PRODIGE: PRediction models in prOstate cancer for personalized meDIcine challenGE.

AIM: Identifying the best care for a patient can be extremely challenging. To support the creation of multifactorial Decision Support Systems (DSSs), we propose an Umbrella Protocol, focusing on prostate cancer. MATERIALS & METHODS: The PRODIGE project consisted of a workflow for standardizing data, and procedures, to create a consistent dataset useful to elaborate DSSs. Techniques from classical statistics and machine learning will be adopted. The general protocol accepted by our Ethical Committee can be downloaded from cancerdata.org . RESULTS: A standardized knowledge sharing process has been implemented by using a semi-formal ontology for the representation of relevant clinical variables. CONCLUSION: The development of DSSs, based on standardized knowledge, could be a tool to achieve a personalized decision-making.

Could machine learning improve the prediction of pelvic nodal status of prostate cancer patients? Preliminary results of a pilot study.

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

Clinical similarities: an innovative approach for supporting medical decisions.

Taking decisions in the medical domain is a very complex task. The context is strongly affected by uncertainty and the possible undesired side effects of the treatments have to be carefully considered. Currently, these decisions are based on the physician's own experience and the evidences of the published literature, according, when available, with the philosophy of Evidence Based Medicine. The main issues of this approach are that the own experience can be different, and the results in the literature are sometimes contrasting. For helping physicians while taking medical decisions, we are proposing an innovative approach based on the idea of the clinical similarity. Given a set of clinical variables, the proposed approach selects patients that are similar, presenting to the physician the respective decisions taken and the corresponding clinical effects.

Immunoglobulin and HLA-DP genes contribute to the susceptibility to juvenile dermatitis herpetiformis.

HLA-DQ genes and gluten diet are the main factors involved in the pathogenesis of Dermatitis Herpetiformis (DH), as well as Coeliac Disease (CD). However other genetic factors are probably relevant, since about 10% of the patients with DH and CD lack the DQA1*0501/B1*0201 heterodimer while the majority of individuals presenting this genotype and also being exposed to gluten diets did not suffer from these diseases. To evaluate the role of other genes, 36 Northern Italian children with DH were analysed for DNA polymorphisms at HLA-DP and immunoglobulin (Ig) heavy chain loci. DPA1*0201 and DPB1*1301 frequencies were higher in patients than in controls (Pc = 0.0357 and Pc = 0.0273). With respect to immunoglobulin heavy chain restriction fragment length polymorphisms (RFLP), the 4.6 kb SacI RFLP at the switch alpha 2 gene was more frequent in patients (0.13) than in controls (0.019; Pc = 0.036). Moreover, rare alleles or duplications in the switch regions occurred more frequently in the patients than in the controls. These results support the hypothesis of a multifactorial inheritance of DH, the HLA and Ig constant heavy chain genes being some of the loci contributing to the susceptibility. In accordance with previous CD studies, these data also confirm that DP subregion is probably involved in the pathogenesis of DH.