Roberto Gatta

Changes in patterns of practice for prostate cancer radiotherapy in Italy 1995-2003. A survey of the Prostate Cancer Study Group of the Italian Radiation Oncology Society

Aims and Background In 2002, a survey including 1759 patients treated from 1980 to 1998 established a “benchmark” Italian data source for prostate cancer radiotherapy. This report updates the previous one. Methods Data on clinical management and outcomes of 3001 patients treated in 15 centers from 1999 through 2003 were analyzed and compared with those of the previous survey. Results Significant differences in clinical management (-10% had abdominal magnetic resonance imaging; +26% received ≥70 Gy, +48% conformal radiotherapy, −20% pelvic radiotherapy) and in G3–4 toxicity rates (-3.8%) were recorded. Actuarial 5-year overall, disease-specific, clinical relapse-free, and biochemical relapse-free survival rates were 88%, 96%, 96% and 88%, respectively. At multivariate analysis, DAmico risk categories significantly impacted on all the outcomes; higher radiotherapy doses were significantly related with better overall survival rates, and a similar trend was evident for disease-specific and biochemical relapse-free survival; cumulative probability of 5-year late G1–4 toxicity was 24.8% and was significantly related to higher radiotherapy doses (P <0.001). Conclusions The changing patterns of practice described seem related to an improvement in efficacy and safety of radiotherapy for prostate cancer. However, the impact of the new radiotherapy techniques should be prospectively evaluated.

Assessing the conformity to clinical guidelines in oncology: An example for the multidisciplinary management of locally advanced colorectal cancer treatment

Purpose n n n n nThe purpose of this paper is to describe a methodology to deal with conformance checking through the implementation of computer-interpretable-clinical guidelines (CIGs), and present an application of the methodology to real-world data and a clinical pathway for radiotherapy-related oncological treatment. n n n n nDesign/methodology/approach n n n n nThis methodology is implemented by a software able to use the hospital electronic health record data to assess the adherence of the actual executed clinical processes to a clinical pathway, monitoring at the same time management-related efficiency and performance parameters, and ideally, suggesting ways to improve them. n n n n nFindings n n n n nThree use cases are presented, in which the results of conformance checking are used to compare different branches of the executed guidelines with respect to the adherence to ideal process, temporal distribution of state-to-state transitions, and overall treatment efficacy, in order to extract data-driven evidence that could be of interest for the hospital management. n n n n nOriginality/value n n n n nThis approach has the result of applying management-oriented data mining technique on sequential data, typical of process mining, to the result of a conformity check between the preliminary knowledge defined by clinicians and the real-world data, typical of CIGs.

Development and validation of a machine learning-based predictive model to improve the prediction of inguinal status of anal cancer patients: A preliminary report

Introduction The role of prophylactic inguinal irradiation (PII) in the treatment of anal cancer patients is controversial. We developped an innovative algorithm based on the Machine Learning (ML) allowing the tailoring of the prescription of PII. Results Once verified on the independent testing set, J48 showed the better performances, with specificity, sensitivity, and accuracy rates in predicting relapsing patients of 86.4%, 50.0% and 83.1% respectively (vs 36.5%, 90.4% and 80.25%, respectively, for LR). Methods We classified 194 anal cancer patients with Logistic Regression (LR) and other 3 ML techniques based on decision trees (J48, Random Tree and Random Forest), using a large set of clinical and therapeutic variables. We tested obtained ML algorithms on an independent testing set of 65 anal cancer patients. TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis) methodology was used for the development, the Quality Assurance and the description of the experimental procedures. Conclusion In an internationally approved quality assurance framework, ML seems promising in predicting the outcome of patients that would benefit or not of the PII. Once confirmed in larger and/or multi-centric databases, ML could support the physician in tailoring the treatment and in deciding if deliver or not the PII.

How Can Radiomics Improve Clinical Choices

Over the past decade, we have witnessed a great expansion of the use and the role of medical imaging technologies in clinical oncology from a primarily diagnostic, qualitative tool to include a central role in the context of individualized medicine, with a dominant quantitative value [1].

ENT COBRA ONTOLOGY: the covariates classification system proposed by the Head & Neck and Skin GEC-ESTRO Working Group for interdisciplinary standardized data collection in head and neck patient cohorts treated with interventional radiotherapy (brachytherapy)

Purpose Clinical data collecting is expensive in terms of time and human resources. Data can be collected in different ways; therefore, performing multicentric research based on previously stored data is often difficult. The primary objective of the ENT COBRA (COnsortium for BRachytherapy data Analysis) ontology is to define a specific terminological system to standardized data collection for head and neck (H&N) cancer patients treated with interventional radiotherapy. Material and methods ENT-COBRA is a consortium for standardized data collection for H&N patients treated with interventional radiotherapy. It is linked to H&N and Skin GEC-ESTRO Working Group and includes 11 centers from 6 countries. Its ontology was firstly defined by a multicentric working group, then evaluated by the consortium followed by a multi-professional technical commission involving a mathematician, an engineer, a physician with experience in data storage, a programmer, and a software expert. Results Two hundred and forty variables were defined on 13 input forms. There are 3 levels, each offering a specific type of analysis: 1. Registry level (epidemiology analysis); 2. Procedures level (standard oncology analysis); 3. Research level (radiomics analysis). The ontology was approved by the consortium and technical commission; an ad-hoc software architecture (“broker”) remaps the data present in already existing storage systems of the various centers according to the shared terminology system. The first data sharing was successfully performed using COBRA software and the ENT COBRA Ontology, automatically collecting data directly from 3 different hospital databases (Lübeck, Navarra, and Rome) in November 2017. Conclusions The COBRA Ontology is a good response to the multi-dimensional criticalities of data collection, retrieval, and usability. It allows to create a software for large multicentric databases with implementation of specific remapping functions wherever necessary. This approach is well-received by all involved parties, primarily because it does not change a single center’s storing technologies, procedures, and habits.

Magnetic Resonance, Vendor-independent, Intensity Histogram Analysis Predicting Pathologic Complete Response After Radiochemotherapy of Rectal Cancer

PURPOSEnThe objective of this study is finding an intensity based histogram (IBH) signature to predict pathologic complete response (pCR) probability using only pre-treatment magnetic resonance (MR) and validate it externally in order to create a workflow for the external validation of an MR IBH signature and to apply the model out of the environment where it has been tuned. The impact of pCR and the final predictors on the survival outcome were also evaluated.nnnMETHODS AND MATERIALSnThree centers using different MR scanners were involved in this retrospective study. The first center recruited 162 patients for model training, and the second and third centers provided 34 plus 25 patients for external validation. Patients provided written consent. Accrual period was from May 2008 to December 2014. After surgery pathologic response was defined. T2-weighted MR scans acquired before chemoradiation therapy (CRT) were used for analysis addressed on primary lesions. Images were pre-processed using Laplacian of Gaussian (LoG) filter with multiple σ, and first order intensity histogram-based features (kurtosis, skewness, and entropy) were extracted. Features selection was performed using Mann-Whitney test. Tumor staging (cT, cN) was added to build a logistic regression model and predict pCR. Model performance was evaluated with internal and external validation using area under the curve (AUC) of the receiver operator characteristic (ROC) and calibration with Hosmer-Lemeshow test. The linear cross-correlation matrix (Pearsons coefficient) and the variance inflation factor (VIF) were used to check the correlation and the co-linearity among the final predictors. The amount of the information added through the radiomics features was estimated by using the DeLongs test, and the impact of pCR and the final predictors on survival outcomes were evaluated through the Kaplan-Meier curves by using the log-rank test and the multivariate Cox model.nnnRESULTSnCandidate-to-analysis features were skewness (σxa0=xa00.485, P valuexa0=xa0.01) and entropy (σxa0=xa00.344, P valuexa0<xa0.05). Logistic regression analysis showed as significant covariates cT (P valuexa0<xa0.01), skewness-σxa0=xa00.485 (P valuexa0=xa0.01), and entropy-σxa0=xa00.344 (P valuexa0<xa0.05). Model AUCs were 0.73 (internal) and 0.75 (external).nnnCONCLUSIONSnThis MR-based, vendor-independent model can be helpful for predicting pCR probability in locally advanced rectal cancer (LARC) patients only using pre-treatment imaging.

Towards a modular decision support system for radiomics: A case study on rectal cancer

Following the personalized medicine paradigm, there is a growing interest in medical agents capable of predicting the effect of therapies on patients, by exploiting the amount of data that is now available for each patient. In disciplines like oncology, where images and scans are available, the exploitation of medical images can provide an additional source of potentially useful information. The study and analysis of features extracted by medical images, exploited for predictive purposes, is termed radiomics. A number of tools are available for supporting some of the steps of the radiomics process, but there is a lack of approaches which are able to deal with all the steps of the process. In this paper, we introduce a medical agent-based decision support system capable of handling the whole radiomics process. The proposed system is tested on two independent data sets of patients treated for rectal cancer. Experimental results indicate that the system is able to generate highly performant centre-specific predictive model, and show the issues related to differences in data sets collected by different centres, and how such issues can affect the performance of the generated predictive models.

Bridging the Gap between Knowledge Representation and Electronic Health Records

Decision Support Systems (DSSs) are systems that supports decision-making activities. Their application in medical domain needs to face the critical issue of retrieving information from heterogeneous existing data sources, such as Electronic Health Records (EHRs). It is well-known that there exists a huge problem of standardisation. In fact, EHRs can represent the same knowledge in many different ways. It is evident that the applicability of DSSs strongly relies on the availability of homogeneous collections of data. On the other hand, the gap between DSSs and different EHRs can be bridged by exploiting middleware technologies. nIn this paper, we tested CSL, a technology designed for working as a middleware between DSS and EHRs, nwhich is able to combine data taken from different EHR sources and to provide abstract and homogeneous ndata to DSSs. Moreover, CSL has been used for implementing three Clinical Guidelines, in order to test its capability in representing complex work-flows. The performed analysis highlight strengths and limitations of the proposed approach.