (1377 patients) was analyzed with Cox proportional hazards model. Survival analysis stratified by the Dynamic International Prognostic Scoring System (DIPSS) revealed that the first year of treatment arm assignment, due to upfront risk of transplant-related mortality (TRM), HCT was associated with inferior OS compared with non-HCT (non-HCT vs HCT: DIPSS intermediate 1 [Int-1]: hazard ratio [HR] = 0.26, P < .0001; DIPSS-Int-2 and higher: HR, 0.39, P < .0001). Similarly, in the DIPSS low-risk MF group, due to upfront TRM risk, OS was superior with non-HCT therapies compared with HCT in the first-year post treatment arm assignment (HR, 0.16, P = .006). However, after 1 year, OS was not significantly different (HR, 1.38, P = .451). Beyond 1 year of treatment arm assignment, an OS advantage with HCT therapy in Int-1 and higher DIPSS score patients was observed (non-HCT vs HCT: DIPSS-Int-1: HR, 2.64, P < .0001; DIPSS-Int-2 and higher: HR, 2.55, P < .0001). In conclusion, long-term OS advantage with HCT was observed for patients with Int-1 or higher risk MF, but at the cost of early TRM. The magnitude of OS benefit with HCT increased as DIPSS risk score increased and became apparent with longer follow-up.
  • Thumbnail Image
    Item
    Weighted-Support Vector Machine Learning Classifier of Circulating Cytokine Biomarkers to Predict Radiation-Induced Lung Fibrosis in Non-Small-Cell Lung Cancer Patients
    (Frontiers Media, 2021-02-01) Yu, Hao; Lam, Ka-On; Wu, Huanmei; Green, Michael; Wang, Weili; Jin, Jian-Yue; Hu, Chen; Jolly, Shruti; Wang, Yang; Kong, Feng-Ming Spring; BioHealth Informatics, School of Informatics and Computing
    Background: Radiation-induced lung fibrosis (RILF) is an important late toxicity in patients with non-small-cell lung cancer (NSCLC) after radiotherapy (RT). Clinically significant RILF can impact quality of life and/or cause non-cancer related death. This study aimed to determine whether pre-treatment plasma cytokine levels have a significant effect on the risk of RILF and investigate the abilities of machine learning algorithms for risk prediction. Methods: This is a secondary analysis of prospective studies from two academic cancer centers. The primary endpoint was grade≥2 (RILF2), classified according to a system consistent with the consensus recommendation of an expert panel of the AAPM task for normal tissue toxicity. Eligible patients must have at least 6 months' follow-up after radiotherapy commencement. Baseline levels of 30 cytokines, dosimetric, and clinical characteristics were analyzed. Support vector machine (SVM) algorithm was applied for model development. Data from one center was used for model training and development; and data of another center was applied as an independent external validation. Results: There were 57 and 37 eligible patients in training and validation datasets, with 14 and 16.2% RILF2, respectively. Of the 30 plasma cytokines evaluated, SVM identified baseline circulating CCL4 as the most significant cytokine associated with RILF2 risk in both datasets (P = 0.003 and 0.07, for training and test sets, respectively). An SVM classifier predictive of RILF2 was generated in Cohort 1 with CCL4, mean lung dose (MLD) and chemotherapy as key model features. This classifier was validated in Cohort 2 with accuracy of 0.757 and area under the curve (AUC) of 0.855. Conclusions: Using machine learning, this study constructed and validated a weighted-SVM classifier incorporating circulating CCL4 levels with significant dosimetric and clinical parameters which predicts RILF2 risk with a reasonable accuracy. Further study with larger sample size is needed to validate the role of CCL4, and this SVM classifier in RILF2.