Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features.

Breast cancer holds the highest diagnosis rate among female tumors and is the leading cause of death among women. Quantitative analysis of radiological images shows the potential to address several medical challenges, including the early detection and classification of breast tumors. In the P.I.N.K study, 66 women were enrolled. Their paired Automated Breast Volume Scanner (ABVS) and Digital Breast Tomosynthesis (DBT) images, annotated with cancerous lesions, populated the first ABVS+DBT dataset. This enabled not only a radiomic analysis for the malignant vs. benign breast cancer classification, but also the comparison of the two modalities. For this purpose, the models were trained using a leave-one-out nested cross-validation strategy combined with a proper threshold selection approach. This approach provides statistically significant results even with medium-sized data sets. Additionally it provides distributional variables of importance, thus identifying the most informative radiomic features. The analysis proved the predictive capacity of radiomic models even using a reduced number of features. Indeed, from tomography we achieved AUC-ROC 89.9 % using 19 features and 92.1 % using 7 of them; while from ABVS we attained an AUC-ROC of 72.3 % using 22 features and 85.8 % using only 3 features. Although the predictive power of DBT outperforms ABVS, when comparing the predictions at the patient level, only 8.7% of lesions are misclassified by both methods, suggesting a partial complementarity. Notably, promising results (AUC-ROC ABVS-DBT 71.8 % - 74.1 % ) were achieved using non-geometric features, thus opening the way to the integration of virtual biopsy in medical routine.

Promote Community Engagement in Participatory Research for Improving Breast Cancer Prevention: The P.I.N.K. Study Framework.

Breast cancer (BC) has overtaken lung cancer as the most common cancer in the world and the projected incidence rates show a further increase. Early detection through population screening remains the cornerstone of BC control, but a progressive change from early diagnosis only-based to a personalized preventive and risk-reducing approach is widely debated. Risk-stratification models, which also include personal lifestyle risk factors, are under evaluation, although the documentation burden to gather population-based data is relevant and traditional data collection methods show some limitations. This paper provides the preliminary results from the analysis of clinical data provided by radiologists and lifestyle data collected using self-administered questionnaires from 5601 post-menopausal women. The weight of the combinations of women's personal features and lifestyle habits on the BC risk were estimated by combining a model-driven and a data-driven approach to analysis. The weight of each factor on cancer occurrence was assessed using a logistic model. Additionally, communities of women sharing common features were identified and combined in risk profiles using social network analysis techniques. Our results suggest that preventive programs focused on increasing physical activity should be widely promoted, in particular among the oldest women. Additionally, current findings suggest that pregnancy, breast-feeding, salt limitation, and oral contraception use could have different effects on cancer risk, based on the overall woman's risk profile. To overcome the limitations of our data, this work also introduces a mobile health tool, the Dress-PINK, designed to collect real patients' data in an innovative way for improving women's response rate, data accuracy, and completeness as well as the timeliness of data availability. Finally, the tool provides tailored prevention messages to promote critical consciousness, critical thinking, and increased health literacy among the general population.

Dietary habits, lifestyle, and gestational diabetes in immigrant women: a survey in Northwestern Tuscany (Central Italy).

BACKGROUND: immigrant women diagnosed with gestational diabetes mellitus (GDM) have additional language and cultural obstacles in following lifestyle and dietary recommendations within a Western health care setting. OBJECTIVES: to describe: • sociodemographic characteristics and dietary and lifestyle behaviours in Italian and immigrant pregnant women who underwent a GDM screening; • any differences in these aspects among GDM Italian and immigrant women; • any differences in terms of primary maternal-neonatal outcomes among GDM and normal glucose tolerance (NGT) cohorts. DESIGN: survey. SETTING AND PARTICIPANTS: this survey was conducted in three hospitals located in Tuscany Region (Central Italy). According to a convenience sampling, an ad hoc questionnaire was administered both to Italian and immigrant women who underwent an oral glucose tolerance test. MAIN OUTCOME MEASURES: information about nutrition and lifestyle, medical and obstetric history, clinical and therapy data, maternal and neonatal primary outcomes was analysed. Eating habits have been investigated referring to the prudent diet, in order to also include those foods specifically consumed by the immigrant women, in addition to the Mediterranean Diet which is more widespread among Italians. RESULTS: a total of 117 Italian women (42 diagnosed with GDM) and 95 immigrant women (36 with GDM) were enrolled. Immigrant women showed lower adherence to the prudent diet compared to Italian women (p<0.05) and a broader use of unhealthy food preparation (e.g., frying; p<0.05). Primary maternal and neonatal outcomes (preterm birth, caesarean section, macrosomia) showed no statistical differences among GDM and NGT cohorts. CONCLUSIONS: even if immigrant and Italian women gained similar pregnancy outcomes, immigrant women showed lower adherence to the prudent diet at the time of GDM screening. An ethnic and tailored meal plan is needed to overcome cultural barriers in dietary recommendations during pregnancy in immigrant women.

Participation in Low Back Pain Management: It Is Time for the To-Be Scenarios in Digital Public Health.

Low back pain (LBP) carries a high risk of chronicization and disability, greatly impacting the overall demand for care and costs, and its treatment is at risk of scarce adherence. This work introduces a new scenario based on the use of a mobile health tool, the Dress-KINESIS, to support the traditional rehabilitation approach. The tool proposes targeted self-manageable exercise plans for improving pain and disability, but it also monitors their efficacy. Since LBP prevention is the key strategy, the tool also collects real-patient syndromic information, shares valid educational messages and fosters self-determined motivation to exercise. Our analysis is based on a comparison of the performance of the traditional rehabilitation process for non-specific LBP patients and some different scenarios, designed by including the Dress-KINESIS's support in the original process. The results of the simulations show that the integrated approach leads to a better capacity for taking on patients while maintaining the same physiotherapists' effort and costs, and it decreases healthcare costs during the two years following LBP onset. These findings suggest that the healthcare system should shift the paradigm towards citizens' participation and the digital support, with the aim of improving its efficiency and citizens' quality of life.

Cardiovascular Risk Perception and Knowledge among Italian Women: Lessons from IGENDA Protocol.

A multicenter, cross-sectional observational study (Italian GENder Differences in Awareness of Cardiovascular risk, IGENDA study) was carried out to evaluate the perception and knowledge of cardiovascular risk among Italian women. An anonymous questionnaire was completed by 4454 women (44.3 ± 14.1 years). The 70% of respondents correctly identified cardiovascular disease (CVD) as the leading cause of death. More than half of respondents quoted cancer as the greatest current and future health problem of women of same age. Sixty percent of interviewed women considered CVD as an almost exclusively male condition. Although respondents showed a good knowledge of the major cardiovascular risk factors, the presence of cardiovascular risk factors was not associated with higher odds of identifying CVD as the biggest cause of death. Less than 10% of respondents perceived themselves as being at high CVD risk, and the increased CVD risk perception was associated with ageing, higher frequency of cardiovascular risk factors and disease, and a poorer self-rated health status. The findings of this study highlight the low perception of cardiovascular risk in Italian women and suggest an urgent need to enhance knowledge and perception of CVD risk in women as a real health problem and not just as a as a life-threatening threat.

Long-term effects of a combination of isoflavones, agnus castus and magnolia extracts on climacteric symptoms and cardiometabolic risk profile in postmenopausal women.

OBJECTIVE: To evaluate the long-term effects of a combination of isoflavones, agnus castus and magnolia extracts (combined isoflavone compound [CIC]) on climacteric symptoms and cardiometabolic risk in symptomatic postmenopausal women. METHODS: This interventional, prospective study evaluated climacteric symptoms, mood and sleep disorders using the 21-item Greene Climacteric Scale (GCS) and 7-item Insomnia Severity Index (ISI) questionnaires; and cardiovascular, metabolic and thrombotic risk markers at baseline (T0) and after 12 months of CIC treatment (T1). RESULTS: In healthy postmenopausal women (N = 71), 12-month CIC treatment significantly reduced patient-reported vasomotor symptoms (100% vs. 17%), mood disorders (67% vs. 25%) and sleep disorders (89% vs. 19%%) (all p < .001) compared with baseline; and significantly improved GCS psychological, somatic, and vasomotor domain scores and ISI sleep disturbance scores (all p < .05). CIC significantly reduced systolic (p = .022) and diastolic blood pressure (p < .001), and heart rate (p < .001); glucose concentrations (p = .018), HOMA index (p = .013), and ALT (p = .035), homocysteine (p = .005) and NT-proBNP (p = .003) levels. CONCLUSIONS: Long-term CIC therapy improved vasomotor symptoms, mood disorders, sleep disorders, hemodynamic measurements and cardiometabolic risk markers in healthy postmenopausal women. CLINICALTRIALS.GOV IDENTIFIER: NCT03699150.

Sex- and gender-related differences linked to SARS-CoV-2 infection among the participants in the web-based EPICOVID19 survey: the hormonal hypothesis.

Objective To investigate sex- and gender-based differences linked to SARS-COV-2 infection and to explore the role of hormonal therapy (HT) in females. Study design Data from the self-administered, cross-sectional, web-based EPICOVID19 survey of 198,822 adults living in Italy who completed an online questionnaire during the first wave of the epidemic in Italy (April-May 2020) were analyzed. Main outcomes measures Multivariate binary logistic and multinomial regression models were respectively used to estimate the odds ratios (ORs) with 95% confidence intervals (CIs) for positive nasopharyngeal swab (NPS) test results and severe SARS-CoV-2 infection. Results The data from 6,873 participants (mean age 47.9 ± 14.1 years, 65.8% females) who had a known result from an NPS test were analyzed. According to the multivariate analysis, females had lower odds of a positive result from the NPS test (aOR 0.75, 95%CI 0.66-0.85) and of having a severe infection (aOR 0.46, 95%CI 0.37-0.57) than did their male counterparts. These differences were greater with decreasing age in both sexes. In addition, females aged ≥60 years receiving HT (N = 2,153, 47.6%) had a 46% lower probability of having a positive NPS test (aOR 0.54, 95%CI 0.36-0.80) than their same-aged peers who had never used HT; there were no differences in the younger age groups with respect to HT status. Conclusion Female sex was associated with an age-dependent lower risk of having a severe SARS-CoV-2 infection than their male counterparts. Age seemed to modify the relationship between HT status and infection: while the two were not related among younger participants, it was negative in the older ones. Future prospective studies are needed to elucidate the potential protective role sex hormones may play. Trial registration ClinicalTrials.gov NCT04471701.

Epidemiology of SARS-CoV-2 Infection in Italy Using Real-World Data: Methodology and Cohort Description of the Second Phase of Web-Based EPICOVID19 Study.

Digital technologies have been extensively employed in response to the SARS-CoV-2 pandemic worldwide. This study describes the methodology of the two-phase internet-based EPICOVID19 survey, and the characteristics of the adult volunteer respondents who lived in Italy during the first (April-May 2020) and the second wave (January-February 2021) of the epidemic. Validated scales and ad hoc questionnaires were used to collect socio-demographic, medical and behavioural characteristics, as well as information on COVID-19. Among those who provided email addresses during phase I (105,355), 41,473 participated in phase II (mean age 50.7 years ± 13.5 SD, 60.6% females). After a median follow-up of ten months, 52.8% had undergone nasopharyngeal swab (NPS) testing and 13.2% had a positive result. More than 40% had undergone serological test (ST) and 11.9% were positive. Out of the 2073 participants with at least one positive ST, 72.8% had only negative results from NPS or never performed it. These results indicate that a large fraction of individuals remained undiagnosed, possibly contributing to the spread of the virus in the community. Participatory online surveys offer a unique opportunity to collect relevant data at individual level from large samples during confinement.

Facing the National Recovery and Resilience Plan: Sources of Data, Indicators, and Participatory Strategies in Healthcare and Social Fields.

Innovation in governance and services should be the target of the Italian National Recovery and Resilience Plan. Monitoring processes, impacts, and outcomes requires a system of new indicators that are practical to collect. Secondary data sources, their availability, and their information potential should be evaluated, and primary sources should be implemented to supplement traditional disease surveillance. This work highlights the most relevant aspects for bridging the mismatching between complex community needs and current health/social supply and how those aspects could be faced. As a result, we propose a structured multi-phases process for setting the design and functionalities of a cooperative information system, built on the integration between secondary and primary data for informing policies about chronic low back pain (CLBP), a widely recognized determinant of disability and significant economic burden. In particular, we propose the Dress-KINESIS, a tool for improving community capacity development and participation that allows one to freely collect big health and social data and link it to existing secondary data. The system also may be able to monitor how the resources are distributed across different care sectors and suggest how to improve efficiency based on the patient's CLBP risk stratification. Moreover, it is potentially customizable in other fields of health.

The P.I.N.K. Study Approach for Supporting Personalized Risk Assessment and Early Diagnosis of Breast Cancer.

Breast cancer is a clear example of excellent survival when it is detected and properly treated in the early stage. Currently, screening of this cancer relies on mammography, which may be integrated by new imaging techniques for more exhaustive evaluation. The Personalized, Integrated, Network, Knowledge (P.I.N.K.) study is a longitudinal multicentric study involving several diagnostic centres across Italy, co-ordinated by the Italian National Research Council and co-funded by the Umberto Veronesi Foundation. Aim of the study is to evaluate the increased diagnostic accuracy in detecting cancers obtained with different combinations of imaging technologies, and find the most effective diagnostic pathway matching the characteristics of an individual patient. The study foresees the enrolment of 50,000 women over the age of 40 years presenting for breast examination and providing informed consent to data handling. So far, the 15 participating centres across Italy have recruited a total of 22,848 patients. Based on the analyses of the first 175 histopathological-proven breast cancers, mammographic sensitivity was estimated to be 61.7% (n = 108 cancers), whereas diagnostic accuracy increased by 35.5% (n = 44 cancers) when mammography was integrated with other imaging modalities (ultrasound and/or digital breast tomosynthesis). Increase was mainly determined by ultrasound alone. Given the ongoing data collection and recruitment, the number of cancers detected is too low to allow any further in-depth analysis to explore links to patient characteristics. Past studies show that the uniform approach of population screening guidelines should be revised in favour of more personalised regimens, where known standards are integrated by imaging techniques most suitable for the individual's characteristics. With the ultimate goal of identifying early breast cancer detection strategies, our preliminary results suggest that integrated diagnostic approach could lead to a paradigm shift from an age-based regimen toward more specific and effective risk-based personalised screening regimens, in order to reduce mortality from breast cancer.

Shifting the Paradigm: The Dress-COV Telegram Bot as a Tool for Participatory Medicine.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic management is limited by great uncertainty, for both health systems and citizens. Facing this information gap requires a paradigm shift from traditional approaches to healthcare to the participatory model of improving health. This work describes the design and function of the Doing Risk sElf-assessment and Social health Support for COVID (Dress-COV) system. It aims to establish a lasting link between the user and the tool; thus, enabling modeling of the data to assess individual risk of infection, or developing complications, to improve the individual's self-empowerment. The system uses bot technology of the Telegram application. The risk assessment includes the collection of user responses and the modeling of data by machine learning models, with increasing appropriateness based on the number of users who join the system. The main results reflect: (a) the individual's compliance with the tool; (b) the security and versatility of the architecture; (c) support and promotion of self-management of behavior to accommodate surveillance system delays; (d) the potential to support territorial health providers, e.g., the daily efforts of general practitioners (during this pandemic, as well as in their routine practices). These results are unique to Dress-COV and distinguish our system from classical surveillance applications.

The Individual Profile of Pathology as a New Model for Filling Knowledge Gaps in Health Policies for Chronicity.

Chronicity is the real challenge for public healthcare systems especially in relation to multi-morbidity. The growing demand for multidisciplinary care could be addressed by implementing integrated programs in the primary care field and facilitating other specific care only as necessary. Some models of long-term management have been suggested since the 2000s. The objective here is to propose the Individual Profile of Pathology (IPP) model as the preliminary step for identifying groups of population which shares health and social needs and for optimizing the management of chronicity, referring to the Kaiser Permanente Pyramid paradigm. The IPP model is able to inform a data feedback system for improving performances at the patient's individual level and for addressing and evaluating health policies. The stratification of needs comes out of the IPP algorithm. It works on patient information databases based on the logic of disease as a process that evolves over time and interacts with many factors unique to that patient. Individual patients' data used in this work refers to 138,859 subjects from a large area in Italy and concerns hospitalization, outpatient drug prescriptions, access to the emergency room and outpatient prescriptions for visits, laboratory/imaging tests, and medications. The IPP model allows to identify for each subject a complexity level, taking into account the weight of groups of pathologies, both in terms of absorption of resources and the level of severity. Costs and healthcare performances have been analyzed taking into account the complexity levels. The IPP model can be an efficient methodology for (a) improving performances at the patient's individual level (b) allowing standardized comparison among different geographical areas (c) supporting large population-focused surveillance programs and (d) providing knowledge to identify and fill the gaps in public health policies. Currently, the IPP algorithm is limited by data availability, restricted to the administrative databases processing, but the theoretical model is able to include more data dimensions providing the potential to identify homogeneous groups of subjects with a higher level of precision.

The CARPEDIEM Algorithm: A Rule-Based System for Identifying Heart Failure Phenotype with a Precision Public Health Approach.

Modern medicine remains dependent on the accurate evaluation of a patient's health state, recognizing that disease is a process that evolves over time and interacts with many factors unique to that patient. The CARPEDIEM project represents a concrete attempt to address these issues by developing reproducible algorithms to support the accuracy in detection of complex diseases. This study aims to establish and validate the CARPEDIEM approach and algorithm for identifying those patients presenting with or at risk of heart failure (HF) by studying 153,393 subjects in Italy, based on patient information flow databases and is not reliant on the electronic health record to accomplish its goals. The resulting algorithm has been validated in a two-stage process, comparing predicted results with (1) HF diagnosis as identified by general practitioners (GPs) among the reference cohort and (2) HF diagnosis as identified by cardiologists within a randomly sampled subpopulation of 389 patients. The sources of data used to detect HF cases are numerous and were standardized for this study. The accuracy and the predictive values of the algorithm with respect to the GPs and the clinical standards are highly consistent with those from previous studies. In particular, the algorithm is more efficient in detecting the more severe cases of HF according to the GPs' validation (specificity increases according to the number of comorbidities) and external validation (NYHA: II-IV; HF severity index: 2, 3). Positive and negative predictive values reveal that the CARPEDIEM algorithm is most consistent with clinical evaluation performed in the specialist setting, while it presents a greater ability to rule out false-negative HF cases within the GP practice, probably as a consequence of the different HF prevalence in the two different care settings. Further development includes analyzing the clinical features of false-positive and -negative predictions, to explore the natural clustering of markers of chronic conditions by adding additional methodologies, e.g., Social Network Analysis. CARPEDIEM establishes the potential that an algorithmic approach, based on integrating administrative data with other public data sources, can enable the development of low cost and high value population-based evaluations for improving public health and impacting public health policies.

Integrated information for integrated care in the general practice setting in Italy: using social network analysis to go beyond the diagnosis of frailty in the elderly.

BACKGROUND: Frailty has been defined in different ways and several diagnostic tools exist, but most of them are not applicable in routine primary care. Nonetheless, general practitioners (GPs) have a natural advantage in identifying frailty, due to their continued access to patients, patient-centered approach and training. GPs have also an advantage in conducting population-based evaluation as consequence of their role of gatekeepers of the health care system. This paper aims to identify those socio-demographic and clinical profiles and the relative information sources that, from the GPs' perspective, act as frailty markers, not solely as a diagnosis of state but as the ability to identify a patient's trajectory, over time, through the aging process. METHODS: This study was performed as a survey within a population aged 75 and over, attending 148 GPs in Italy. A total of 23,996 patients were classified by GPs in distinct frailty status, without the use of a specific evaluation tool, but only referring to general indications. Co-morbidity was objectively assessed by a record-linkage with previous hospitalizations, in order to assess the occurrence of previous illnesses that could be associated with the likelihood of being identified as frails or at risk. The methodological approach is based on social network analysis (SNA), suited to explore relational aspects of complex phenomena. RESULTS: Our findings reveal that GPs are able to perform low cost population-based evaluation, by exploiting the advantages of their approach to patients, combined with the information derived from their daily practice and from other sources currently available. CONCLUSION: We believe that informative integration among different sources of available data can provide a comprehensive picture of the health state of patients in a shorter time and at lower cost. The identification of limited patient trajectories based on these observations can enable the development of critical biomarkers/diagnostics and prognostic indicators that will enhance patient care and potentially reduce inappropriate healthcare use. We also believe that network analysis is an extremely flexible research tool and a rich theoretical paradigm, and it may be used in the healthcare planning.

Poly-pharmacy among the elderly: analyzing the co-morbidity of hypertension and diabetes.

Clinical medicine faces many challenges, e.g. applying personalized medicine and genomics in daily practice; utilizing highly specialized diagnostic technologies; prescribing costly therapeutics. Today's population is aging and patients are diagnosed with more co-morbid conditions than in the past. Co-morbidity makes management of the elderly difficult also in terms of pharmacotherapy. The high prevalence of hypertension and diabetes as co-morbidities is indicative of the complexities that can impact accuracy in diagnosis and treatment, with poly-pharmacy being a significant component. It is essential to apply analytic methods to evaluate retrospective data to understand real world patients and medical practice. This study applies social network analysis, a novel method, to administrative data to evaluate the scope and impact of poly-pharmacy and reveal potential problems in management of elderly patients with diabetes and hypertension. Social Network Analysis (SNA) enables the examination of large patient data sets to identify complex relationships that may exist and go undetected either because of infrequent observation or complexity of the interactions. The application of SNA identifies critical aspects derived from over-connected portions of the network. These criticalities mainly involve the high rate of poly-pharmacy that results from the observation of additional co-morbid conditions in the study population. The analysis identifies crucial factors for consideration in developing clinical guidelines to deal with real-world patient observations. The analysis of routine health data, as analyzed using SNA, can be further compared with the inclusion/exclusion criteria presented in the current guidelines and can additionally provide the basis for further enhancement of such criteria.

Bridging the gap between translational medicine and unmet clinical needs.

To date, the actual rate of successful translation has been extremely low although those few successes have been notable and provide for continued and expanding enthusiasm and support. This paper examines whether the fundamental premise may be flawed. Could the success rate be improved to further enhance quality of life and cost optimization for patients by changing the paradigm to "bedside to bench to bedside", and focusing the research on addressing unmet clinical needs? It examines all aspects of the healthcare ecosystem to understand issues that arise with real world patients and in real world clinical practice and how addressing these should be the focus of translational research.

Alcoholic drinks as triggers in primary headaches.

OBJECTIVE: This project aims to investigate the role of alcoholic drinks (ADs) as triggers for primary headaches. METHODS: Patients followed in the Headache Centre and presenting with migraine without aura, migraine with aura (MA), chronic migraine (CM), and tension-type headache (TH) were asked if their headache was precipitated by AD and also about their alcohol habits. Individual characteristics and drink habits were evaluated within two binary logistic models. RESULTS: About one half (49.7%) of patients were abstainers, 17.6% were habitual consumers, and 32.5% were occasional consumers. Out of 448 patients, only 22 (4.9%), all with migraine, reported AD as a trigger factor. None of 44 patients with MA and none of 47 patients with TH reported AD as a trigger factor. Among those patients with migraine who consume AD, only 8% reported that AD can precipitate their headache. Multivariate analyses showed that AD use, both occasional and habitual, is unrelated to TH. Moreover, analysis performed among migraine patients, points out that occasional and habitual drinkers have a lower risk of presenting with CM than abstainers, although statistical significance occurred only among occasional drinkers. Only 3% of migraine patients who abstain from AD reported that they do not consume alcohol because it triggers their headache. CONCLUSION: Our study shows that AD acts as headache triggers in a small percentage of migraine patients. Differing from some prior studies, our data suggest that AD do not trigger MA and TH attacks. Moreover, the percentage of abstainers in our sample is higher compared with that reported in general population surveys.

Health effects of exposure to waste incinerator emissions:a review of epidemiological studies.

This review evaluates the epidemiological literature on health effects in relation to incineration facilities. Several adverse health effects have been reported. Significant exposure-disease associations are reported by two thirds of the papers focusing on cancer (lung and larynx cancer, non-Hodgkin's lymphoma). Positive associations were found for congenital malformations and residence near incinerators. Exposure to PCB and heavy metals were associated with several health outcomes and in particular with reduction of thyroid hormones. Findings on non-carcinogen pathologies are inconclusive. Effect of biases and confounding factors must be considered in the explanation of findings. Methodological problems and insufficient exposure information generate difficulties on study results. Research needs include a better definition of exposure in qualitative and quantitative terms in particular by developing the use of biomarkers and by implementing environmental measurements.