Search

The potential of a voltametric E-tongue coupled with a custom data pre-processing stage to improve the performance of machine learning techniques for rapid discrimination of tomato purées between cultivars of different economic value has been investigated. To this aim, a sensor array with screen-printed carbon electrodes modified with gold nanoparticles (GNP), copper nanoparticles (CNP) and bulk gold subsequently modified with poly(3,4-ethylenedioxythiophene) (PEDOT), was developed to acquire data to be transformed by a custom pre-processing pipeline and then processed by a set of commonly used classifiers. The GNP and CNP-modified electrodes, selected based on their sensitivity to soluble monosaccharides, demonstrated good ability in discriminating samples of different cultivars. Among the different data analysis methods tested, Linear Discriminant Analysis (LDA) proved to be particularly suitable, obtaining an average F1 score of 99.26%. The pre-processing stage was beneficial in reducing the number of input features, decreasing the computational cost, i.e., the number of computing operations to be performed, of the entire method and aiding future cost-efficient hardware implementation. These findings proved that coupling the multi-sensing platform featuring properly modified sensors with the custom pre-processing method developed and LDA provided an optimal tradeoff between analytical problem solving and reliable chemical information, as well as accuracy and computational complexity. These results can be preliminary to the design of hardware solutions that could be embedded into low-cost portable devices. [ABSTRACT FROM AUTHOR]

Introduction: According with "Numbers of cancer in Italy. 2021" mortality is decreasing for both the genders (-10% for men, -8% for women) in Italy. However, this trend is not uniform and seems stable in the Southern regions. Analyses of oncological care in Campania Region highlighted some structural critical issues and delays, which did not guarantee an efficient and effective use of the available economic resources. So, the Campania region established in September 2016 the Campania oncological network (Roc) addressed to prevention, diagnosis, treatment and rehabilitation of tumours through the establishment of multidisciplinary oncological groups (Gom). In February 2020, the ValPeRoc project was launched with the aim of periodically and progressively evaluating the Roc's performance both for the clinical services and for the economic aspects., Methods: In five Goms (colon, ovary, lung, prostate, bladder) active in some Roc hospitals, the pre-Gom time elapsing between the date of diagnosis and the date of the first Gom meeting and the Gom time elapsing between the date of the first Gom meeting and the date of the treatment decision were measured. Gom times longer than 28 days were defined as high. The risk of high Gom time was analyzed with a Bart-type machine learning algorithm, considering the set of regressors (features) available to classify patients., Results: The results on the test set (54 patients) report an accuracy of 0.68. The classification technique reported a good fit for colon Gom (93%) and an over-classification for lung Gom. The study of the marginal effects showed a higher risk for those who had a previous therapeutic act and for lung Gom., Conclusions: Within the Goms took in consideration the proposed statistical technique showed that, depending on each Gom, correctly classified about 70% of individuals on risk of delaying permanence within the Roc. The ValPeRoc project evaluates Roc activity for the first time through a replicable analysis of patient pathway times from diagnosis to the act of treatment. Specifically, the times analyzed measure the quality of the regional health care system.

Objective: The primary goal of the Campania Oncology Network (ROC) was to reduce cancer delay and care fragmentation through the establishment of cancer-specific multidisciplinary oncologic groups (GOMs) and diagnostic and therapeutic assistance paths (PDTAs)., Methods: Five cancer centres of the ROC, with their own cancer specific GOM, were selected. In our analysis, we have focused on four neoplasms: lung, colon, ovarian and prostate cancers. The median time for pre-GOM and GOM Times was calculated for each tumour site. Univariate and multivariate logistic regressions were performed to individuate risk factors for pre-GOM and GOM Time., Results: Significant differences were observed for prostate cancer compared to other patients either for pre-GOM or GOM Times. Significant risks were found for ovarian and prostate cancers in pre-GOM time and for prostate cancer in GOM-Time., Conclusions: This experience will produce knowledge and data to guide decision-making and to manage more effectively the challenges of fighting cancer in Campania region. The Valutazione Percorso Rete Oncologica Campana (ValPeROC) study evaluates, for the first time, the ROC activity, through the analysis of key performance indices. Pre-GOM and GOM Time represent the quality of the entire regional health system and are useful to define models, which can evaluate the performance of the ROC over time., (© 2022 John Wiley & Sons Ltd.)