The number of physically active individuals who develop knee and hip arthritis and who undergo arthroplasties of these joints ie ever increasing. It has become necessary to develop evaluation scales which address the specific issues raised by such individuals. The High Activity Arthroplasty Score is one such scales, originally developed in English. The HAAS-I was developed by means of forward-backward translation, a final review by an expert committee and a test of the pre-final version to establish its correspondence with the original English version. The psychometric testing included reliability by means of internal consistency (Cronbach’s alpha) and test–retest reliability (intraclass correlation coefficients) and construct validity by Pearson’s correlations with a pain intensity numerical rating scale (NRS), the Western Ontario and McMaster University index (WOMAC, for THA subjects), the Knee injury and Osteoarthritis Outcome Scale (KOOS; for TKA subjects) and the Short-Form 36 Health Survey (SF-36). The questionnaire was administered to 67 subjects with THA and 61 with TKA and proved to be acceptable. The questionnaire showed good internal consistency (0.85 for THA and 0.91 for TKA) and a high level of test–retest reliability (ICC = 0.97 with 95% CI 0.95–0.98 for THA; ICC = 0.95 with 95% CI 0.92–0.98 for TKA). There was a moderate correlation between the HAAS-I and NRS (r = − 0.40), there was a high correlation between the HAAS-I and WOMAC (r = − 0.68) and there were moderate to high correlations between the HAAS-I and SF-36 subscales (r = 0.34 to 0.63) for THA. There was a moderate correlation between the HAAS-I and NRS (r = − 0.77); there was a high correlation between the HAAS-I and KOOS subscales (r = − 0.79 to r = − 0.91); and there were low correlations between the HAAS-I and SF-36 subscales (r = 0.01 to 0.29) for TKA. The HAAS-I was successfully translated into Italian and proved to have good psychometric properties that replicated the results of existing versions. Its use is recommended for clinical and research purposes.
14 March 2023 in Advances in Data Analysis and Classification
The Threshold-based Naïve Bayes (Tb-NB) classifier is introduced as a (simple) improved version of the original Naïve Bayes classifier. Tb-NB extracts the sentiment from a Natural Language text corpus and allows the user not only to predict how much a sentence is positive (negative) but also to quantify a sentiment with a numeric value. It is based on the estimation of a single threshold value that concurs to define a decision rule that classifies a text into a positive (negative) opinion based on its content. One of the main advantage deriving from Tb-NB is the possibility to utilize its results as the input of post-hoc analysis aimed at observing how the quality associated to the different dimensions of a product or a service or, in a mirrored fashion, the different dimensions of customer satisfaction evolve in time or change with respect to different locations. The effectiveness of Tb-NB is evaluated analyzing data concerning the tourism industry and, specifically, hotel guests’ reviews from all hotels located in the Sardinian region and available on Booking.com. Moreover, Tb-NB is compared with other popular classifiers used in sentiment analysis in terms of model accuracy, resistance to noise and computational efficiency.
19 October 2019 in Knowledge and Information Systems
The use of digital image analysis for discriminating between and comparing groups of seeds is becoming an increasingly common practice in taxonomic studies. For this type of study, many variables, concerning different kinds of data such as size, texture and shape, are generally used as inputs in statistical algorithms without any data pre-processing, thereby generating problems with noise and the consistency of the process for new samples. We propose an approach in which the variables for each kind of data are separately pre-processed by performing Principal Component Analysis and Fourier Analysis. Furthermore, the accuracy of the different kinds of data is measured by comparing the results obtained using several classification algorithms: k-Nearest Neighbour, Linear Discriminant Analysis, Naive Bayes, Support Vector Machines and Random Forest. We have taken as a case study the seeds of 19 cultivars of Sardinian Prunus domestica L. and four cultivars referable to other Prunus species. The combination of size, texture and shape data was able to perform well in discriminating between the seeds of Prunus sp. The present study confirms that image analysis techniques combined with the pre-processing of data are a useful tool for taxonomic investigation in plant biology and for discrimination at the cultivar level.
Purpose: To culturally adapt and validate the Urogenital Distress Inventory-6 and Incontinence Impact Questionnaire-7 (short forms) for use in Italian-speaking women with urinary incontinence. Methods: We developed Italian versions of the two questionnaires through forward-backward translation, expert review and cognitive interviews. We then administered them to 100 women with urinary incontinence (mean age 58.02 ± 11.9 years) to assess the internal consistency (Cronbach’s alpha), test–retest reliability (intraclass correlation coefficient), standard error of measurement, minimum detectable change, and construct validity by hypothesis testing. Results: No difficulties in acceptability emerged. Internal consistency was 0.61 for Urogenital Distress Inventory-6 and 0.88 for Incontinence Impact Questionnaire-7. Test–retest reliability was respectively 0.79 and 0.91. The minimum detectable change was respectively 22.9 and 18.1 points (on a 0–100 scale). Nine out of 10 a priori hypotheses regarding construct validity were confirmed. Conclusions: The Italian versions of the Urogenital Distress Inventory-6 and Incontinence Impact Questionnaire-7 showed reliability levels in line with the literature and good construct validity. Thus, we think that the present study extends the evidence for both questionnaires as useful tools for assessing women with urinary incontinence.
3 April 2023 in Statistical Methods & Applications
During the recent Coronavirus disease 2019 (COVID-19) outbreak, the microblogging service Twitter has been widely used to share opinions and reactions to events. Italy was one of the first European countries to be severely affected by the outbreak and to establish lockdown and stay-at-home orders, potentially leading to country reputation damage. We resort to sentiment analysis to investigate changes in opinions about Italy reported on Twitter before and after the COVID-19 outbreak. Using different lexicons-based methods, we find a breakpoint corresponding to the date of the first established case of COVID-19 in Italy that causes a relevant change in sentiment scores used as a proxy of the country’s reputation. Next, we demonstrate that sentiment scores about Italy are associated with the values of the FTSE-MIB index, the Italian Stock Exchange main index, as they serve as early detection signals of changes in the values of FTSE-MIB. Lastly, we evaluate whether different machine learning classifiers were able to determine the polarity of tweets posted before and after the outbreak with a different level of accuracy.