Search

Treatment and survival for patients with lung cancer vary between and within countries. We have undertaken a multifaceted study of a clinical dataset of 635 patients, to see if clinician treatment decisions were being made consistently and in accordance with the appropriate Scottish Intercollegiate Guidelines Network (SIGN) document. Subsequently, we created a dataset of 117 patients who should have undergone surgery according to the SIGN guideline. As analyses of this dataset did not provide clear distinctions between the main treatment groups, a clinician reviewed the case notes and dataset, checking for inconsistencies. The revised dataset was processed by a decision tree algorithm which suggests clinically plausible decisions. Further, statistical analyses compared the 54 patients offered surgery with the 52 who were not. These analyses suggest that there are significant differences: the most discriminating feature is significant co-morbidity ( p < 0.001). The article concludes with suggestions for how future guidelines might be enhanced.

We discuss the use of machine learning algorithms to predict which breast cancer patients are likely to respond to (neoadjunctive) chemotherapy. A group of 96 patients from the Aberdeen Royal Infirmary had the size of their tumours assessed by Positron Emission Tomography at various stages of their chemotherapy treatment. The aim is to predict at an early stage which patients have low response to the therapy, for which alternative treatment plans should be followed. A variety of machine learning algorithms were used with this data set. Results indicate that machine learning methods outperform previous statistical approaches on the same data set.

Dysgerminoma is a rare, highly radiosensitive, malignant germ cell tumor occurring in young females. At Radiumhemmet, Stockholm, Sweden, from 1927 to 1984, 60 patients with histologically confirmed pure dysgerminoma were treated. Primary treatment was surgery followed by radiotherapy. Recurrences were irradiated. The mean age was 23.2 years. Sixty-seven percent were in International Federation of Gynecology and Obstetrics (FIGO) Stage I, 6% Stage II, 22% Stage III, 3% Stage IV, and 2% were not staged. The median follow-up time was 19 years (range, 1-53). Generally, women with Stage IA disease had unilateral oophorectomy and unilateral external irradiation. Fourteen have borne 22 children after treatment. Seventeen women in the series have died, 11 from dysgerminoma. Actuarial survival, only counting deaths from dysgerminoma, was 83% at 5 years. No patient has died of dysgerminoma since 1963 when radiotherapy with megavoltage x-rays was introduced. The authors consider external irradiation to be an effective treatment as a complement to surgery in dysgerminoma of the ovary.

Many machines used in the modern hospital settings offer real time physiological monitoring. Haemodialysis machines combine a therapeutic treatment system integrated with sophisticated monitoring equipment. A large array of parameters can be collected including cardiovascular measures such as heart rate and blood pressure together with treatment related data including relative blood volume, ultrafiltration rate and small molecule clearance. A small subset of this information is used by clinicians to monitor treatment and plan therapeutic strategies but it is not usually analysed in any detail. The focus of this paper is the analysis of data collected over a number of treatment sessions with a view to predicting patient physiological behaviour whilst on dialysis and correlating this with clinical characteristics of individual patients. One of the commonest complications experienced by patients on dialysis is symptomatic hypotension. We have taken real time treatment data and outline a program of work which attempts to predict when hypotension is likely to occur, and which patients might be particularly prone to haemodynamic instability. This initial study has investigated: the rate of change of blood pressure versus rate of change of heart rate, rate of fluid removal, and rate of uraemic toxin clearance. We have used a variety of machine learning techniques (including hierarchical clustering, and Bayesian Network analysis algorithms). We have been able to detect from this dataset, 3 distinct groups which appear to be clinically meaningful. Furthermore we have investigated whether it is possible to predict changes in blood pressure in terms of other parameters with some encouraging results that merit further study.

The role of the Internet in today’s information world can be considered as one of an agora, a French pre-revolution cafe, or simply an unlimited source of information available to everyone on request. The beneficiaries of this information availability are many. Academic issues as well as everyday discussions may make use of the world wide web to promote debates, raise issues of interest, put forward concepts and ideas, and generally contribute to the proliferation of knowledge even at the most remote location on the globe either as a blue ribbon medium or as a moderated discussion forum. This increasing information availability, on the one hand, and demand, on the other, pose a very important question: what should computer scientists do to make this worldwide spread of information not only available, but also and most importantly, useful to its recipients?