Article
Health Care Sciences & Services
Hannah Johns, Julie Bernhardt, Leonid Churilov
Summary: Predicting patient outcomes based on patient characteristics and care processes is common in medical research, but simplifying multifaceted features into scalar variables for statistical analysis may result in a loss of important clinical detail. The limited range of distance-based predictive methods poses a challenge for researchers, who must balance between simplifying features for analysis or using methods that may not fully meet the needs of the analysis problem.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Oncology
Rodolphe Vallee, Jean-Noel Vallee, Carole Guillevin, Athena Lallouette, Clement Thomas, Guillaume Rittano, Michel Wager, Remy Guillevin, Alexandre Vallee
Summary: The study aims to use machine learning decision tree models applied to perfusion and spectroscopy MRI to classify lymphomas, glioblastomas, and metastases, and identify the underlying key pathophysiological processes involved in the decision-making algorithms of the models.
FRONTIERS IN ONCOLOGY
(2023)
Article
Agronomy
Elzbieta Wojcik-Gront, Marcin Studnicki
Summary: The study evaluated the yield variability of spring and winter triticale in 31 locations across Poland from 2009 to 2017, finding that spring triticale is more influenced by soil quality while winter triticale is more dependent on water availability, suggesting early sowing for spring triticale and consideration of fungicides and growth regulators for winter triticale grown in Poland with periodic excess water.
Article
Health Care Sciences & Services
Shashikant Rathod, Leena Phadke, Uttam Chaskar, Chetankumar Patil
Summary: According to the World Health Organization, one in ten adults will have Type 2 Diabetes Mellitus (T2DM) in the next few years. This study used a combined approach of resting and orthostatic challenge Heart Rate Variability (HRV) measurement with machine learning techniques to evaluate autonomic dysfunction in T2DM patients. The results showed a blunted autonomic response in the T2DM group compared to the control group, and the developed Classification and Regression Tree (CART) model had better performance in detecting autonomic dysfunction in T2DM.
TECHNOLOGY AND HEALTH CARE
(2022)
Article
Engineering, Industrial
Jiyong Choi, Daniel P. de Oliveira, Fernanda Leite
Summary: This research proposes a novel approach using Classification and Regression Trees to capture similarity in capital project benchmarking, specifically in healthcare projects. The trees are constructed by selecting critical and flexible features associated with cost and schedule performance of the projects. The effectiveness of the method is validated through statistical methods and comparative analysis. This new approach allows for more targeted performance comparisons.
JOURNAL OF MANAGEMENT IN ENGINEERING
(2022)
Article
Business, Finance
Koresh Galil, Ami Hauptman, Rosit Levy Rosenboim
Summary: This study utilizes machine learning techniques to predict corporate credit ratings, finding that classification and regression trees and support vector regression have their own advantages in accuracy and interpretability. However, unconstrained models may produce non-monotonic relationships, thus recommending the use of restricted models. Additionally, the importance of company size in credit rating prediction is underscored.
FINANCE RESEARCH LETTERS
(2023)
Article
Biotechnology & Applied Microbiology
Giovanni D'Addio, Leandro Donisi, Giuseppe Cesarelli, Federica Amitrano, Armando Coccia, Maria Teresa La Rovere, Carlo Ricciardi
Summary: Heart-rate variability, specifically analyzed through Poincare plot parameters, has been used to classify CHF patients into different NYHA classes using machine-learning algorithms. Statistical analysis and feature selection were conducted to choose the best subset of parameters for classification, resulting in promising ML results with accuracies exceeding 80% and AUROC values above 0.7. The study suggests the potential of using ML with unconventional parameters to automatically discriminate CHF patients, warranting further investigation with larger datasets.
BIOENGINEERING-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Shangwen Qu, Ronghua Wang, Jiangbi Hu, Li Yang
Summary: Improper design of bikeway systems can lead to safety risks for cyclists. This study focuses on quantifying cycling workload as a measure of safety and comfort. Through experiments and analysis, a quantitative model for assessing cycling workload is established.
APPLIED SCIENCES-BASEL
(2022)
Article
Cardiac & Cardiovascular Systems
Kelly D. Stamp, Marilyn A. Prasun, Thomas P. McCoy, Lisa Rathman
Summary: This study aimed to evaluate the validity, reliability, and accuracy of HF and PC providers' assignment of NYHA-FC using the NYHA-FC Guide. The results showed that the accuracy scores of HF providers were significantly higher than those of PC providers, indicating that the Guide played a role in assisting with assigning HF class.
Article
Public, Environmental & Occupational Health
Rui Zhu, Yun-Hao Zheng, Zi-Han Zhang, Pei-Di Fan, Jun Wang, Xin Xiong
Summary: This study developed a new category scheme for the profile morphology of temporomandibular disorders (TMDs) based on lateral cephalometric morphology. The study identified three subgroups based on cephalometric morphology and built a decision tree model with high prediction accuracy. This proposed category system may supplement the understanding of TMD and benefit the management of TMD treatment.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Chemistry, Analytical
Cukic Milena, Chiara Romano, Francesca De Tommasi, Massimiliano Carassiti, Domenico Formica, Emiliano Schena, Carlo Massaroni
Summary: Heart rate variability (HRV) indexes are useful for various applications and can be retrieved from the heart's electrical activity or mechanical signals recorded from the body's surface. However, the morphology of mechanical signals is strongly affected by body posture. This study investigated the feasibility of estimating HRV indexes from accelerometer and gyroscope data collected with a wearable IMU positioned at the xiphoid level.
Article
Engineering, Geological
Alireza Salimi, Jamal Rostami, Christian Moormann, Jafar Hassanpour
Summary: The study develops models for predicting TBM penetration rate by incorporating the effects of rock type, using field penetration index and machine learning algorithm. The models provide estimated FPIs based on different rock types, rock strength, and rock mass properties, presented in the form of graphs.
ROCK MECHANICS AND ROCK ENGINEERING
(2022)
Review
Biochemistry & Molecular Biology
Giuseppe Gancitano, Russel J. Reiter
Summary: The aim of this review is to provide a general overview on the rationale and potential benefits of melatonin for military personnel. Melatonin can help stabilize wounded individuals, especially in battlefield conditions where immediate access to medical care may be limited. It also has the potential to synchronize the neuro-cardio-respiratory systems, contributing to the oscillation of the heartbeat in synchrony with the breath. This field of investigation holds promise for future research.
Article
Engineering, Environmental
Mahshid Oladi, Mohammad Reza Shokri
Summary: This study assessed the impact of oil-related activities on coral reefs using multiple indicators, with bioaccumulation of PAH in coral tissues, live coral cover, and the Sediment Constituent (SEDCON) Index identified as the most robust proxies. The study emphasized the need for routine monitoring and mitigation practices to maintain healthy reefs in the study areas, particularly in locations subjected to PAH pollution.
JOURNAL OF HAZARDOUS MATERIALS
(2021)
Article
Chemistry, Analytical
Aline Taoum, Alexis Bisiaux, Florian Tilquin, Yann Le Guillou, Guy Carrault
Summary: Continuous measurement of heart rate variability using wearable devices is important for monitoring physiological status and preventing diseases. This study compared HRV features measured by a commercial device (Bora Band) and reference electrocardiography (ECG), and validated the use of ultra-short-term HRV as a substitute for short-term HRV features. The results showed agreement between PPG and ECG recordings for most HRV features, and the Bora Band provided valid and reliable HRV measurements in both short and ultra-short-term recordings.
Article
Economics
Carlo Federici, Leandro Pecchia
Summary: Payers and manufacturers may have different opinions on the evidence required for new medical devices, leading to sub-optimal decisions and high societal costs. This study evaluated a total artificial heart using a cost-effectiveness model, calculating the expected value of perfect information (EVPI) from both perspectives. Different decision rules and constraints resulted in significant differences in EVPI between manufacturers and payers. The use of value of information can highlight potential misalignments and facilitate early discussions between manufacturers and payers.
Review
Medicine, General & Internal
Katy Stokes, Busola Oronti, Francesco P. Cappuccio, Leandro Pecchia
Summary: This article presents a systematic review on the use of technologies, including mobile health technology, internet of things devices, and artificial intelligence, in hypertension healthcare in sub-Saharan Africa. The study findings suggest that the use of mobile technology for hypertension management in this region is effective and has positive outcomes.
Article
Medicine, General & Internal
Alessia Maccaro, Davide Piaggio, Iyabosola Busola Oronti, Marius Vignigbe, Antoinette Gbokli, Roch Houngnihin, Leandro Pecchia
Summary: This study investigates the importance of social engagement in the fight against COVID-19 in low-resource settings, with a focus on Benin. The results suggest that there is widespread hesitancy towards the vaccine and tracking program in Benin due to local beliefs and uncertainty about government management. Traditional medical practices and fear of neo-colonialism were also identified as hindrances to population involvement. The study calls for a specific framework to interpret and manage bioethical and biomedical issues in low-resource settings.
FRONTIERS IN MEDICINE
(2022)
Article
Medical Informatics
Carmelo De Maria, Andres Diaz Lantada, Timo Jamsa, Leandro Pecchia, Arti Ahluwalia
Summary: The study aims to identify the strengths and weaknesses in the field of Biomedical Engineering in low- and middle-income settings, and highlights the areas where intervention is necessary for improvement.
HEALTH AND TECHNOLOGY
(2022)
Editorial Material
Public, Environmental & Occupational Health
Madison Moon, Leandro Pecchia, Adriana Velazquez Berumen, April Baller
AMERICAN JOURNAL OF INFECTION CONTROL
(2022)
Article
Health Care Sciences & Services
A. Maccaro, D. Piaggio, S. Leesurakarn, N. Husen, S. Sekalala, S. Rai, L. Pecchia
Summary: This article discusses the applicability of regulatory frameworks for medical devices in low-resource settings, using Benin as a case study. The existing regulatory frameworks drafted by high-income countries are not suitable for low-resource settings. The article proposes a framework to help policymakers consider the particularism of each context, especially in vulnerable countries, promoting an ever-evolving model of universalism.
BMC HEALTH SERVICES RESEARCH
(2022)
Article
Computer Science, Information Systems
Ersilia Vallefuoco, Carmela Bravaccio, Giovanna Gison, Leandro Pecchia, Alessandro Pepino
Summary: This paper presents a 3D personalized serious game developed to help ASD patients practice shopping activities. The game was validated through real-life experiences and demonstrated significant improvements in daily living skills.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Engineering, Biomedical
Emiliano Fernandez-Cervantes, Luis Montesinos, Andres Gonzalez-Nucamendi, Leandro Pecchia
Summary: This study used recurrence quantification analysis (RQA) measures to characterize balance control during quiet standing in young and older adults, and to differentiate between different fall risk groups. The results showed that older adults had less predictable and stable balance control compared to young adults under testing conditions with restricted or altered sensory information. However, there were no significant differences between non-fallers and fallers.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Medical Informatics
Martina Andellini, Salman Haleem, Massimiliano Angelini, Matteo Ritrovato, Riccardo Schiaffini, Ernesto Iadanza, Leandro Pecchia
Summary: This study aims to validate an artificial intelligence-based algorithm for detecting glycaemic events using ECG signals collected through a non-invasive device. T1D paediatric participants who already use CGM will wear an additional non-invasive wearable device to record physiological data and respiratory rate.
HEALTH AND TECHNOLOGY
(2023)
Article
Medical Informatics
Ernesto Iadanza, Giammarco Pasqua, Davide Piaggio, Corrado Caputo, Monica Gherardelli, Leandro Pecchia
Summary: The study aimed to design, prototype, and test a new device that can connect users with common-use or medical-use interfaces to minimize the risk of infection from contact with contaminated surfaces. The device was successfully developed using UML schemes and a risk analysis, and it included a programmed micro-controller linked to a mobile app. This prototype opens up possibilities for further research in pandemic emergency management.
HEALTH AND TECHNOLOGY
(2023)
Review
Imaging Science & Photographic Technology
Francesca Angelone, Alfonso Maria Ponsiglione, Carlo Ricciardi, Giuseppe Cesarelli, Mario Sansone, Francesco Amato
Summary: In addition to their use for obtaining 3D digital dental models, intraoral scanners (IOSs) have recently shown promise as tools for oral health diagnostics. This review examined the literature on the applications of IOSs as detection systems for oral cavity pathologies, highlighting their potential in areas such as tooth wear, caries, plaques, periodontal defects, and other complications. However, there is limited clinical evidence for the use of IOSs as oral health probes, and further validation is needed.
JOURNAL OF IMAGING
(2023)
Review
Computer Science, Information Systems
Alessio Luschi, Camilla Petraccone, Giuseppe Fico, Leandro Pecchia, Ernesto Iadanza
Summary: This study aims to identify and analyze available ontologies that can depict all the available use-cases describing the hospital environment in relation to the European project ODIN. A total of 32 articles were analyzed, resulting in 34 ontologies. The results will lead to the implementation of an integrated ontology that can facilitate data exchange and interconnections among healthcare entities, people, devices, and applications.
Article
Oncology
Mario Sansone, Roberta Fusco, Francesca Grassi, Gianluca Gatta, Maria Paola Belfiore, Francesca Angelone, Carlo Ricciardi, Alfonso Maria Ponsiglione, Francesco Amato, Roberta Galdiero, Roberta Grassi, Vincenza Granata, Roberto Grassi
Summary: The study aims to develop mammographic image processing techniques for the extraction of indicators indicative of breast density (BD) risk factors. The results show that machine learning techniques can classify breasts, with the best classifier being the Support Vector Machine (SVM) with an accuracy of 93.55%, true positive rate of 94.44%, and true negative rate of 92.31%. The SVM with 7 selected features by a wrapper method achieves an accuracy of 0.95, sensitivity of 0.96, and specificity of 0.90 in the external validation cohort. Conclusion: Radiomics analysis and machine learning approach can objectively identify breast density.
Proceedings Paper
Computer Science, Artificial Intelligence
Mario Sansone, Alfonso Maria Ponsiglione, Francesca Angelone, Francesco Amato, Roberto Grassi
Summary: Digital mammography requires high contrast for accurate diagnoses, but scatter phenomenon reduces this contrast. The use of anti-scatter grids in current systems leads to the elimination of primary radiation and increased patient irradiation. Therefore, it is important to develop digital image processing methods for scatter correction. This study aims to evaluate the effectiveness of digital scatter removal and propose a framework for comparing experimental and theoretical breast attenuation coefficient as a measure of scattering effects.
2022 IEEE INTERNATIONAL CONFERENCE ON METROLOGY FOR EXTENDED REALITY, ARTIFICIAL INTELLIGENCE AND NEURAL ENGINEERING (METROXRAINE)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Francesca Angelone, Alfonso Maria Ponsiglione, Carlo Ricciardi, Maria Paola Belfiore, Gianluca Gatta, Francesco Amato, Mario Sansone, Roberto Grassi
Summary: Breast cancer is the most prevalent cancer in females, and breast density is a risk factor affecting screening plans. This study focuses on the development of mammographic image processing techniques to extract indicators of breast density risk from textural patterns. Machine learning techniques are used to classify breasts based on tissue density values. Preliminary results show a high accuracy of the binary classification between dense and no-dense tissues.
2022 IEEE INTERNATIONAL CONFERENCE ON METROLOGY FOR EXTENDED REALITY, ARTIFICIAL INTELLIGENCE AND NEURAL ENGINEERING (METROXRAINE)
(2022)