publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- Climbing the ladder: a ranking approach to burnout predictionAlvise Dei Rossi, Davide Marzorati, Radoslava Švihrová, and 4 more authorsFrontiers in Digital Health, Jan 2026
Validated psychological assessment tools, such as the Shirom–Melamed Burnout Measure (SMBM), are essential for reliably assessing burnout. However, their reliance on active, self-reported input limits their suitability for continuous monitoring and early detection, and introduces the potential for human bias. The SMBM specifically targets the energy depletion component of burnout, with items organized into three subscales: Physical Fatigue (PF), Cognitive Weariness (CW), and Emotional Exhaustion (EE). In the present work, we investigate the feasibility of predicting burnout risk unobtrusively using the preceding trajectory of passive physiological data from wearable devices, supplemented by baseline demographic and occupational information. We evaluate classification, regression, and learning-to-rank formulations for the prediction of SMBM subscale scores on a 9-month real-world dataset of 239 workers, using both aggregate-based and sequential models. Binary classification yields modest performance [ROC AUC: PF (0.66), CW (0.67), EE(0.56)], and regression models offer negligible gains over naïve benchmarks. However, rank-based metrics suggest relative burnout severity can be partially inferred from wearable signals. Motivated by this, we propose a siamese recurrent neural network, explicitly tailored for sequential wearable data and optimized for pairwise risk estimation. Results show improved alignment with the ordinal nature of burnout scores for PF (Spearman’s ρ=0.29, Normalized Discounted Cumulative Gain=0.93) and CW (Spearman’s ρ=0.25, Normalized Discounted Cumulative Gain= 0.89), whereas assessing EE may require additional modalities. Although real-world implementation remains challenging, ranking-based techniques could pave the way for more effective burnout risk monitoring.
- In-the-Wild Data Collection with Digital Apps and Wearable Devices: Insights from a Longitudinal Study on Burnout with Office and Production WorkersDavide Marzorati, Alvise Dei Rossi, Radoslava Śvirová, and 4 more authorsSage DIGITAL HEALTH, 2026
- Inferring daily mobility patterns from Google Maps Timeline: Opportunities and challengesDavide Marzorati, Francesca Cellina, and Tiziano GerosaTravel Behaviour and Society, Jul 2026
Passive location tracking through smartphone-based services offers promising avenues for mobility research, yet its reliability and analytical value remain underexplored. This study presents a comprehensive methodology for extracting commuting patterns from Google Maps Timeline (GMT) data and applies it to a 30-day longitudinal dataset on 294 participants, collected in 2024 in Southern Switzerland. We developed and released an open-source data processing methodology to convert raw GMT activity segments into discrete location bins, enabling the detection of significant places (home and workplace) and commuting trips through unsupervised algorithms. Our findings show that GMT achieves a mean location coverage of 72% across study participants and days with a 200-meter distance threshold between consecutive segments, and allows for the reliable identification of commuting trips in days in which study participants self-reported having worked. While GMT presents limitations in data completeness and algorithm transparency, it offers scalable, low-burden alternatives to traditional mobility data collection methods. Future research should explore its applicability across diverse populations and contexts, and consider open-source alternatives for enhanced transparency and control.
- Unpacking teleworking benefits: Evidence on mobility demand and carbon emissionsTiziano Gerosa, Davide Marzorati, and Francesca CellinaSustainable Cities and Society, Jul 2026
Teleworking is widely promoted to reduce transport emissions and support climate goals, yet its real-world effectiveness remains uncertain. We combine high-resolution GPS tracking, georeferenced data, app-based daily diaries, and mode-specific life-cycle emission inventories to quantify the mobility and carbon impacts of teleworking. In Spring 2024, we monitored 294 employees in Southern Switzerland over 30 consecutive workdays. A within-subject counterfactual design shows that teleworking reduces daily travel distance by 55% and CO2 emissions by 47%, primarily through substitution of car-based commuting. Additional non-commuting trips do not meaningfully offset these benefits, indicating no compensation effect. Reductions are larger for long or car-dependent commutes and smaller in transit-rich areas, highlighting the role of spatial context. Social and institutional time constraints, such as childcare and school schedules, affect teleworking impacts by inducing compensatory mobility behaviors. Seasonal and weather conditions further moderate the effects, with warmer days encouraging some additional non-commuting trips. Substitution dominates, and teleworking delivers substantial carbon savings. Our findings provide actionable insights for hybrid work policies, urban sustainability, and decarbonization strategies.
2025
- Designing digital health interventions with causal inference and multi-armed bandits: a reviewRadoslava Švihrová, Alvise Dei Rossi, Davide Marzorati, and 2 more authorsFrontiers in Digital Health, Jun 2025
Recent statistics from the World Health Organization show that non-communicable diseases account for 74% of global fatalities, with lifestyle playing a pivotal role in their development. Promoting healthier behaviors and targeting modifiable risk factors can significantly improve both life expectancy and quality of life. The widespread adoption of smartphones and wearable devices enables continuous, in-the-wild monitoring of daily habits, opening new opportunities for personalized, data-driven health interventions. This paper provides an overview of the advancements, challenges, and future directions in translating principles of lifestyle medicine and behavior change into AI-powered mobile health (mHealth) applications, with a focus on Just-In-Time Adaptive Interventions. Considerations for the design of adaptive interventions that leverage wearable and contextual data to dynamically personalize behavioral change strategies in real time are discussed. Bayesian multi-armed bandits from reinforcement learning are exploited as a framework for tailoring interventions, with causal inference methods used to incorporate structural assumptions about the user’s behavior. Furthermore, strategies for evaluation at both individual and population levels are presented, with causal inference tools to further guide unbiased estimates. A running example of a simple real-world scenario aimed at increasing physical activity through digital interventions is used throughout the paper. With input from domain experts, the proposed approach is generalizable to a wide range of behavior change use cases.
- Cascade learning in multi-task encoder–decoder networks for concurrent bone segmentation and glenohumeral joint clinical assessment in shoulder CT scansLuca Marsilio, Davide Marzorati, Matteo Rossi, and 4 more authorsArtificial Intelligence in Medicine, Jul 2025
Osteoarthritis is a degenerative condition that affects bones and cartilage, often leading to structural changes, including osteophyte formation, bone density loss, and the narrowing of joint spaces. Over time, this process may disrupt the glenohumeral (GH) joint functionality, requiring a targeted treatment. Various options are available to restore joint functions, ranging from conservative management to surgical interventions, depending on the severity of the condition. This work introduces an innovative deep learning framework to process shoulder CT scans. It features the semantic segmentation of the proximal humerus and scapula, the 3D reconstruction of bone surfaces, the identification of the GH joint region, and the staging of three common osteoarthritic-related conditions: osteophyte formation (OS), GH space reduction (JS), and humeroscapular alignment (HSA). Each condition was stratified into multiple severity stages, offering a comprehensive analysis of shoulder bone structure pathology. The pipeline comprised two cascaded CNN architectures: 3D CEL-UNet for segmentation and 3D Arthro-Net for threefold classification. A retrospective dataset of 571 CT scans featuring patients with various degrees of GH osteoarthritic-related pathologies was used to train, validate, and test the pipeline. Root mean squared error and Hausdorff distance median values for 3D reconstruction were 0.22 mm and 1.48 mm for the humerus and 0.24 mm and 1.48 mm for the scapula, outperforming state-of-the-art architectures and making it potentially suitable for a PSI-based shoulder arthroplasty preoperative plan context. The classification accuracy for OS, JS, and HSA consistently reached around 90% across all three categories. The computational time for the entire inference pipeline was less than 15 s, showcasing the framework’s efficiency and compatibility with orthopedic radiology practice. The achieved reconstruction and classification accuracy, combined with the rapid processing time, represent a promising advancement towards the medical translation of artificial intelligence tools. This progress aims to streamline the preoperative planning pipeline, delivering high-quality bone surfaces and supporting surgeons in selecting the most suitable surgical approach according to the unique patient joint conditions.
- Unobtrusive Perceived Sleep Quality Monitoring in the WildAlvise Dei Rossi, Davide Marzorati, Tiziano Gerosa, and 3 more authorsProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Sep 2025
Perceived sleep quality is a key aspect of sleep health and a crucial factor in mental health. However, predicting it accurately is difficult because of its deeply personal nature and the considerable variability in how individuals perceive their sleep at night. This study presents a robust subject-wise nested cross-validation framework for passive daily monitoring of perceived sleep quality using wearable data through population-level machine learning modeling. A total of 294 participants (mean age 42 (SD = 10) years; 43% female) were monitored over 30 days employing commercial wearable devices in free-living conditions, with daily self-reported sleep quality. A novel adaptation of the person-mean centering approach was employed to split time-varying features into within-person and between-person components, preventing temporal leakage and enabling unbiased daily prediction. Various machine learning models were trained, and SHAP values were used to identify key predictors. Our results show that fully passive prediction of perceived sleep quality is feasible at population-level from the first day of monitoring (ROC AUC 0.715, F1 0.494, BA 0.666), with within-person deviations from individual baselines being the primary predictors. The most influential predictors were found to be deviations in sleep duration and continuity, followed by cardiac, stress-related features, and SF-12 health survey components.
- Toward burnout prevention with Bayesian mixed-effects regression analysis of longitudinal data from wearables: a preliminary study.Radoslava Švihrová, Davide Marzorati, Michal Bechný, and 5 more authorsFrontiers in Digital Health, 2025
Wearable devices have gained significant popularity in recent years, as they provide valuable insights into behavioral patterns and enable unobtrusive continuous monitoring. This work explores how daily lifestyle choices and physiological factors contribute to coping capacities and aims at designing burnout prevention systems. Key variables examined include sleep stage proportions and nocturnal stress levels, as both play a crucial role in recovery and resilience. Longitudinal data from a 1-week study incorporating wearable-derived features and contextual information are analyzed using a mixed-effects model, accounting for both overall trends and individual differences. A Bayesian inference approach is exploited to quantify uncertainty in estimated effects, providing their probabilistic interpretation and ensuring robustness despite the low sample size. Findings indicate that alcohol consumption negatively affects rapid-eye-movement sleep, increases awake time, and elevates nocturnal stress. Excessive daily stress reduces deep sleep, while an increase in daily active hours promote it. These results align with the existing literature, demonstrating the potential of consumer-grade wearables to monitor clinically relevant relationships and guide interventions for stress reduction and burnout prevention.
- Data-Driven Causal Discovery: Insights from a Longitudinal Study with Wearable DataRadoslava Švihrová, Davide Marzorati, Alvise Dei Rossi, and 2 more authors2025
Wearable devices offer unprecedented opportunities for continuous health monitoring and data collection in the general or clinical populations. In this study, we explore the feasibility of using data from consumer-grade wearable devices, combined with daily questionnaires, for long-term telemonitoring. To validate the plausibility of collected data at the level of relationships among derived variables, the causal structure is estimated in a data-driven way, and evaluated against existing literature to ensure alignment with established findings. Identification of the causal relationships is done with Structural Expectation-Maximization (SEM) algorithm, to address the challenge of missing data, and further strengthened by providing an initial structure estimated by the bootstrapped Temporal Peter-Clark (TPC) algorithm. Obtained results demonstrate plausibility of the discovered relationships, evaluated both against existing literature and in a data-driven way by fitting a Bayesian network. This supports the utility of consumer-grade wearables for continuous monitoring, and enabling new directions for designing of targeted interventions.
- Estimating Weather Effects on Well-Being and Mobility with Multi-Source Longitudinal DataDavide Marzorati, Francesca Dalia Faraci, and Tiziano GerosaInformation, Oct 2025
Understanding the influence of weather on human well-being and mobility is essential to promoting healthier lifestyles. In this study we employ data collected from 151 participants over a continuous 30-day period in Switzerland to examine the effects of weather on well-being and mobility. Physiological data were retrieved through wearable devices, while mobility was automatically tracked through Google Location History, enabling detailed analysis of participants’ mobility behaviors. Mixed effects linear models were used to estimate the effects of temperature, precipitation, and sunshine duration on well-being and mobility while controlling for potential socio-demographic confounders. In this work, we demonstrate the feasibility of combining multi-source physiological and location data for environmental health research. Our results show small but significant effects of weather on several well-being outcomes (activity, sleep, and stress), while mobility was mostly affected by the level of precipitation. In line with previous research, our findings confirm that normal weather fluctuations exert significant but moderate effects on health-related behavior, highlighting the need to shift research focus toward extreme weather variations that lie beyond typical seasonal ranges. Given the potentially severe consequences of such extremes for public health and health-care systems, this shift will help identify more consistent effects, thereby informing targeted interventions and policy planning.
- Low sparsity, high granularity: Making the most of smartphones and smartwatches for mobility and well-being policy-makingTiziano Gerosa, Davide Marzorati, Mirko Galati Rando, and 3 more authorsTransportation Research Interdisciplinary Perspectives, Nov 2025
- Burnout Risk Prediction through Wearable Devices: An Initial Assessment.Davide Marzorati, Alvise Dei Rossi, Radoslava Svihrova, and 2 more authorsAnnual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, Jul 2025
Early detection of burnout is of utmost importance to avoid severe health consequences. Burnout is typically assessed through standardized questionnaires with self-reported information, a technique that could potentially delay its diagnosis. Wearable devices continuously and unobtrusively collect health-related data, making them valuable tools for the early detection of several mental health issues, including burnout syndrome. In this paper we report initial insights on the machine learning prediction of baseline burnout risk across cognitive, emotional, and physical dimensions. Our data consists of the first 30 days of a 9-months longitudinal study with 239 participants, including monthly burnout assessments and health data from smartwatches. Aggregated mean and standard deviation of physiological features over time windows of varying duration were employed as predictors of baseline burnout risk. Models employing sleep, cardiac, and stress features achieved a balanced accuracy of 0.66 and 0.68 in the detection of cognitive weariness and physical fatigue risk, respectively. The prediction of emotional exhaustion risk reached lower performance with a balanced accuracy of 0.55, suggesting the need of integrating additional data sources to reach better-than-chance performance. We expect to improve burnout risk prediction by crafting additional features and exploiting the collected data over their full longitudinal scale.
- An App-Based Intervention to Protect Home Care Workers From Heat-Related Health Risks: Protocol for a Randomized Controlled Trial.Tiziano Gerosa, Remo Fortunato, Francesca Cellina, and 6 more authorsInquiry : a journal of medical care organization, provision and financing, 2025
Climate change is intensifying the frequency and severity of heatwaves, posing growing risks for workers. Home care workers face heightened heat risks due to physically demanding tasks, rising patient needs, frequent travel, and limited access to cooling environments. This study aims to causally evaluate the effectiveness of an app-based intervention (REHEAT strategy) in reducing adverse effects of heatwaves among Swiss home care workers. This multicenter, unblinded, randomized controlled trial (RCT) will involve 350 home care workers from the regions of Northern and Southern Switzerland. Participants will be randomized (1:1) into intervention and control groups, stratified by sex, age group, and geographical location. The intervention group will use the REHEAT app from June to September 2025, while the control group will gain access only after summer 2025. Both groups will be monitored over the summer using a wrist-worn wearable device (smartwatch), online questionnaires, diaries and cognitive tests. The impact of the REHEAT intervention will be evaluated using an Intention-To-Treat (ITT) approach to provide reliable real-world effect estimates, supplemented by Local Average Treatment Effects (LATE) analyses to assess impact based on participant exposure and compliance levels. Primary outcomes include strain accumulation, cognitive performance, emotional distress, sleep, night recovery, and mental and physical health. Outcomes will be analyzed longitudinally with mixed-effects models, while LATE will be estimated using app usage as an instrumental variable in generalized linear mixed models. At the time of submission, recruitment had been successfully completed, with a total of 350 participants enrolled in accordance with the study protocol. The intervention and data collection phases are ongoing, and no outcome data have yet been accessed or analyzed. The findings will inform the development of occupational health interventions in response to heat-related stressors and support climate change adaptation policies for health sector workers.
2024
- Modeling Perceived Sleep Quality Through Objective and Subjective DataAlvise Dei Rossi, Davide Marzorati, Radoslava Švihrová, and 3 more authorsIn 2024 12th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), Sep 2024
2023
- Temperature Modulation of MOS Sensors for Enhanced Detection of Volatile Organic CompoundsAndrea Rescalli, Davide Marzorati, Simone Gelosa, and 2 more authorsChemosensors, Sep 2023
Disease diagnosis through biological fluids, particularly exhaled breath analysis, has gained increasing importance. Volatile organic compounds (VOCs) present in exhaled breath offer diagnostic potential as they reflect altered and disease-specific metabolic pathways. While gas chromatography-mass spectrometry (GC-MS) has been traditionally used for VOCs detection, electronic noses have emerged as a promising alternative for disease screening. Metal oxide semiconductor (MOS) sensors play an essential role in these devices due to their simplicity and cost-effectiveness. However, their limited specificity and sensitivity pose challenges for accurate diagnosis at lower VOCs concentrations, typical of exhaled breath. To address specificity and sensitivity issues, temperature modulation (TM) has been proposed in this paper, introducing a custom-developed electronic nose based on multiple and heterogeneous gas sensors located within an analysis chamber. Four different TM patterns (i.e., square, sine, triangular, and a combination of square and triangular) were applied to the gas sensors to test their response to three different analytes at three distinct concentrations. Data were analyzed by extracting meaningful features from the sensor raw data, and dimensionality reduction using principal component analysis (PCA) was performed. The results demonstrated distinct clusters for each experimental condition, indicating successful discrimination of analytes and concentrations. In addition, an analysis of which set of sensors and modulation pattern yielded the best results was performed. In particular, the most promising TM pattern proved to be the square and triangular combination, with optimal discrimination accuracy between both concentrations and analytes. One specific sensor, namely, TGS2600 from Figaro USA, Inc., provided the best performance. While preliminary results highlighted the potential of TM to improve the sensitivity of gas sensors in electronic nose devices, paving the way for further advancements in the field of exhaled breath analysis.
- Merging Contour-and Region-Aware Branches in the UNet Decoder to Enhance Osseous Segmentation in Shoulder CT ScansLuca Marsilio, Matteo Rossi, Alfonso Manzotti, and 2 more authorsIn 2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), Oct 2023
2022
- Hybrid Convolutional Networks for End-to-End Event Detection in Concurrent PPG and PCG Signals Affected by Motion ArtifactsDavide Marzorati, Andrea Dorizza, Dario Bovio, and 3 more authorsIEEE Transactions on Biomedical Engineering, Aug 2022
The accurate detection of physiologically-related events in photopletismographic (PPG) and phonocardiographic (PCG) signals, recorded by wearable sensors, is mandatory to perform the estimation of relevant cardiovascular parameters like the heart rate and the blood pressure. However, the measurement performed in uncontrolled conditions without clinical supervision leaves the detection quality particularly susceptible to noise and motion artifacts. This work proposes a new fully-automatic computational framework, based on convolutional networks, to identify and localize fiducial points in time as the foot, maximum slope and peak in PPG signal and the S1 sound in the PCG signal, both acquired by a custom chest sensor, described recently in the literature by our group. The event detection problem was reframed as a single hybrid regression-classification problem entailing a custom neural architecture to process sequentially the PPG and PCG signals. Tests were performed analysing four different acquisition conditions (rest, cycling, rest recovery and walking). Cross-validation results for the three PPG fiducial points showed identification accuracy greater than 93 % and localization error (RMSE) less than 10 ms. As expected, cycling and walking conditions provided worse results than rest and recovery, however reaching an accuracy greater than 90 % and a localization error less than 15 ms. Likewise, the identification and localization error for S1 sound were greater than 90 % and less than 25 ms. Overall, this study showcased the ability of the proposed technique to detect events with high accuracy not only for steady acquisitions but also during subject movements. We also showed that the proposed network outperformed traditional Shannon-energy-envelope method in the detection of S1 sound, reaching detection performance comparable to state of the art algorithms. Therefore, we argue that coupling chest sensors and deep learning processing techniques may disclose wearable devices to unobtrusively acquire health information, being less affected by noise and motion artifacts.
2021
- MOS Sensors Array for the Discrimination of Lung Cancer and At-Risk Subjects with Exhaled Breath AnalysisDavide Marzorati, Luca Mainardi, Giulia Sedda, and 3 more authorsChemosensors, Aug 2021
Lung cancer is characterized by a tremendously high mortality rate and a low 5-year survival rate when diagnosed at a late stage. Early diagnosis of lung cancer drastically reduces its mortality rate and improves survival. Exhaled breath analysis could offer a tool to clinicians to improve the ability to detect lung cancer at an early stage, thus leading to a reduction in the associated survival rate. In this paper, we present an electronic nose for the automatic analysis of exhaled breath. A total of five a-specific gas sensors were embedded in the electronic nose, making it sensitive to different volatile organic compounds (VOCs) contained in exhaled breath. Nine features were extracted from each gas sensor response to exhaled breath, identifying the subject breathprint. We tested the electronic nose on a cohort of 80 subjects, equally split between lung cancer and at-risk control subjects. Including gas sensor features and clinical features in a classification model, recall, precision, and accuracy of 78%, 80%, and 77% were reached using a fourfold cross-validation approach. The addition of other a-specific gas sensors, or of sensors specific to certain compounds, could improve the classification accuracy, therefore allowing for the development of a clinical tool to be integrated in the clinical pipeline for exhaled breath analysis and lung cancer early diagnosis.
2020
- Chest Wearable Apparatus for Cuffless Continuous Blood Pressure Measurements Based on PPG and PCG SignalsDavide Marzorati, Dario Bovio, Caterina Salito, and 2 more authorsIEEE Access, 2020
This paper describes an integrated chest wearable apparatus for continuous blood pressure (BP) measurements exploiting the heart-rate (HR) and the pulse arrival time (PAT) in a modified Moens-Korteweg model. The device embeds a miniaturized gas pressure sensor to record the phonocardiogram (PCG) of the heart sounds, a LED-photodiode pair to detect the photoplethysmogram (PPG) of the blood flow wave, a \mucontroller, a wireless communication module and the power supply. With the proposed device no active participation would be required from human subjects for BP measurements, since the HR and the PAT are continuously extracted from the PCG and PPG signals. Dedicated signal processing algorithms were developed and implemented off-line to extract both HR and PAT. A subject-specific calibration protocol of the BP model was designed and implemented. The calibration and validation of the apparatus were performed on a cohort of 20 healthy subjects. A GIMA ABPM pressure Holter was chosen as reference device, and 8 measurements points, evenly distributed over a 10-minute interval, were used for model calibration for each subject. The range of DBP and SBP measurements were 52-85 mmHg and 90-141 mmHg, respectively. The results from Bl- and-Altman analysis showed that the mean\pm1.96SD for the estimated diastolic, systolic, and mean BP with the proposed method against reference were 0.01\pm7.55, 1.47\pm3.76, 0.74\pm4.38 mmHg, respectively. The corresponding mean absolute differences (MAD) were 3.06, 1.83, and 1.80 mmHg. These results demonstrates that the acquisition apparatus is able to continuously estimate the BP with an accuracy comparable to traditional cuff-based devices.
- Deep 3D Convolutional Networks to Segment Bones Affected by Severe Osteoarthritis in CT Scans for PSI-Based Knee Surgical PlanningDavide Marzorati, Mattia Sarti, Luca Mainardi, and 2 more authorsIEEE Access, 2020
Segmentation of bony structures in CT scans is a crucial step in knee arthroplasty based on personalized surgical instruments (PSI). As a matter of fact, the success of the surgery depends on the quality of the matching between the patient-specific resection jigs, manufactured exploiting the patient bony surfaces attained by segmentation, and true patient surfaces. Severe pathological conditions as chronic osteoarthritis, deteriorating the cartilages, narrowing the intra-articular spaces and leading to bone impingement, complicate the segmentation making the recognition of bony boundaries sub-optimal for traditional semi-automated methods and often extremely difficult even for expert radiologists. Deep convolutional neural networks (CNNs) have been investigated in the last years towards automatic labeling of diagnostic images, especially harnessing the encoding-decoding U-Net architecture. In this article, we implemented deep CNNs to encompass the concurrent segmentation of the distal femur and the proximal tibia in CT images and evaluate how segmentation uncertainty may impact on the surgical planning. A retrospective set of 200 knee CT scans of patients was used to train the network and test the segmentation performances. Tests on a subset of 20 scans provided median dice, sensitivity and positive predictive value indices greater than 96% for both shapes, with median 3D reconstruction error in the range of 0.5mm. Median 3D errors on both PSI femoral and tibial contact areas and surgical cut alignments were less than 2mm and 2^∘, respectively, which can be considered clinically acceptable. These results substantiate that deep CNN architectures can disclose the opportunity of segmenting bone shapes in CT scans for PSI-based surgical planning with promising accuracy. However, we observed that segmentation scores alone cannot be taken as representative of the 3D errors at the contact areas of the PSI. Therefore when comparing segmentation algorithms of PSI-based surgical planning the 3D errors should be explicitly analyzed.
2019
- A review of exhaled breath: a key role in lung cancer diagnosisDavide Marzorati, Luca Mainardi, Giulia Sedda, and 3 more authorsJournal of Breath Research, Apr 2019
One of the main causes of the high mortality rate in lung cancer is the late-stage tumor detection. Early diagnosis is therefore essential to increase the chances of obtaining an effective treatment quickly thus increasing the survival rate. Current screening techniques are based on imaging, with low-dose computed tomography (LDCT) as the pivotal approach. Even if LDCT has high accuracy, its invasiveness and high false positive rate limit its application to high-risk population screening. A non-invasive, cost-efficient, and easy-to-use test should instead be designed as an alternative. Exhaled breath contains thousands of volatile organic compounds (VOCs). Since ancient times, it has been understood that changes in the VOCs’ mixture may be directly related to the presence of a disease, and recent studies have quantified the change in the compounds’ concentration. Analyzing exhaled breath to achieve lung cancer early diagnosis represents a non-invasive, low-cost, and user-friendly approach, thus being a promising candidate for high-risk lung cancer population screening. This review discusses technological solutions that have been proposed in the literature as tools to analyze exhaled breath for lung cancer diagnosis, together with factors that potentially affect the outcome of the analysis. Even if research on this topic started many years ago, and many different technological approaches have since been adopted, there is still no validated clinical application of this technique. Standard guidelines and protocols should be defined by the medical community in order to translate exhaled breath analysis to clinical practice.
- A Metal Oxide Gas Sensors Array for Lung Cancer Diagnosis Through Exhaled Breath AnalysisDavide Marzorati, Luca Mainardi, Giulia Sedda, and 3 more authorsIn 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 2019
Lung cancer high mortality rate is mainly related to late-stage tumor diagnosis. Survival rates and treatments could be greatly improved with an effective early diagnosis. Volatile organic compounds (VOCs) in exhaled breath have been known for long to be linked to the presence of a disease. Exhaled breath analysis for early diagnosis of lung cancer represents a non-invasive, low-cost and user-friendly approach. In this paper we present the design and development of an electronic nose based on a metal oxide sensors array for the early diagnosis of lung cancer. Breath samples collected from healthy controls (n=10) and lung cancer subjects (n=6) were analyzed by the electronic nose, and classification was performed using an artificial neural network (ANN). A sensitivity of 85.7%, specificity of 100%, and accuracy of 93.8% were reached with leave one out cross validation (LOOCV). The presented device demonstrates that a simple, cost-effective, and non-invasive approach based on exhaled breath analysis has the potential to be of great help in decreasing lung cancer mortality.