Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

A Neural Network Approach to Treatment Optimization

Sanguansintukul, Siripun (2011) A Neural Network Approach to Treatment Optimization. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Primary Text

Download (7MB) | Preview

Abstract

An approach for optimizing medical treatment as a function of measurable patient data is analyzed using a two-network system. The two-network approach is inspired by the field of control systems: one network, called a patient model (PM), is used to predict the outcome of the treatment, while the other, called a treatment network (TN), is used to optimize the predicted outcome. The system is tested with a variety of functions: one objective criterion (with and without interaction between treatments) and multi-objective criteria (with and without interaction between treatments). Data are generated using a simple Gaussian function for some studies and with functions derived from the medical literature for other studies. The experimental results can be summarized as follows: 1) the relative importance of symptoms can be adjusted by applying different coefficient weights in the PM objective functions. Different coefficients are employed to modulate the tradeoffs in symptoms. Higher coefficients in the cost function result in higher accuracy. 2) Different coefficients are applied to the objective functions of the TN when both objective functions are quadratic, the experimental results suggest that the higher the coefficient the better the symptom. 3) The simulation results of training the TN with a quadratic cost function and a quartic cost function indicate the threshold-like behavior in the quartic cost function when the dose is in the neighborhood of the threshold. 4) In general, the network illustrates a better performance than the quadratic model. However, the network encounters a local minima problem. Ultimately, the results indicate a proof of idea that this framework might be a useful tool for augmenting a clinician's decision in selecting dose strengths for an individual patient need.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Sanguansintukul, Siripunsiripuns@mail.sis.pitt.edu
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairPaul, Munropmunro@mail.sis.pitt.eduPWM
Committee MemberPeter, Brusilovskypeterb@mail.sis.pitt.eduPETERB
Committee MemberMarek, zdzelmarek@mail.sis.pitt.eduDRUZDZEL
Committee MemberSatish, Iyengarssi@pitt.eduSSI
Committee MemberBambang, Parmantoparmanto@pitt.eduPARMANTO
Date: 17 February 2011
Date Type: Completion
Defense Date: 5 September 2003
Approval Date: 17 February 2011
Submission Date: 24 September 2003
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Institution: University of Pittsburgh
Schools and Programs: School of Information Sciences > Information Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: back propagation; distal learning; dose optimization
Other ID: http://etd.library.pitt.edu/ETD/available/etd-09242003-142535/, etd-09242003-142535
Date Deposited: 10 Nov 2011 20:02
Last Modified: 15 Nov 2016 13:50
URI: http://d-scholarship.pitt.edu/id/eprint/9380

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item