Personalized prediction of optimal water intake in adult population by blended use of machine learning and clinical data.

Growing evidence suggests that sustained concentrated urine contributes to chronic metabolic and kidney diseases. Recent results indicate that a daily urinary concentration of 500 mOsm/kg reflects optimal hydration. This study aims at providing personalized advice for daily water intake considering personal intrinsic (age, sex, height, weight) and extrinsic (food and fluid intakes) characteristics to achieve a target urine osmolality (UOsm) of 500 mOsm/kg using machine learning and optimization algorithms. Data from clinical trials on hydration (four randomized and three non-randomized trials) were analyzed. Several machine learning methods were tested to predict UOsm. The predictive performance of the developed algorithm was evaluated against current dietary guidelines. Features linked to urine production and fluid consumption were listed among the most important features with relative importance values ranging from 0.10 to 0.95. XGBoost appeared the most performing approach (Mean Absolute Error (MAE) = 124.99) to predict UOsm. The developed algorithm exhibited the highest overall correct classification rate (85.5%) versus that of dietary guidelines (77.8%). This machine learning application provides personalized advice for daily water intake to achieve optimal hydration and may be considered as a primary prevention tool to counteract the increased incidence of chronic metabolic and kidney diseases.

Multivariate nonparametric methods in two-way balanced designs: performances and limitations in small samples.

Investigations of multivariate population are pretty common in applied researches, and the two-way crossed factorial design is a common design used at the exploratory phase in industrial applications. When assumptions such as multivariate normality and covariance homogeneity are violated, the conventional wisdom is to resort to nonparametric tests for hypotheses testing. In this paper we compare the performances, and in particular the power, of some nonparametric and semi-parametric methods that have been developed in recent years. Specifically, we examined resampling methods and robust versions of classical multivariate analysis of variance (MANOVA) tests. In a simulation study, we generate data sets with different configurations of factor's effect, number of replicates, number of response variables under null hypothesis, and number of response variables under alternative hypothesis. The objective is to elicit practical advice and guides to practitioners regarding the sensitivity of the tests in the various configurations, the tradeoff between power and type I error, the strategic impact of increasing number of response variables, and the favourable performance of one test when the alternative is sparse. A real case study from an industrial engineering experiment in thermoformed packaging production is used to compare and illustrate the application of the various methods.

Machine learning and design of experiments with an application to product innovation in the chemical industry.

Industrial statistics plays a major role in the areas of both quality management and innovation. However, existing methodologies must be integrated with the latest tools from the field of Artificial Intelligence. To this end, a background on the joint application of Design of Experiments (DOE) and Machine Learning (ML) methodologies in industrial settings is presented here, along with a case study from the chemical industry. A DOE study is used to collect data, and two ML models are applied to predict responses which performance show an advantage over the traditional modeling approach. Emphasis is placed on causal investigation and quantification of prediction uncertainty, as these are crucial for an assessment of the goodness and robustness of the models developed. Within the scope of the case study, the models learned can be implemented in a semi-automatic system that can assist practitioners who are inexperienced in data analysis in the process of new product development.

Improved Non-Invasive Diagnosis of Bladder Cancer with an Electronic Nose: A Large Pilot Study.

BACKGROUND: Bladder cancer (BCa) emits specific volatile organic compounds (VOCs) in the urine headspace that can be detected by an electronic nose. The diagnostic performance of an electronic nose in detecting BCa was investigated in a pilot study. METHODS: A prospective, single-center, controlled, non-randomized, phase 2 study was carried out on 198 consecutive subjects (102 with proven BCa, 96 controls). Urine samples were evaluated with an electronic nose provided with 32 volatile gas analyzer sensors. The tests were repeated at least two times per sample. Accuracy, sensitivity, specificity, and variability were evaluated using mainly the non-parametric combination method, permutation tests, and discriminant analysis classification. RESULTS: Statistically significant differences between BCa patients and controls were reported by 28 (87.5%) of the 32 sensors. The overall discriminatory power, sensitivity, and specificity were 78.8%, 74.1%, and 76%, respectively; 13/96 (13.5%) controls and 29/102 (28.4%) BCa patients were misclassified as false positive and false negative, respectively. Where the most efficient sensors were selected, the sensitivity and specificity increased up to 91.1% (72.5-100) and 89.1% (81-95.8), respectively. None of the tumor characteristics represented independent predictors of device responsiveness. CONCLUSIONS: The electronic nose might represent a potentially reliable, quick, accurate, and cost-effective tool for non-invasive BCa diagnosis.

Personalized Tests in Paralympic Athletes: Aerobic and Anaerobic Performance Profile of Elite Wheelchair Rugby Players.

In Paralympic sports, the goal of functional classifications is to minimize the impact of impairment on the outcome of the competition. The present cross-sectional study aimed to investigate aerobic and anaerobic personalized tests in Paralympic athletes and to correlate them with the classification of the international wheelchair rugby federation (IWRF). Sixteen elite players of the Italian wheelchair rugby team volunteered for the study. Aerobic (incremental test to exhaustion) and anaerobic (Wingate 30s all-out test, 5 and 10-meter sprint test, shuttle test, isometric test) sport-performance measurements were correlated singularly or grouped (Z scores) with the classification point. Moreover, a multivariate permutation-based ranking analysis investigated possible differences in the overall level of performance among the adjacent classified groups of players, considering the scores of each test. A statistically significant correlation between the performance parameters and the IWRF functional classification considering both aerobic and anaerobic personalized tests was detected (0.58 ≤ r ≤ 0.88; 0.0260 ≤ p ≤ 0.0001). The multivariate permutation-based ranking analysis showed differences only for the low-pointers versus mid-pointers (p = 0.0195) and high-pointers (p = 0.0075). Although single performance parameters correlated with athletes' classification point, results of the multivariate permutation-based ranking analysis seem to suggest considering only the most significant anaerobic and sport-specific performance parameters among athletes. These should be combined with the physical assessment and the qualitative observation, which are already part of the classification process to improve its effectiveness.

Multivariate permutation tests for two sample testing in presence of nondetects with application to microarray data.

Very often, data collected in medical research are characterized by censored observations and/or data with mass on the value zero. This happens for example when some measurements fall below the detection limits of the specific instrument used. This type of left censored observations is called "nondetects". Such a situation of an excessive number of zeros in a data set is also referred to as zero-inflated data. In the present work, we aim at comparing different multivariate permutation procedures in two-sample testing for data with nondetects. The effect of censoring is investigated with regard to the different values that may be attributed to nondetected values, both under the null hypothesis and under alternative. We motivate the problem using data from allergy research.

Nonparametric combination tests for comparing two survival curves with informative and non-informative censoring.

This paper looks at permutation methods used to deal with hypothesis testing within the survival analysis framework. In the literature, several attempts have been made to deal with the comparison of survival curves and, depending on the survival and hazard functions of two groups, they can be more or less efficient in detecting differences. Furthermore, in some situations, censoring can be informative in that it depends on treatment effect. Our proposal is based on the nonparametric combination approach and has proven to be very effective under different configurations of survival and hazard functions. It allows the practitioner to test jointly on primary and censoring events and, by using multiple testing methods, to assess the significance of the treatment effect separately on the survival and the censoring process.

Alkaline Water and Longevity: A Murine Study.

The biological effect of alkaline water consumption is object of controversy. The present paper presents a 3-year survival study on a population of 150 mice, and the data were analyzed with accelerated failure time (AFT) model. Starting from the second year of life, nonparametric survival plots suggest that mice watered with alkaline water showed a better survival than control mice. Interestingly, statistical analysis revealed that alkaline water provides higher longevity in terms of "deceleration aging factor" as it increases the survival functions when compared with control group; namely, animals belonging to the population treated with alkaline water resulted in a longer lifespan. Histological examination of mice kidneys, intestine, heart, liver, and brain revealed that no significant differences emerged among the three groups indicating that no specific pathology resulted correlated with the consumption of alkaline water. These results provide an informative and quantitative summary of survival data as a function of watering with alkaline water of long-lived mouse models.

Iterated combination-based paired permutation tests to determine shape effects of chemotherapy in patients with esophageal cancer.

The nonparametric combination of dependent permutation tests method is a useful general tool when a testing problem can be broken down into a set of different k > 1 partial tests. These partial tests, after adjustment of p-values to control for multiplicity, can be marginally analyzed, but jointly considered they can provide information on an overall hypothesis, which might represent the true goal of the testing problem. On the one hand, independence among the partial tests is usually an unrealistic assumption; on the other, even when the underlying dependence relations are known quite often they are difficult to cope with properly. Therefore this combination must be achieved nonparametrically, by implicitly taking into account the dependence structure of tests without explicitly describing it. An important property of the tests based on nonparametric combination methodology, when the number of response variables is high compared to the sample sizes, consists in the finite sample consistency. A practical problem involves choosing the most suitable combining function for each specific testing problem given that the final result can be affected by this crucial choice. The purpose of this article is to present an nonparametric combination solution based on the iterated combination of partial tests, evaluate its power behavior using a Monte Carlo simulation study and apply it to a real medical problem, namely the evaluation of the effects of chemotherapy on the shape of esophageal tumors. R code has been implemented to carry out the analyses.

[Statistical tests in medical research: traditional methods vs. multivariate NPC permutation tests]. / Test statistici nella ricerca medica: metodi tradizionali vs test multivariati di permutazione NPC.

Statistical tests in medical research: traditional methods vs. multivariate npc permutation tests.Within medical research, a useful statistical tool is based on hypotheses testing in terms of the so-called null, that is the treatment has no effect, and alternative hypotheses, that is the treatment has some effects. By controlling the risks of wrong decisions, empirical data are used in order to possibly reject the null hypotheses in favour of the alternative, so that demonstrating the efficacy of a treatment of interest. The multivariate permutation tests, based on the nonparametric combination - NPC method, provide an innovative, robust and effective hypotheses testing solution to many real problems that are commonly encountered in medical research when multiple end-points are observed. This paper discusses the various approaches to hypothesis testing and the main advantages of NPC tests, which consist in the fact that they require much less stringent assumptions than traditional statistical tests. Moreover, the related results may be extended to the reference population even in case of selection-bias, that is non-random sampling. In this work, we review and discuss some basic testing procedures along with the theoretical and practical relevance of NPC tests showing their effectiveness in medical research. Within the non-parametric methods, NPC tests represent the current "frontier" of statistical research, but already widely available in the practice of analysis of clinical data.

Metabolic syndrome associated with primary biliary cirrhosis.

INTRODUCTION: Primary biliary cirrhosis (PBC) is characterized by a long natural history and a low incidence of cardiovascular events despite high serum cholesterol levels. The role of any metabolic conditions (obesity, hypertension, diabetes) in association with PBC has not been analyzed, however. AIM: : To assess the influence of metabolic syndrome (MS) on response to ursodeoxycholic acid (UDCA) and the survival in PBC patients. METHODS: The historical database (1975 to 2011) comprising consecutively enrolled PBC patients with a mean follow-up of 123 months (range, 12 to 425 mo) was used. All patients were treated with UDCA (15 mg/kg/d). Responders to UDCA were defined as patients achieving at least a 40% drop in their alkaline phosphatase levels after 1 year. MS was defined according to the American Heart Association criteria. Survival was analyzed by means of Kaplan-Meier curves. RESULTS: A total of 171 PBC patients were eligible for the study; 55 of them (32.1%) fulfilled the criteria for MS at presentation. Liver function tests and Mayo score were found comparable in PBC patients with and without MS. Histologic stages were similar in the 2 groups at the baseline. Significantly more cardiovascular events occurred in patients with MS during the follow-up (P<0.0001). Response to UDCA was greater in the group without MS, but the difference was not statistically significant. The Kaplan-Meier curves were similar in the 2 groups. CONCLUSIONS: When associated with MS, PBC should be monitored carefully due to the risk of cardiovascular events.

Long-term results of sequential vein coronary artery bypass grafting compared with totally arterial myocardial revascularization: a propensity score-matched follow-up study†.

OBJECTIVES: The aim of the study was to analyse the early and long-term outcomes of a consecutive series of patients who underwent sequential coronary artery bypass grafting (CABG) and to compare them with a matched population of totally arterial revascularized patients. METHODS: From January 1994 to December 1996, 209 patients underwent total arterial myocardial revascularization at our institution [arterial (ART) group]. In the same period, 2097 patients underwent CABG with left internal thoracic artery on left anterior descending and great saphenous vein on the right and circumflex branches sequentially [sequential vein (SV) group]. The propensity score methodology was used to obtain risk-adjusted outcome comparisons between the two groups (209 vs 243 patients in the ART group and SV group, respectively). RESULTS: In-hospital mortality was 1% in the ART group and 0.4% in the SV group (P = 0.86). Mean follow-up was 14 ± 4 years. Long-term survival was comparable among the two study groups [actuarial 5- and 15-year survival rates were 97 vs 93% and 82 vs 79% in the ART group and the SV group, respectively (P = 0.29)]. At follow-up, recurrence of angina (17 vs 18%; P = 0.99), acute myocardial infarction (MI) (3 vs 5%; P = 0.72) and repeated percutaneous coronary intervention (19 vs 21%; P = 0.69) were similar in the ART group compared with the SV group. In the Cox regression analysis, type of revascularization was not an independent predictor of any long-term outcomes (death or major adverse cardiac events). In asymptomatic patients, exercise stress test at follow-up was comparable between the two groups (P = 0.14). CONCLUSIONS: Sequential vein CABG appears to have good early and long-term clinical outcomes. Also, early and long-term incidence of acute MI was not significantly higher in the SV group. However, further studies with a larger population are warranted in order to confirm the present results.

Reliability of multiple-degree incisal/occlusal tooth wear assessment on dental casts: findings from a fiveexaminer investigation and related clinical implications.

OBJECTIVE: The aim was to answer the clinical research question: is incisal/occlusal tooth wear assessment on dental casts performed by five professionals with expertise in different fields of dentistry reliable? METHOD AND MATERIALS: Five examiners with different fields of expertise in the dental profession assessed tooth wear on dental casts of 45 subjects, based on a six-degree rating of incisal/occlusal wear. After a calibration meeting, the examiners evaluated the casts individually and various issues concerning interexaminer agreement and reliability were assessed. RESULTS: A total of 872 teeth were evaluated. The five examiners agreed only for the rating of 6.6% of the teeth. The teeth with the highest percentage of agreement were the premolars. Pairwise comparison of the assessments of the examiners #1 (bruxism expert), #2 (orthodontist), #3 (temporomandibular disorders [TMD] and occlusion expert), #4 (dental nurse) showed fair to moderate agreement, with κ-values ranging from 0.306 to 0.577, whilst the examiner #5 (lab technician) achieved low interexaminer reliability values with all the other four examiners. CONCLUSION: The interexaminer reliability of tooth wear assessment on dental casts performed by five professionals with expertise in different fields of dentistry is highly variable. General practitioners should keep in mind that consensus decisions by the examiners and assessment by raters belonging to the same dental discipline are recommended strategies to increase the reliability of tooth wear evaluation in the clinical setting. CLINICAL SIGNIFICANCE: This investigation adds to the literature suggesting that, in a clinical setting, a single examiner's assessment of tooth wear on dental casts does not have optimal reliability and that it may be source of internal validity problems in the research setting.

Measured and perceived environmental comfort: field monitoring in an Italian school.

Microclimatic conditions were recorded in an Italian school and Fanger's indexes PMV and PPD were calculated under different conditions. Students' sensations were investigated four times by means of two surveys, one related to actual microclimatic conditions and one on overall satisfaction, interaction occupant-building and reactions to discomfort. Pupils' classroom position was considered to look for possible influence on thermal comfort: a difference emerged from PMV and the survey, but the results obtained from the two approaches differ for both the entity of discomfort and its distribution within each classroom. Innovative multivariate nonparametric statistical techniques were applied to compare and rank the classrooms in accordance with students' subjective perceptions; a global ranking has been also calculated, considering thermal and visual comfort and air quality. Comparing pupil-sensation-based ranking with environmental parameters no clear correspondence was found, except for mid-season, where PMV, CO2 concentration and desk illuminance were similar in all the classrooms.

Comparison of magnetic resonance imaging findings in temporomandibular joints of the two sides.

OBJECTIVES: The aim of this investigation was to assess the association of magnetic resonance imaging (MRI)-diagnosed temporomandibular joint (TMJ) disorders [i.e., disc displacement with reduction, disc displacement without reduction (DDNR), osseous changes (OC), joint effusion] on the same side as well as in the joints of the two sides of the same individual. MATERIALS AND METHODS: A total of 199 patients undergoing bilateral MRI of the TMJs were included in the study. A single variable correlation matrix was created to assess the within- and between-side correlation of single diagnoses. Then, based on 12 possible combinations of diagnoses per each side, a contingency table was created to assess the chi-square values of the differences between the observed and expected frequencies of the different cross-combinations. Multiple variable permutation test was performed to assess the null hypothesis that the diagnoses in the right and left joints are not related. RESULTS: Within the signs of the same side, DDNR was positively correlated with OC. As for combination of diagnoses, the presence of a specific combination of signs on one side implied the same combination of signs on the other side. The global multivariate permutation test with Tippett combination was significant at p < 0.001, showing that the null hypothesis of independence between diagnoses of the two sides was rejected. CONCLUSIONS: It can be suggested that disc displacement without reduction is associated with osseous changes of the same joint and that joints of the two sides are likely to be affected by the same combinations of MRI signs. CLINICAL RELEVANCE: This investigation supports the concept that the two temporomandibular joints work as a unit.

Quantitative evaluation of the clinical effects of S-adenosylmethionine on mood and behavior in Lesch-Nyhan patients.

UNLABELLED: BACKGROUND, RATIONALE, AND METHODS: Lesch-Nyhan disease is a rare, X-linked disorder due to hypoxanthine phosphoribosyltransferase deficiency. To evaluate reported benefit on mood and behavior obtained by the administration of S-adenosyl-L-methionine in this condition, we developed 2 quantitative evaluation tools, and used them to assess the effects of the drug in our population: the weekly questionnaire and the resistance to self-injurious behavior test. We performed an open-label, dose-escalation trial of the drug on 14 patients. RESULTS: Four patients tolerated the drug and reported beneficial effects. The majority experienced worsened behavior. The 2 assessment tools demonstrated effectiveness in quantitatively evaluating the self-injurious behavior.

An assessment of the usefulness of jaw kinesiography in monitoring temporomandibular disorders: correlation of treatment-related kinesiographic and pain changes in patients receiving temporomandibular joint injections.

BACKGROUND: The authors conducted a study in patients with temporomandibular joint (TMJ) osteoarthritis to assess whether treatment-related changes in pain levels and chewing ability coincide with a change in jaw kinesiographic (KG) parameters. METHODS: The authors selected 34 patients with a diagnosis of TMJ osteoarthritis that met Research Diagnostic Criteria for Temporomandibular Disorders (RDC/TMD) to undergo a cycle of five weekly arthrocentesis procedures with injections of 1 milliliter hyaluronic acid. They performed a permutation test to assess the correlation between changes across time (from baseline to end of treatment) in two clinical outcome parameters-pain level and chewing ability-and changes across time in the KG outcome parameters. RESULTS: The authors observed improvement across time in both chewing ability (F = 8.328; P = .005) and pain level (F = 10.903; P = .002). The authors observed no significant changes in any KG variables. With minor exceptions, no significant correlations were shown between changes in the clinical and KG parameters during the treatment period. CONCLUSIONS: Treatment-related changes in pain levels and chewing ability in patients with TMJ osteoarthritis do not coincide with changes in KG parameters. PRACTICAL IMPLICATIONS: If one assumes pain variables to be the primary outcome measures in assessing treatment of TMJ osteoarthritis, KG recordings of the jaw are not useful for monitoring TMJ osteoarthritis in the clinical setting.

Cyclic variations of bone resorption mediators and markers in the different phases of the menstrual cycle.

Female hormones are very important in regulating bone homeostasis; the drop of estrogen levels occurring at menopause is linked to a dramatic prevalence of bone resorption on formation. Only a small number of studies investigated the relationship between changes in circulating female sex hormones and the markers and mediators of bone homeostasis and they showed conflicting results. To explore such relationships we studied 20 young fertile healthy women, aged between 19 and 32 years. None had received hormone treatment for at least 6 months. We assayed luteinizing hormone, follicle-stimulating hormone, progesterone and 17ß-estradiol, as well as the levels of osteoprotegerin (OPG), C-terminal telopeptide of collagen type I (CTx) and RANKL (receptor activator of nuclear factor-B ligand) in samples drawn from every subject at four different times during the menstrual cycle when estrogens are lowest, at the start of the cycle: T 0 (2-4th day); when estrogens are highest, in the pre-ovulatory period: T 14 (12-14th day); when progesterone activity is highest, in the advanced luteal phase: T 26 (24-26th day); and again at the start of the next cycle: T 01 (2-4th day). We observed that CTx levels are highest at the start of the cycle, decreased significantly from T 0 to T 26 (pfwe = 0.0455) and then increased from T 26 to T 01 (pfwe = 0.0415); OPG, on the other hand, which was also highest at the start of the cycle, decreased significantly from T 0 to T 14 (pfwe = 0.02) and then increased, though not significantly, from T 14 to T 01; no variation was observed in RANKL values at any time. We observed inverse correlations between estradiol and OPG levels, which became highly significant at T 01 between estradiol nadir and OPG peak levels (pfw = 0.0095). Furthermore, the increase of estradiol from T 0 to T 14 was negatively correlated with the concomitant decrease of OPG (pfwe = 0.0277), as was the fall of estradiol from T 26 to T 01 with the OPG peak levels, both at T 01 (pfw = 0.0045) and at T 0 (pfwe = 0.0381). We also observed direct correlations between the OPG levels and the variations of progesterone in the preceding intervals, but they never attained statistical significance. We conclude that OPG and CTx fluctuation during the menstrual cycle are likely due to the physiological variations of sex steroids levels.

Robust non-parametric tests for complex-repeated measures problems in ophthalmology.

The NonParametric Combination methodology (NPC) of dependent permutation tests allows the experimenter to face many complex multivariate testing problems and represents a convincing and powerful alternative to standard parametric methods. The main advantage of this approach lies in its flexibility in handling any type of variable (categorical and quantitative, with or without missing values) while at the same time taking dependencies among those variables into account without the need of modelling them. NPC methodology enables to deal with repeated measures, paired data, restricted alternative hypotheses, missing data (completely at random or not), high-dimensional and small sample size data. Hence, NPC methodology can offer a significant contribution to successful research in biomedical studies with several endpoints, since it provides reasonably efficient solutions and clear interpretations of inferential results. Pesarin F. Multivariate permutation tests: with application in biostatistics. Chichester-New York: John Wiley &Sons, 2001; Pesarin F, Salmaso L. Permutation tests for complex data: theory, applications and software. Chichester, UK: John Wiley &Sons, 2010. We focus on non-parametric permutation solutions to two real-case studies in ophthalmology, concerning complex-repeated measures problems. For each data set, different analyses are presented, thus highlighting characteristic aspects of the data structure itself. Our goal is to present different solutions to multivariate complex case studies, guiding researchers/readers to choose, from various possible interpretations of a problem, the one that has the highest flexibility and statistical power under a set of less stringent assumptions. MATLAB code has been implemented to carry out the analyses.

Treatment effectiveness of arthrocentesis plus hyaluronic acid injections in different age groups of patients with temporomandibular joint osteoarthritis.

PURPOSE: To investigate for treatment effectiveness in different age groups of patients with temporomandibular joint osteoarthritis who underwent a cycle of 5 weekly arthrocenteses plus hyaluronic acid injections. MATERIALS AND METHODS: We implemented a retrospective study on 76 patients followed up for 1 year. Outcome variables were pain levels at rest and during chewing, subjective masticatory efficiency, functional limitation, perceived efficacy, and jaw range of motion. Three age groups of patients were identified, and treatment effectiveness was compared among groups by means of a multistrata permutation test. RESULTS: All the partial P values of the subtests related to the age groups, adjusted according to the close testing method for controlling multiplicity, were significant: P = .009 (aged <45 years), P = .001 (aged 45-65 years), and P = .001 (aged >65 years). For the younger age group, the treatment had a significant effect only on the pain at mastication and on the subjective efficacy. For the other age groups, the treatment effectiveness was evident with regard to almost all the considered symptoms. CONCLUSIONS: Our findings suggested that the treatment protocol was more effective in patients older than 45 years, thus having important clinical implications regarding attempts to define tailored treatment protocols for patients with temporomandibular disorders.