Towards a Precision Medicine Approach Based on Machine Learning for Tailoring Medical Treatment in Alkaptonuria.

ApreciseKUre is a multi-purpose digital platform facilitating data collection, integration and analysis for patients affected by Alkaptonuria (AKU), an ultra-rare autosomal recessive genetic disease. It includes genetic, biochemical, histopathological, clinical, therapeutic resources and quality of life scores that can be shared among registered researchers and clinicians in order to create a Precision Medicine Ecosystem (PME). The combination of machine learning application to analyse and re-interpret data available in the ApreciseKUre shows the potential direct benefits to achieve patient stratification and the consequent tailoring of care and treatments to a specific subgroup of patients. In this study, we have developed a tool able to investigate the most suitable treatment for AKU patients in accordance with their Quality of Life scores, which indicates changes in health status before/after the assumption of a specific class of drugs. This fact highlights the necessity of development of patient databases for rare diseases, like ApreciseKUre. We believe this is not limited to the study of AKU, but it represents a proof of principle study that could be applied to other rare diseases, allowing data management, analysis, and interpretation.

Pediatric Tuberculosis in Italian Children: Epidemiological and Clinical Data from the Italian Register of Pediatric Tuberculosis.

Tuberculosis (TB) is one of the leading causes of death worldwide. Over the last decades, TB has also emerged in the pediatric population. Epidemiologic data of childhood TB are still limited and there is an urgent need of more data on very large cohorts. A multicenter study was conducted in 27 pediatric hospitals, pediatric wards, and public health centers in Italy using a standardized form, covering the period of time between 1 January 2010 and 31 December 2012. Children with active TB, latent TB, and those recently exposed to TB or recently adopted/immigrated from a high TB incidence country were enrolled. Overall, 4234 children were included; 554 (13.1%) children had active TB, 594 (14.0%) latent TB and 3086 (72.9%) were uninfected. Among children with active TB, 481 (86.8%) patients had pulmonary TB. The treatment of active TB cases was known for 96.4% (n = 534) of the cases. Overall, 210 (39.3%) out of these 534 children were treated with three and 216 (40.4%) with four first-line drugs. Second-line drugs where used in 87 (16.3%) children with active TB. Drug-resistant strains of Mycobacterium tuberculosis were reported in 39 (7%) children. Improving the surveillance of childhood TB is important for public health care workers and pediatricians. A non-negligible proportion of children had drug-resistant TB and was treated with second-line drugs, most of which are off-label in the pediatric age. Future efforts should concentrate on improving active surveillance, diagnostic tools, and the availability of antitubercular pediatric formulations, also in low-endemic countries.

Multilevel approach to male fertility by machine learning highlights a hidden link between haematological and spermatogenetic cells.

BACKGROUND: Male infertility represents a complex clinical condition requiring an accurate multilevel assessment, in which machine learning technology, combining large data series in non-linear and highly interactive ways, could be innovatively applied. METHODS: A longitudinal, observational, retrospective, big data study was carried out, applying for the first time the ML in the context of male infertility. A large database including all semen samples collected between 2010 and 2016 was generated, together with blood biochemical examinations, environmental temperature and air pollutants exposure. First, the database was analysed with principal component analysis and multivariable linear regression analyses. Second, classification analyses were performed, in which patients were a priori classified according to semen parameters. Third, machine learning algorithms were applied in a training phase (80% of the entire database) and in a tuning phase (20% of the data set). Finally, conventional statistical analyses were applied considering semen parameters and those other variables extracted during machine learning. RESULTS: The final database included 4239 patients, aggregating semen analyses, blood and environmental parameters. Classification analyses were able to recognize oligozoospermic, teratozoospermic, asthenozoospermic and patients with altered semen parameters (0.58 accuracy, 0.58 sensitivity and 0.57 specificity). Machine learning algorithms detected three haematological variables, that is lymphocytes number, erythrocyte distribution and mean globular volume, significantly related to semen parameters (0.69 accuracy, 0.78 sensitivity and 0.41 specificity). CONCLUSION: This is the first machine learning application to male fertility, detecting potential mathematical algorithms able to describe patients' semen characteristics changes. In this setting, a possible hidden link between testicular and haematopoietic tissues was suggested, according to their similar proliferative properties.

Complications and risk factors for severe outcome in children with measles.

OBJECTIVE AND DESIGN: Risk factors for severe measles are poorly investigated in high-income countries. The Italian Society for Paediatric Infectious Diseases conducted a retrospective study in children hospitalised for measles from January 2016 to August 2017 to investigate the risk factors for severe outcome defined by the presence of long-lasting sequelae, need of intensive care or death. RESULTS: Nineteen hospitals enrolled 249 children (median age 14.5 months): 207 (83%) children developed a complication and 3 (1%) died. Neutropaenia was more commonly reported in children with B3-genotype compared with other genotypes (29.5% vs 7.7%, p=0.01). Pancreatitis (adjusted OR [aOR] 9.19, p=0.01) and encephalitis (aOR 7.02, p=0.04) were related to severe outcome in multivariable analysis, as well as C reactive protein (CRP) (aOR 1.1, p=0.028), the increase of which predicted severe outcome (area under the receiver operating characteristic curve 0.67, 95% CI 0.52 to 0.82). CRP values >2 mg/dL were related to higher risk of complications (OR 2.0, 95% CI 1.15 to 3.7, p=0.01) or severe outcome (OR 4.13, 95% CI 1.43 to 11.8, p<0.01). CONCLUSION: The risk of severe outcome in measles is independent of age and underlying conditions, but is related to the development of organ complications and may be predicted by CRP value.

Seasonal variation of semen parameters correlates with environmental temperature and air pollution: A big data analysis over 6 years.

BACKGROUND: Male fertility is progressively declining in many developed countries, but the relationship between male infertility and environmental factors is still unclear. OBJECTIVES: To assess the influence of environmental temperature and air pollution on semen parameters, using a big-data approach. METHODS: A big data analysis of parameters related to 5131 men, living in a province of Northern Italy and undergoing semen analyses between January 2010 and March 2016 was performed. Ambient temperature was recorded on the day of analysis and the 90 days prior to the analysis and the average value of particulate matter (PM) and NO2 in the year of the test. All data were acquired by geocoding patients residential address. A data warehouse containing 990,904,591 data was generated and analysed by multiple regressions. RESULTS: 5573 semen analyses were collected. Both maximum and minimum temperatures registered on the day of collection were inversely related to total sperm number (p < .001), non-progressive motility (NPrM) (p < .005) and normal forms (p < .001). Results were confirmed considering temperature in the 30 and 60 days before collection, but not in the 90 days before collection. Total sperm number was lower in summer/autumn (p < .001) and was inversely related with daylight duration (p < .001). PM10 and PM2.5 were inversely related to PrM (p < .001 and p < .005) and abnormal forms (p < .001). CONCLUSIONS: This is the first evaluation of the relationship between male fertility-related parameters and environment using a big-data approach. A seasonal change in semen parameters was found, with a fluctuation related to both temperature and daylight duration. A negative correlation between air pollution and semen quality is suggested. Such seasonal and environmental associations should be considered when assessing changes of male fertility-related parameters over time.