scholarly journals CANCER PROGNOSTIC EVALUATION VIA SUPPORT VECTOR MACHINES

2014 ◽  
pp. 29-34
Author(s):  
Domenico Conforti ◽  
Domenico Costanzo ◽  
Rosita Guido

In this paper we considered a very challenging medical decision making problem: the short-term prognosis evaluation of breast cancer patients. In particular, the oncologist has to predict the more likely outcome of the disease in terms of survival or recurrence after a given follow-up period: “good” prognosis if the patient is still alive and has not recurrence after the follow-up period, “poor” prognosis if the patient has recurrence or dies within the follow-up period. This prediction can be realized on the basis of the execution of specific clinical tests and patient examinations. The relevant medical decision making problem has been formulated as a supervised binary classification problem. By the framework of generalized Support Vector Machine models, we tested and validate the behavior of four kernel based classifiers: Linear, Polynomial, Gaussian and Laplacian. The overall results demonstrate the effectiveness and robustness of the proposed approaches for solving the relevant medical decision making problem.

2005 ◽  
Vol 15 (1) ◽  
pp. 9-19 ◽  
Author(s):  
Thomas F. Hack ◽  
Lesley F. Degner ◽  
Peter Watson ◽  
Luella Sinha

2012 ◽  
Vol 30 (34_suppl) ◽  
pp. 20-20
Author(s):  
Suepattra G. May ◽  
Katharine Rendle ◽  
Meghan Halley ◽  
Nicole Ventre ◽  
Allison W. Kurian ◽  
...  

20 Background: Shared medical decision making (SDM) has been lauded by advocates for its potential to democratize the patient-physician relationship. However, the practice of SDM is still conceived of as largely a dyadic moment that exists between the patient and the physician. Few studies have looked at the role of significant others (spouses, partners, family members and friends) in decision making or considered how discussions and actions outside the consultation room affect a patient’s medical decisions. This prospective study investigated the impact of significant others on the decision making deliberations of newly diagnosed breast cancer patients. Methods: Forty-one newly diagnosed breast cancer patients were interviewed at four critical time points throughout treatment to explore how they deliberated decisions with both care providers and significant others. Surveys assessing HRQOL, role preferences and treatment satisfaction along with EHR abstraction augmented interview data. Grounded theory analysis was used to identify recurrent themes in the qualitative data, and survey data were analyzed using IBM SPSS Statistics 20. Results: Emergent themes from our analysis identified several factors that patients consider when faced with cancer treatment decisions, including 1) presentation of treatment options 2) patient or significant other conflict/concordance with care team recommendations 3) perceived risk of recurrence and 4) short and long term impact of treatment on daily life. Participants stressed the need for clinicians to view patients beyond diagnosis and recognize their larger care network as influential factors in their decision making. Conclusions: Our interviews highlight how the current healthcare delivery structure rarely acknowledges the circles of care that can exert influence on decision making. Lack of attention to non-clinical others can lead to sub-optimal medical decision making because these influences are not adequately understood by clinicians. Findings from this study suggest the need to enhance clinicians’ and researchers’ understanding of the influence of others in patients’ treatment decision making, enabling them to intervene in these practices.


2019 ◽  
Vol 15 (02) ◽  
pp. 351-359 ◽  
Author(s):  
Murat Kirişci

In the present study, for the medical decision-making problem, the proposed techniques related to the intuitionistic fuzzy parametrized soft sets and Riesz mean methods were used. The results of the given methods were compared. The values obtained from the methods were ordered and the success of the measurement techniques of the methods were evaluated. The real dataset which is called Cleveland heart disease dataset was applied in this problem.


Sign in / Sign up

Export Citation Format

Share Document