Respiratory diseases constitute one of the leading causes of death worldwide and directly affect the patient’s quality of life. Early diagnosis and patient monitoring, which conventionally include lung auscultation, are essential for the efficient management of respiratory diseases. Manual lung sound interpretation is a subjective and time-consuming process that requires high medical expertise. The capabilities that deep learning offers could be exploited in order that robust lung sound classification models can be designed. In this paper, we propose a novel hybrid neural model that implements the focal loss (FL) function to deal with training data imbalance. Features initially extracted from short-time Fourier transform (STFT) spectrograms via a convolutional neural network (CNN) are given as input to a long short-term memory (LSTM) network that memorizes the temporal dependencies between data and classifies four types of lung sounds, including normal, crackles, wheezes, and both crackles and wheezes. The model was trained and tested on the ICBHI 2017 Respiratory Sound Database and achieved state-of-the-art results using three different data splitting strategies—namely, sensitivity 47.37%, specificity 82.46%, score 64.92% and accuracy 73.69% for the official 60/40 split, sensitivity 52.78%, specificity 84.26%, score 68.52% and accuracy 76.39% using interpatient 10-fold cross validation, and sensitivity 60.29% and accuracy 74.57% using leave-one-out cross validation.
Introduction Post-operative hypoparathyroidism is the most encountered complication of thyroid surgery and is classified as temporary or permanent. However, its incidence varies greatly in the literature ranging from 0.5% to 65%. This can be mainly attributed to the different definition of hypoparathyroidism used in each study and especially to the different time cutoff applied to distinguish temporary from permanent hypoparathyroidism. Methods We conducted a systematic literature search in PubMed, Scopus, Cochrane and GoogleScholar databases, as well as grey literature. Ultimately, 45 articles with 23,164 patients in total were included in this review. These articles used either the cutoff of six or twelve post-operative months to distinguish temporary from permanent hypoparathyroidism. Results The overall incidence of permanent hypoparathyroidism diagnosed at 6 months post-operatively was 4.11% and 4.08% at 12 months post-operatively. There was no statistically significant difference between the two groups (p = 0.92). Conclusions We suggest that adhering to the current guidelines that recommend diagnosing temporary hypoparathyroidism when recovery is made within 6 months after surgery is important when conducting future research in order to narrow the gap that exists currently in the literature, as well as when deciding to put patients on long-term calcium supplements.
Obesity in childhood and adolescence represents a major health problem. Novel e-Health technologies have been developed in order to provide a comprehensive and personalized plan of action for the prevention and management of overweight and obesity in childhood and adolescence. We used information and communication technologies to develop a “National Registry for the Prevention and Management of Overweight and Obesity” in order to register online children and adolescents nationwide, and to guide pediatricians and general practitioners regarding the management of overweight or obese subjects. Furthermore, intelligent multi-level information systems and specialized artificial intelligence algorithms are being developed with a view to offering precision and personalized medical management to obese or overweight subjects. Moreover, the Big Data against Childhood Obesity platform records behavioral data objectively by using inertial sensors and Global Positioning System (GPS) and combines them with data of the environment, in order to assess the full contextual framework that is associated with increased body mass index (BMI). Finally, a computerized decision-support tool was developed to assist pediatric health care professionals in delivering personalized nutrition and lifestyle optimization advice to overweight or obese children and their families. These e-Health applications are expected to play an important role in the management of overweight and obesity in childhood and adolescence.
Background Coronary artery disease (CAD) remains one of the leading causes of mortality and morbidity worldwide. As oxygen and nutrient supply to the myocardium significantly decrease during ischemic periods, important changes occur regarding myocardial intermediary energy metabolism. Metabolomics is an emerging field in systems biology, which quantifies metabolic changes in response to disease progression. This study aims to evaluate the diagnostic utility of plasma metabolomics-based biomarkers for determining the complexity and severity of CAD, as it is assessed via the SYNTAX score. Methods Corlipid is a prospective, non-interventional cohort trial empowered to enroll 1065 patients with no previous coronary intervention history, who undergo coronary angiography in University Hospital AHEPA, Thessaloniki. Venous blood samples are collected before coronary angiography. State-of the-art analytical methods are performed to calculate the serum levels of novel biomarkers: ceramides, acyl-carnitines, fatty acids, and proteins such as galectin-3, adiponectin, and the ratio of apolipoprotein B/apolipoprotein A1. Furthermore, all patients will be categorized based on the indication for coronary angiography (acute coronary syndrome, chronic coronary syndrome, preoperative coronary angiography) and on the severity of CAD using the SYNTAX score. Follow-up of 12 months after enrollment will be performed to record the occurrence of major adverse cardiovascular events. A risk prediction algorithm will be developed by combining clinical characteristics with established and novel biomarkers to identify patients at high risk for complex CAD based on their metabolite signatures. The first patient was enrolled in July 2019 and completion of enrollment is expected until May 2021. Discussion CorLipid is an ongoing trial aiming to investigate the correlation between metabolic profile and complexity of coronary artery disease in a cohort of patients undergoing coronary angiography with the potential to suggest a decision-making tool with high discriminative power for patients with CAD. To our knowledge, Corlipid is the first study aspiring to create an integrative metabolomic biomarkers-based algorithm by combining metabolites from multiple classes, involved in a wide range of pathways with well-established biochemical markers. Trial registration CorLipid trial registration: ClinicalTrials.gov number: NCT04580173. Registered 8 October 2020—Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT04580173.
Background Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals. Objective This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications. Methods The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches. Results We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models. Conclusions We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.
Thyroid cancer is the most common endocrine malignancy with an increasing incidence over the past few years. Surgery is considered the primary therapeutic option, which often involves lymph node dissection. The aim of this study was to assess the role of carbon nanoparticles, a novel agent, in thyroid cancer surgery. For that purpose, we conducted a systematic review of the literature on MEDLINE, EMBASE, Scopus, Cochrane and Google Scholar databases from 1 January 2002 to 31 January 2022. Ultimately, 20 articles with a total number of 2920 patients were included in the analysis. The outcome of the analysis showed that the use of carbon nanoparticles is associated with a higher number of harvested lymph nodes (WMD, 1.47, 95% CI, 1.13 to 1.82, p < 0.001) and a lower rate of accidental parathyroid gland removal (OR 0.34, CI 95% 0.24 to 0.50, p < 0.001). Based on these results, we suggest that carbon nanoparticles are applied in thyroid cancer surgery on a wider scale, so that these findings can be confirmed by future research on the subject.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.