Biomedical subjects

George Papadatos

Publications and source records attributed to George Papadatos.

3 recordsLinked to original sources

PubMed2007

Evaluation of machine-learning methods for ligand-based virtual screening.

Machine-learning methods can be used for virtual screening by analysing the structural characteristics of molecules of known (in)activity, and we here discuss the use of kernel discrimination and naive Bayesian classifier (NBC) methods for this purpose. We report a kernel method that allows the processing of molecules represented by binary, integer and real-valued descriptors, and show that it is little different in screening performance from a previously described kernel that had been developed specifically for the analysis of binary fingerprint representations of molecular structure. We then evaluate the performance of an NBC when the training-set contains only a very few active molecules. In such cases, a simpler approach based on group fusion would appear to provide superior screening performance, especially when structurally heterogeneous datasets are to be processed.

Artificial Intelligence↗

PubMed2004

Waiting times for radiotherapy--a survey of patients' attitudes.

BACKGROUND AND PURPOSE: To determine the maximum time cancer patients were willing to wait for radiotherapy. PATIENTS AND METHODS: Using a trade-off technique (TOT) the maximum time patients were prepared to wait for treatment at the centre closest to home before electing to transfer their care to a centre located (1) at a distance necessitating an extra 30 min travelling each day (MWT 1) or (2) at a distance necessitating staying away from home for the duration of therapy (MWT 2) was determined. A TOT was utilised to determine the loss in treatment effectiveness (LIE 1, LIE 2) patients were willing to accept as a consequence of their MWT 1 and MWT 2 choices. RESULTS: The median MWT 1 was 4 weeks while the median MWT 2 was 8 weeks. A longer MWT 1 was associated with increasing patient age and a problem with travelling an extra 30 min. Symptomatic patients were less likely to accept a longer MWT 1. The MWT 2 increased as the expected duration of treatment increased but patients in regional areas were less likely to accept a longer MWT 2. The majority of patients indicated that they were unwilling to accept any loss in treatment effectiveness. Patients who had a problem with travelling an extra 30 min daily or who were unable to drive were willing to accept a loss in treatment effectiveness. CONCLUSIONS: This study provides an estimate of the waiting times cancer patients are prepared to accept for radiation therapy and suggests that cancer patients are unlikely to trade-off effectiveness for convenience.

Attitude to Health↗

PubMed2002

Women's choice between sentinel lymph node biopsy and axillary clearance.

PURPOSE: To determine whether women would choose sentinel lymph node biopsy (SLNB) or axillary clearance (AC) for breast cancer treatment when they are given a single choice based on clear information about morbidity and mortality. METHODS: The expected 5-year survival rate of women with breast cancer after either SLNB or AC was calculated using a utility analysis of established literature. The difference in survival was one in 1000. This and other detailed information on SLNB and AC was presented in a questionnaire, which provided subjects with a scenario and a choice between SLNB and AC. After a pilot study of 40 subjects, the questionnaire was mailed to 400 women (who had no mammographic abnormality) attending Breast Screen and handed to 100 women (who were over 40 years of age and had breast symptoms but not cancer) attending the rooms of two surgical specialists. RESULTS: One hundred and twenty one of the 243 respondents to the mailed questionnaires (49.8%) chose SLNB and 35% of the 100 consulting room subjects chose SLNB rather than AC. CONCLUSIONS: Women faced with the possibility of having breast cancer seem to be very conservative in their choice of treatment, many choosing the increased morbidity of AC rather than the very small (one in 1000) increased risk of death at 5 years from SLNB. This raises questions about proposals to offer SLNB as standard treatment and demands that women are fully informed about any increased risk of death when making their choice between SLNB and AC.

Adult↗