Learn More
Use of the Rotterdam Symptom Checklist (RSCL) to measure psychological and physical distress as experienced by cancer patients, is discussed in this paper. The stability of the structure of the RSCL was assessed in principal component analyses in three studies: one concerning cancer patients during either chemotherapy or follow-up (n = 86), one done in(More)
In the current paper, the Promedas model for internal medicine , developed by our team, is introduced. The model is based on up-to-date medical knowledge and consists of approximately 2000 diagnoses, 1000 findings and 8600 connections between diagnoses and findings, covering a large part of internal medicine. We show that Belief Propagation (BP) can be(More)
Expression of the growth-associated protein B50 (GAP-43) mRNA in dorsal root ganglia (DRG) of rats was studied by in situ hybridization. In response to treatment with the neurotoxic agent cisplatin, B50 mRNA expression was significantly enhanced following a cumulative cisplatin dose of 14 mg/kg. In the untreated age-matched control animals, only half of the(More)
131 patients with osteolytic metastases from breast cancer were randomised to receive long-term oral treatment with aminohydroxy-propylidene-bisphosphonate (APD), 300 mg daily (n = 70), or to act as controls (n = 61) in a multicentre trial. Specific antitumour therapy was at the discretion of the clinician and variable. An interim analysis was made after a(More)
Computer-based diagnostic decision support systems (DSS) will play an increasingly important role in health care. Due to the inherent probabilistic nature of medical diagnosis, a DSS should preferably be based on a probabilistic model. In particular Bayesian networks provide a powerful and conceptually transparent formalism for probabilistic modeling. A(More)
Cisplatin neurotoxicity was studied in rats by using electrophysiological and functional tests. The drug was injected intraperitoneally two times a week (1 mg/kg) up to a cumulative dose of 19.0 mg/kg body wt. At this dose the H-reflex-related sensory nerve conduction velocity was reduced. After cessation of drug administration, the H-reflex-related sensory(More)
186 patients with advanced epithelial ovarian carcinoma were treated with either a combination of hexamethylmelamine, cyclophosphamide, methotrexate, and 5-fluorouracil (Hexa-CAF) or cyclophosphamide and hexamethylmelamine alternating with doxorubicin and a 5-day course of cisplatin (CHAP-5). Treatment with CHAP-5 resulted in more complete remissions as(More)
Promedas is a medical patient-specific clinical diagnostic decision support systems based on graphical probabilis-tic models. Promedas aims to improve the quality and efficiency of the diagnostic process, while reducing its costs at the same time. Modern-day medical diagnosis is a very complex process, requiring accurate patient data, a profound(More)
The traditional technique to model survival probabilities is the Cox regression analysis Cox and Oakes, 1984]. Recently, also neural networks have been applied for survival analysis and the prediction of prognosis in cancer treatment Liesttl K, 1994]. The main advantages of the neural network approach are the relative ease with which time dependencies in(More)
In this article we show that traditional Cox survival analysis can be improved upon when supplemented with sensible priors and analysed within a neural Bayesian framework. We demonstrate that the Bayesian method gives more reliable predictions, in particular for relatively small data sets. The obtained posterior (the probability distribution of network(More)