RESUMO
OBJECTIVE: Loss of resistance (LOR) is a widely accepted method for performing epidural punctures in clinical settings. However, the risk of failure associated with LOR is still high. Solutions based either on Fiber Bragg grating sensors (FBG) or on artificial intelligence (AI) are gaining ground for supporting clinicians during this kind of procedure. Here, for the first time, we combined the mentioned two technologies to perform an AI-driven LOR identification based on data collected by a custom FBG sensor. METHODS: This study presented two contributions (i.e., automatic labeling and identification) based on machine learning to support epidural procedures by enhancing LOR detection. The methods were tested using data collected by a customized FBG-based flexible cap on 10 patients affected by chronic back pain. RESULTS: The automatic labeling can retrospectively identify every LOR event for each subject under consideration. This serves as the labeling for the automatic identification task, which emulates the real-time application of LOR detection. A Support Vector Machine, trained using a LeaveOne-Out strategy, demonstrates high accuracy in identifying all LOR events while maintaining a minimal rate of false positives. CONCLUSION: Our findings revealed the promising performance of the proposed AI-based approach for automatic LOR detection. Thus, their combination with FBG technology can potentially improve the level of support offered to clinicians in this application. SIGNIFICANCE: The integration of AI and FBG technologies holds the promise of revolutionizing LOR detection, reducing the likelihood of unsuccessful epidural punctures and advancing pain management.
RESUMO
INTRODUCTION: Electronic nose (E-nose) technology has reported excellent sensitivity and specificity in the setting of lung cancer screening. However, the performance of E-nose specifically for early-stage tumors remains unclear. Therefore, the aim of our study was to assess the diagnostic performance of E-nose technology in clinical stage I lung cancer. METHODS: This phase IIc trial (NCT04734145) included patients diagnosed with a single greater than or equal to 50% solid stage I nodule. Exhalates were prospectively collected from January 2020 to August 2023. Blinded bioengineers analyzed the exhalates, using E-nose technology to determine the probability of malignancy. Patients were stratified into three risk groups (low-risk, [<0.2]; moderate-risk, [≥0.2-0.7]; high-risk, [≥0.7]). The primary outcome was the diagnostic performance of E-nose versus histopathology (accuracy and F1 score). The secondary outcome was the clinical performance of the E-nose versus clinicoradiological prediction models. RESULTS: Based on the predefined cutoff (<0.20), E-nose agreed with histopathologic results in 86% of cases, achieving an F1 score of 92.5%, based on 86 true positives, two false negatives, and 12 false positives (n = 100). E-nose would refer fewer patients with malignant nodules to observation (low-risk: 2 versus 9 and 11, respectively; p = 0.028 and p = 0.011) than would the Swensen and Brock models and more patients with malignant nodules to treatment without biopsy (high-risk: 27 versus 19 and 6, respectively; p = 0.057 and p < 0.001). CONCLUSIONS: In the setting of clinical stage I lung cancer, E-nose agrees well with histopathology. Accordingly, E-nose technology can be used in addition to imaging or as part of a "multiomics" platform.
RESUMO
The aim of the present study consists of the evaluation of the biodistribution of a novel 68Ga-labeled radiopharmaceutical, [68Ga]Ga-NODAGA-Z360, injected into Balb/c nude mice through histopathological analysis on bioptic samples and radiomics analysis of positron emission tomography/computed tomography (PET/CT) images. The 68Ga-labeled radiopharmaceutical was designed to specifically bind to the cholecystokinin receptor (CCK2R). This receptor, naturally present in healthy tissues such as the stomach, is a biomarker for numerous tumors when overexpressed. In this experiment, Balb/c nude mice were xenografted with a human epidermoid carcinoma A431 cell line (A431 WT) and overexpressing CCK2R (A431 CCK2R+), while controls received a wild-type cell line. PET images were processed, segmented after atlas-based co-registration and, consequently, 112 radiomics features were extracted for each investigated organ / tissue. To confirm the histopathology at the tissue level and correlate it with the degree of PET uptake, the studies were supported by digital pathology. As a result of the analyses, the differences in radiomics features in different body districts confirmed the correct targeting of the radiopharmaceutical. In preclinical imaging, the methodology confirms the importance of a decision-support system based on artificial intelligence algorithms for the assessment of radiopharmaceutical biodistribution.
RESUMO
The availability of a wearable artificial liver that facilitates extracorporeal dialysis outside of medical facilities would represent a significant advancement for patients requiring dialysis. The objective of this preliminary investigation is to explore, using validated mathematical models based on in vitro data, the feasibility of developing a novel, cost-effective, and highly compact extracorporeal liver support device that can be employed as a transitional therapy to transplantation outside of clinical settings. Such an innovation would offer substantial cost savings to the national healthcare system while significantly improving the patient's quality of life. The experimental components consisted of replacing traditional adsorbent materials with albumin-functionalized silica microspheres due to their capacity to adsorb bilirubin, one of the toxins responsible for liver failure. Two configurations of the dialysis module were tested: one involved dispersing the adsorbent particles in dialysis fluid, while the other did not require dialysis fluid. The results demonstrate the superior performance of the first configuration compared to the second. Although the clinical applicability of these models remains distant from the current stage, further studies will focus on optimizing these models to develop a more compact and wearable device.
RESUMO
Brainstem dysfunctions are very common in Multiple Sclerosis (MS) and are a critical predictive factor for future disability. Brainstem functionality can be explored with blink reflexes, subcortical responses consisting in a blink following a peripheral stimulation. Some reflexes are already employed in clinical practice, such as Trigeminal Blink Reflex (TBR). Here we propose for the first time in MS the exploration of Hand Blink Reflex (HBR), which size is modulated by the proximity of the stimulated hand to the face, reflecting the extension of the peripersonal space. The aim of this work is to test whether Machine Learning (ML) techniques could be used in combination with neurophysiological measurements such as TBR and HBR to improve their clinical information and potentially favour the early detection of brainstem dysfunctionality. HBR and TBR were recorded from a group of People with MS (PwMS) with Relapsing-Remitting form and from a healthy control group. Two AdaBoost classifiers were trained with TBR and HBR features each, for a binary classification task between PwMS and Controls. Both classifiers were able to identify PwMS with an accuracy comparable and even higher than clinicians. Our results indicate that ML techniques could represent a tool for clinicians for investigating brainstem functionality in MS. Also, HBR could be promising when applied in clinical practice, providing additional information about the integrity of brainstem circuits potentially favouring early diagnosis.
Assuntos
Piscadela , Esclerose Múltipla , Humanos , Neurofisiologia , Aprendizado de MáquinaRESUMO
The exponential increase in internet data poses several challenges to cloud systems and data centers, such as scalability, power overheads, network load, and data security. To overcome these limitations, research is focusing on the development of edge computing systems, i.e., based on a distributed computing model in which data processing occurs as close as possible to where the data are collected. Edge computing, indeed, mitigates the limitations of cloud computing, implementing artificial intelligence algorithms directly on the embedded devices enabling low latency responses without network overhead or high costs, and improving solution scalability. Today, the hardware improvements of the edge devices make them capable of performing, even if with some constraints, complex computations, such as those required by Deep Neural Networks. Nevertheless, to efficiently implement deep learning algorithms on devices with limited computing power, it is necessary to minimize the production time and to quickly identify, deploy, and, if necessary, optimize the best Neural Network solution. This study focuses on developing a universal method to identify and port the best Neural Network on an edge system, valid regardless of the device, Neural Network, and task typology. The method is based on three steps: a trade-off step to obtain the best Neural Network within different solutions under investigation; an optimization step to find the best configurations of parameters under different acceleration techniques; eventually, an explainability step using local interpretable model-agnostic explanations (LIME), which provides a global approach to quantify the goodness of the classifier decision criteria. We evaluated several MobileNets on the Fudan Shangai-Tech dataset to test the proposed approach.
Assuntos
Inteligência Artificial , Redes Neurais de Computação , Computação em Nuvem , Algoritmos , ComputadoresRESUMO
Alzheimer's disease (AD) diagnosis often requires invasive examinations (e.g., liquor analyses), expensive tools (e.g., brain imaging) and highly specialized personnel. The diagnosis commonly is established when the disorder has already caused severe brain damage, and the clinical signs begin to be apparent. Instead, accessible and low-cost approaches for early identification of subjects at high risk for developing AD years before they show overt symptoms are fundamental to provide a critical time window for more effective clinical management, treatment, and care planning. This article proposes an ensemble-based machine learning algorithm for predicting AD development within 9 years from first overt signs and using just five clinical features that are easily detectable with neuropsychological tests. The validation of the system involved both healthy individuals and mild cognitive impairment (MCI) patients drawn from the ADNI open dataset, at variance with previous studies that considered only MCI. The system shows higher levels of balanced accuracy, negative predictive value, and specificity than other similar solutions. These results represent a further important step to build a preventive fast-screening machine-learning-based tool to be used as a part of routine healthcare screenings.
RESUMO
Natural Language Processing (NLP) is a discipline at the intersection between Computer Science (CS), Artificial Intelligence (AI), and Linguistics that leverages unstructured human-interpretable (natural) language text. In recent years, it gained momentum also in health-related applications and research. Although preliminary, studies concerning Low Back Pain (LBP) and other related spine disorders with relevant applications of NLP methodologies have been reported in the literature over the last few years. It motivated us to systematically review the literature comprised of two major public databases, PubMed and Scopus. To do so, we first formulated our research question following the PICO guidelines. Then, we followed a PRISMA-like protocol by performing a search query including terminologies of both technical (e.g., natural language and computational linguistics) and clinical (e.g., lumbar and spine surgery) domains. We collected 221 non-duplicated studies, 16 of which were eligible for our analysis. In this work, we present these studies divided into sub-categories, from both tasks and exploited models' points of view. Furthermore, we report a detailed description of techniques used to extract and process textual features and the several evaluation metrics used to assess the performance of the NLP models. However, what is clear from our analysis is that additional studies on larger datasets are needed to better define the role of NLP in the care of patients with spinal disorders.
RESUMO
BACKGROUND: Type 1 Diabetes Mellitus (T1D) is an autoimmune disease that can cause serious complications that can be avoided by preventing the glycemic levels from exceeding the physiological range. Straightforwardly, many data-driven models were developed to forecast future glycemic levels and to allow patients to avoid adverse events. Most models are tuned on data of adult patients, whereas the prediction of glycemic levels of pediatric patients has been rarely investigated, as they represent the most challenging T1D population. METHODS: A Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) Recurrent Neural Network were optimized on glucose, insulin, and meal data of 10 virtual pediatric patients. The trained models were then implemented on two edge-computing boards to evaluate the feasibility of an edge system for glucose forecasting in terms of prediction accuracy and inference time. RESULTS: The LSTM model achieved the best numeric and clinical accuracy when tested in the .tflite format, whereas the CNN achieved the best clinical accuracy in uint8. The inference time for each prediction was far under the limit represented by the sampling period. CONCLUSION: Both models effectively predict glucose in pediatric patients in terms of numerical and clinical accuracy. The edge implementation did not show a significant performance decrease, and the inference time was largely adequate for a real-time application.
RESUMO
Low Back Pain (LBP) is currently the first cause of disability in the world, with a significant socioeconomic burden. Diagnosis and treatment of LBP often involve a multidisciplinary, individualized approach consisting of several outcome measures and imaging data along with emerging technologies. The increased amount of data generated in this process has led to the development of methods related to artificial intelligence (AI), and to computer-aided diagnosis (CAD) in particular, which aim to assist and improve the diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of CAD in the diagnosis and treatment of chronic LBP. A systematic research of PubMed, Scopus, and Web of Science electronic databases was performed. The search strategy was set as the combinations of the following keywords: "Artificial Intelligence", "Machine Learning", "Deep Learning", "Neural Network", "Computer Aided Diagnosis", "Low Back Pain", "Lumbar", "Intervertebral Disc Degeneration", "Spine Surgery", etc. The search returned a total of 1536 articles. After duplication removal and evaluation of the abstracts, 1386 were excluded, whereas 93 papers were excluded after full-text examination, taking the number of eligible articles to 57. The main applications of CAD in LBP included classification and regression. Classification is used to identify or categorize a disease, whereas regression is used to produce a numerical output as a quantitative evaluation of some measure. The best performing systems were developed to diagnose degenerative changes of the spine from imaging data, with average accuracy rates >80%. However, notable outcomes were also reported for CAD tools executing different tasks including analysis of clinical, biomechanical, electrophysiological, and functional imaging data. Further studies are needed to better define the role of CAD in LBP care.
Assuntos
Degeneração do Disco Intervertebral , Dor Lombar , Inteligência Artificial , Computadores , Diagnóstico por Computador , Humanos , Dor Lombar/diagnóstico por imagem , Dor Lombar/terapiaRESUMO
Ovarian cancer is one of the most common gynecological malignancies, ranking third after cervical and uterine cancer. High-grade serous ovarian cancer (HGSOC) is one of the most aggressive subtype, and the late onset of its symptoms leads in most cases to an unfavourable prognosis. Current predictive algorithms used to estimate the risk of having Ovarian Cancer fail to provide sufficient sensitivity and specificity to be used widely in clinical practice. The use of additional biomarkers or parameters such as age or menopausal status to overcome these issues showed only weak improvements. It is necessary to identify novel molecular signatures and the development of new predictive algorithms able to support the diagnosis of HGSOC, and at the same time, deepen the understanding of this elusive disease, with the final goal of improving patient survival. Here, we apply a Machine Learning-based pipeline to an open-source HGSOC Proteomic dataset to develop a decision support system (DSS) that displayed high discerning ability on a dataset of HGSOC biopsies. The proposed DSS consists of a double-step feature selection and a decision tree, with the resulting output consisting of a combination of three highly discriminating proteins: TOP1, PDIA4, and OGN, that could be of interest for further clinical and experimental validation. Furthermore, we took advantage of the ranked list of proteins generated during the feature selection steps to perform a pathway analysis to provide a snapshot of the main deregulated pathways of HGSOC. The datasets used for this study are available in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) data portal ( https://cptac-data-portal.georgetown.edu/ ).
Assuntos
Cistadenocarcinoma Seroso/diagnóstico , Cistadenocarcinoma Seroso/metabolismo , Aprendizado de Máquina , Neoplasias Ovarianas/diagnóstico , Neoplasias Ovarianas/metabolismo , Proteômica/métodos , Biomarcadores Tumorais/metabolismo , Correlação de Dados , Cistadenocarcinoma Seroso/classificação , Bases de Dados Factuais , Árvores de Decisões , Feminino , Humanos , Neoplasias Ovarianas/classificação , Fenótipo , PrognósticoRESUMO
Chronic Low Back Pain (LBP) is a symptom that may be caused by several diseases, and it is currently the leading cause of disability worldwide. The increased amount of digital images in orthopaedics has led to the development of methods related to artificial intelligence, and to computer vision in particular, which aim to improve diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of computer vision in the diagnosis and treatment of LBP. A systematic research of PubMed electronic database was performed. The search strategy was set as the combinations of the following keywords: "Artificial Intelligence", "Feature Extraction", "Segmentation", "Computer Vision", "Machine Learning", "Deep Learning", "Neural Network", "Low Back Pain", "Lumbar". Results: The search returned a total of 558 articles. After careful evaluation of the abstracts, 358 were excluded, whereas 124 papers were excluded after full-text examination, taking the number of eligible articles to 76. The main applications of computer vision in LBP include feature extraction and segmentation, which are usually followed by further tasks. Most recent methods use deep learning models rather than digital image processing techniques. The best performing methods for segmentation of vertebrae, intervertebral discs, spinal canal and lumbar muscles achieve Sørensen-Dice scores greater than 90%, whereas studies focusing on localization and identification of structures collectively showed an accuracy greater than 80%. Future advances in artificial intelligence are expected to increase systems' autonomy and reliability, thus providing even more effective tools for the diagnosis and treatment of LBP.
Assuntos
Disco Intervertebral , Dor Lombar , Inteligência Artificial , Computadores , Humanos , Dor Lombar/diagnóstico , Reprodutibilidade dos TestesRESUMO
BACKGROUND: Type 1 Diabetes Mellitus (T1DM) is a widespread chronic disease in industrialized countries. Preventing blood glucose levels from exceeding the euglycaemic range would reduce the incidence of diabetes-related complications and improve the quality of life of subjects with T1DM. As a consequence, in the last decade, many Machine Learning algorithms aiming to forecast future blood glucose levels have been proposed. Despite the excellent performance they obtained, the prediction of abrupt changes in blood glucose values produced during physical activity (PA) is still one of the main challenges. METHODS: A Jump Neural Network was developed in order to overcome the issue of predicting blood glucose values during PA. Three learning configurations were developed and tested: offline training, online training, and online training with reinforcement. All configurations were tested on six subjects suffering from T1DM that held regular PA (three aerobic and three anaerobic) and exploited Continuous Glucose Monitoring (CGM). RESULTS: The forecasting performance was evaluated in terms of the Root-Mean-Squared-Error (RMSE), according to a paradigm of Precision Medicine. CONCLUSIONS: The online learning configurations performed better than the offline configuration in total days but not on the only CGM associated with the PA; thus, the results do not justify the increased computational burden because the improvement was not significant.
RESUMO
BackgroundThe totality of bacteria, protozoa, viruses and fungi that lives in the human body is called microbiota. Human microbiota specifically colonizes the skin, the respiratory and urinary tract, the urogenital tract and the gastrointestinal system. This study focuses on the intestinal microbiota to explore the drug-microbiota relationship and, therefore, how the drug bioavailability changes in relation to the microbiota biodiversity to identify more personalized therapies, with the minimum risk of side effects. MethodsTo achieve this goal, we developed a new mathematical model with two compartments, the intestine and the blood, which takes into account the colonic mucosal permeability variation - measured by Ussing chamber system on human colonic mucosal biopsies - and the fecal microbiota composition, determined through microbiota 16S rRNA sequencing analysis. Both of the clinical parameters were evaluated in a group of Irritable Bowel Syndrome patients compared to a group of healthy controls. Key ResultsThe results show that plasma drug concentration increases as bacterial concentration decreases, while it decreases as intestinal length decreases too. ConclusionsThe study provides interesting data since in literature there are not yet mathematical models with these features, in which the importance of intestinal microbiota, the "forgotten organ", is considered both for the subject health state and in the nutrients and drugs metabolism.
Assuntos
Microbioma Gastrointestinal , Preparações Farmacêuticas , Antibacterianos , Fezes , Humanos , Mucosa Intestinal , Permeabilidade , RNA Ribossômico 16S/genéticaRESUMO
BACKGROUND: The serological screening for celiac disease (CD) is currently based on the detection of anti-transglutaminase (tTG) IgA antibodies, subsequently confirmed by positive endomysial antibodies (EMA). When an anti-tTG IgA positive/EMA IgA negative result occurs, it can be due either to the lower sensitivity of the EMA test or to the lower specificity of the anti-tTG test. This study aimed at verifying how variation in analytical specificity among different anti-tTG methods could account for this discrepancy. METHODS: A total of 130 consecutive anti-tTG IgA positive/EMA negative samples were collected from the local screening routine and tested using five anti-tTG IgA commercial assays: two chemiluminescence methods, one fluoroimmunoenzymatic method, one immunoenzymatic method and one multiplex flow immunoassay method. RESULTS: Twenty three/130 (17.7%) patients were diagnosed with CD. In the other 107 cases a diagnosis of CD was not confirmed. The overall agreement among the five anti-tTG methods ranged from 28.5% to 77.7%. CD condition was more likely linked to the positivity of more than one anti-tTG IgA assay (monopositive = 2.5%, positive with ≥ three methods = 29.5%; p = 0.0004), but it was not related to anti-tTG IgA antibody levels (either positive or borderline; p = 0.5). CONCLUSIONS: Patients with positive anti-tTG/negative EMA have a low probability of being affected by CD. Given the high variability among methods to measure anti-tTG IgA antibodies, anti-tTG-positive/EMA-negative result must be considered with extreme caution. It is advisable that the laboratory report comments on any discordant results, suggesting to consider the data in the proper clinical context and to refer the patient to a CD reference center for prolonged follow up.
Assuntos
Anticorpos/metabolismo , Doença Celíaca/metabolismo , Proteínas de Ligação ao GTP/metabolismo , Transglutaminases/metabolismo , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Anticorpos/sangue , Doença Celíaca/sangue , Doença Celíaca/diagnóstico , Criança , Pré-Escolar , Feminino , Proteínas de Ligação ao GTP/sangue , Humanos , Masculino , Pessoa de Meia-Idade , Proteína 2 Glutamina gama-Glutamiltransferase , Transglutaminases/sangue , Adulto JovemRESUMO
BACKGROUND AND OBJECTIVE: The indirect immunofluorescence (IIF) on HEp-2 cells is the recommended technique for the detection of antinuclear antibodies. However, it is burdened by some limitations, as it is time consuming and subjective, and it requires trained personnel. In other fields the adoption of deep neural networks has provided an effective high-level abstraction of the raw data, resulting in the ability to automatically generate optimized high-level features. METHODS: To alleviate IIF limitations, this paper presents a computer-aided diagnosis (CAD) system classifying HEp-2 fluorescence intensity: it represents each image using an Invariant Scattering Convolutional Network (Scatnet), which is locally translation invariant and stable to deformations, a characteristic useful in case of HEp-2 samples. To cope with the inter-observer discrepancies found in the dataset, we also introduce a method for gold standard computation that assigns a label and a reliability score to each HEp-2 sample on the basis of annotations provided by expert physicians. Features by Scatnet and gold standard information are then used to train a Support Vector Machine. RESULTS: The proposed CAD is tested on a new dataset of 1771 images annotated by three independent medical centers. The performances achieved by our CAD in recognizing positive, weak positive and negative samples are also compared against those obtained by other two approaches presented so far in the literature. The same system trained on this new dataset is then tested on two public datasets, namely MIVIA and I3Asel. CONCLUSIONS: The results confirm the effectiveness of our proposal, also revealing that it achieves the same performance as medical experts.
Assuntos
Diagnóstico por Computador/métodos , Anticorpos Antinucleares/análise , Linhagem Celular , Conjuntos de Dados como Assunto , Fluorescência , Técnica Indireta de Fluorescência para Anticorpo , Humanos , Redes Neurais de Computação , Reprodutibilidade dos TestesRESUMO
The primary goal of precision medicine is to minimize side effects and optimize efficacy of treatments. Recent advances in medical imaging technology allow the use of more advanced image analysis methods beyond simple measurements of tumor size or radiotracer uptake metrics. The extraction of quantitative features from medical images to characterize tumor pathology or heterogeneity is an interesting process to investigate, in order to provide information that may be useful to guide the therapies and predict survival. This paper discusses the rationale supporting the concept of radiomics and the feasibility of its application to Non-Small Cell Lung Cancer in the field of radiation oncology research. We studied 91 stage III patients treated with concurrent chemoradiation and adaptive approach in case of tumor reduction during treatment. We considered 12 statistics features and 230 textural features extracted from the CT images. In our study, we used an ensemble learning method to classify patients' data into either the adaptive or non-adaptive group during chemoradiation on the basis of the starting CT simulation. Our data supports the hypothesis that a specific signature can be identified (AUC 0.82). In our experience, a radiomic signature mixing semantic and image-based features has shown promising results for personalized adaptive radiotherapy in non-small cell lung cancer.
Assuntos
Carcinoma Pulmonar de Células não Pequenas/radioterapia , Quimiorradioterapia , Medicina de Precisão , Idoso , Idoso de 80 Anos ou mais , Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Carcinoma Pulmonar de Células não Pequenas/patologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estadiamento de Neoplasias , Tomografia Computadorizada por Raios XRESUMO
Chronic Obstructive Pulmonary Disease (COPD) is a preventable, treatable, and slowly progressive disease, whose course is aggravated by a periodic worsening of symptoms and lung function lasting for several days. The development of home telemonitoring systems has made possible to collect symptoms and physiological data in electronic records, boosting the development of decision support systems (DSSs). Current DSSs work with physiological measurements collected by means of several measuring and communication devices as well as with symptoms gathered by questionnaires submitted to COPD subjects. However, this contrasts with the advices provided by the World Health Organization and the Global initiative for chronic Obstructive Lung Disease that recommend to avoid invasive or complex daily measurements. For these reasons this manuscript presents a DSS detecting the onset of worrisome events in COPD subjects. It uses the hearth rate and the oxygen saturation, which can be collected via a pulse oximeter. The DSS consists in a binary finite state machine, whose training stage allows a subject specific personalization of the predictive model, triggering warnings, and alarms as the health status evolves over time. The experiments on data collected from 22 COPD patients tele-monitored at home for six months show that the system recognition performance is better than the one achieved by medical experts. Furthermore, the support offered by the system in the decision-making process allows to increase the agreement between the specialists, largely impacting the recognition of the worrisome events.