PCGmix: A Data-Augmentation Method For Heart-Sound Classification.

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, responsible for 32% of all deaths, with the annual death toll projected to reach 23.3 million by 2030. The early identification of individuals at high risk of CVD is crucial for the effectiveness of preventive strategies. In the field of deep learning, automated CVD-detection methods have gained traction, with phonocardiogram (PCG) data emerging as a valuable resource. However, deep-learning models rely on large datasets, which are often challenging to obtain. In recent years, data augmentation has become a viable solution to the problem of scarce data. In this paper, we propose a novel data-augmentation technique named PCGmix, specifically engineered for the augmentation of PCG data. The PCGmix algorithm employs a process of segmenting and reassembling PCG recordings, incorporating meticulous interpolation to ensure the preservation of the cardinal diagnostic features pertinent to CVD detection. The empirical assessment of the PCGmix method was utilized on a publicly available database of normal and abnormal heart-sound recordings. To evaluate the impact of data augmentation across a range of dataset sizes, we conducted experiments encompassing both limited and extensive amounts of training data. The experimental results demonstrate that the novel method is superior to the compared state-of-the-art, time-series augmentation. Notably, on limited data, our method achieves comparable accuracy to the no-augmentation approach when trained on 31% to 69% larger datasets. This study suggests that PCGmix can enhance the accuracy of deep-learning models for CVD detection, especially in data-constrained environments.

Lyotropic Aqueous 2-Picolinium Ionic Liquid Crystals and Their Shear-Induced Foams.

1-Dodecyl-2-methylpyridinium bromide ([C12-2-Pic][Br]) and 1-hexadecyl-2-methylpyridinium bromide ([C16-2-Pic][Br]) are two ionic liquid crystals presenting thermotropic smectic phases above 80 °C. Aiming to take advantage of the liquid crystalline properties at lower temperatures, lyotropic aqueous systems were prepared from these two organic salts. Both systems were characterized by polarized optical microscopy (POM), X-ray powder diffraction (XRD), and fast field cycling nuclear magnetic resonance (FFC-NMR) relaxometry to assess their texture, phase structure, and molecular dynamics, respectively. The mesomorphic behavior was induced at room temperature. Moreover, the lyotropic [C12-2-Pic][Br]aq revealed a smectic phase with higher separation between layers, different from the lamellar phases found in the thermotropic system (S1 and SA), which is thermally stable up to 50 °C. Furthermore, the surfactant nature of the ionic liquids diluted solutions investigated in this work allowed the formation of foams. It was found that the precursor solutions of the lyotropic dilutions with the longest alkyl chain ([C16-2-Pic][Br]aq) originated liquid foams with more stable structures than those of [C12-2-Pic][Br]aq.

Call for the responsible artificial intelligence in the healthcare.

The integration of artificial intelligence (AI) into healthcare is progressively becoming pivotal, especially with its potential to enhance patient care and operational workflows. This paper navigates through the complexities and potentials of AI in healthcare, emphasising the necessity of explainability, trustworthiness, usability, transparency and fairness in developing and implementing AI models. It underscores the 'black box' challenge, highlighting the gap between algorithmic outputs and human interpretability, and articulates the pivotal role of explainable AI in enhancing the transparency and accountability of AI applications in healthcare. The discourse extends to ethical considerations, exploring the potential biases and ethical dilemmas that may arise in AI application, with a keen focus on ensuring equitable and ethical AI use across diverse global regions. Furthermore, the paper explores the concept of responsible AI in healthcare, advocating for a balanced approach that leverages AI's capabilities for enhanced healthcare delivery and ensures ethical, transparent and accountable use of technology, particularly in clinical decision-making and patient care.

Effects of deacetylation degree of chitosan on the structure of aerogels.

Chitosan aerogels, obtained by (supercritical) CO2 drying of hydrogels, are novel adsorbents because of their large surface area and high porosity. Intrinsic properties of chitosan such as molecular weight (MW) and degree of deacetylation (DDA) had large impacts on the characteristics of chitosan aerogels. Although there are a few studies about the effects of solely DDA or MW on aerogel structure, none of them has focused on the mutual effects. The study aims to investigate the combined effects of MW and DDA of chitosan on aerogel properties. Hydrogels were produced in beads form by physical gelation of the chitosan solutions (2 % w/v in acetic acid of 1 %, v/v) in an alkaline environment (NaOH, 4 N). Supercritical CO2 dried aerogels were examined with respect to the bulk density, diameter as well as pore characteristics, and surface area by Barrett-Joyner-Halenda (BJH) and Brunauer-Emmett-Teller (BET) methods, respectively. Morphologies of aerogels were also examined by Scanning Electron Microscopy (SEM) images and structural changes of aerogels were observed by Fourier Transform Infrared (FTIR) Spectroscopy. Additional to BET-BJH analysis, proton relaxation dispersion was measured by Fast Field Cycling NMR (FFC-NMR) to determine the pore volume of the aerogels. Compact structures were obtained for higher MW chitosan and lower MW chitosans with higher DDA increasing the aerogel diameters. All types of aerogels obtained by different chitosan characteristics (MW and DDA) showed a porous structure and the highest DDA with the lowest MW caused the minimum bulk density with the highest water absorption rate. Although different N2 adsorption-desorption profiles were obtained in terms of pore volumes; all aerogels had Type IV isotherms with Type H1 hysteresis curve. FFC-NMR experiments showed that the coherence length values were associated with the pore volumes and FFC-NMR experiments were found to be meaningful as supportive experiments for the characterization of aerogels.

Wellbeing Forecasting in Postpartum Anemia Patients.

Postpartum anemia is a very common maternal health problem and remains a persistent public health issue globally. It negatively affects maternal mood and could lead to depression, increased fatigue, and decreased cognitive abilities. It can and should be treated by restoring iron stores. However, in most health systems, there is typically a six-week gap between birth and the follow-up postpartum visit. Risks of postpartum maternal complications are usually assessed shortly after birth by clinicians intuitively, taking into account psychosocial and physical factors, such as the presence of anemia and the type of iron supplementation. In this paper, we investigate the possibility of using machine-learning algorithms to more reliably forecast three parameters related to patient wellbeing, namely depression (measured by Edinburgh Postnatal Depression Scale-EPDS), overall tiredness, and physical tiredness (both measured by Multidimensional Fatigue Inventory-MFI). Data from 261 patients were used to train the forecasting models for each of the three parameters, and they outperformed the baseline models that always predicted the mean values of the training data. The mean average error of the elastic net regression model for predicting the EPDS score (with values ranging from 0 to 19) was 2.3 and outperformed the baseline, which already hints at the clinical usefulness of using such a model. We further investigated what features are the most important for this prediction, where the EDPS score and both tiredness indexes at birth turned out to be by far the most prominent prediction features. Our study indicates that the machine-learning model approach has the potential for use in clinical practice to predict the onset of depression and severe fatigue in anemic patients postpartum and potentially improve the detection and management of postpartum depression and fatigue.

Optimizing non-pharmaceutical intervention strategies against COVID-19 using artificial intelligence.

One key task in the early fight against the COVID-19 pandemic was to plan non-pharmaceutical interventions to reduce the spread of the infection while limiting the burden on the society and economy. With more data on the pandemic being generated, it became possible to model both the infection trends and intervention costs, transforming the creation of an intervention plan into a computational optimization problem. This paper proposes a framework developed to help policy-makers plan the best combination of non-pharmaceutical interventions and to change them over time. We developed a hybrid machine-learning epidemiological model to forecast the infection trends, aggregated the socio-economic costs from the literature and expert knowledge, and used a multi-objective optimization algorithm to find and evaluate various intervention plans. The framework is modular and easily adjustable to a real-world situation, it is trained and tested on data collected from almost all countries in the world, and its proposed intervention plans generally outperform those used in real life in terms of both the number of infections and intervention costs.

Artificial intelligence based personalized predictive survival among colorectal cancer patients.

BACKGROUND AND OBJECTIVE: Colorectal cancer is a major health concern. It is now the third most common cancer and the fourth leading cause of cancer mortality worldwide. The aim of this study was to evaluate the performance of machine learning algorithms for predicting survival of colorectal cancer patients 1 to 5 years after diagnosis, and identify the most important variables. METHODS: A sample of 1236 patients diagnosed with colorectal cancer and 118 predictor variables has been used. The outcome of interest was a binary variable indicating whether the patient survived the number of years in question or not. 20 predictor variables were selected using mutual information score with the outcome. We implemented 11 machine learning algorithms and evaluated their performance with a 5 by 2-fold cross-validation with stratified folds and with paired Student's t-tests. We compared the results with the Kaplan-Meier estimator and Cox's proportional hazard regression. RESULTS: Using the 20 most important predictor variables for each of the survival years, the logistic regression algorithm achieved an area under the receiver operating characteristic curve of 0.850 (0.014 SD, 0.840-0.860 95 % CI) for the 1-year, and 0.872 (0.014 SD, 0.861-0.882 95% CI) for the 5-year survival prediction. Using only the 5 most important predictor variables, the corresponding values are 0.793 (0.020 SD, 0.778-0.807 95% CI) and 0.794 (0.011 SD, 0.785-0.802 95% CI). The most important variables for 1-year prediction were number of R residual, M distant metastasis, overall stage, probable recurrence within 5 years, and tumour length, whereas for 5-year prediction the most important were probable recurrence within 5 years, R residual, M distant metastasis, number of positive lymph nodes, and palliative chemotherapy. Biomarkers do not appear among the top 20 most important ones. For all survival intervals, the probability of the top model agrees with the Kaplan-Meier estimate, both in the interval of one standard deviation and in the 95% confidence interval. CONCLUSIONS: The findings suggest that machine learning algorithms can predict the survival probability of colorectal cancer patients and can be used to inform the patients and assist decision-making in clinical care management. In addition, this study unveils the most essential variables for estimating survival short- and long-term among patients with Colorectal cancer.

Adult height prediction using the growth curve comparison method.

Understanding the growth pattern is important in view of child and adolescent development. Due to different tempo of growth and timing of adolescent growth spurt, individuals reach their adult height at different ages. Accurate models to assess the growth involve intrusive radiological methods whereas the predictive models based solely on height data are typically limited to percentiles and therefore rather inaccurate, especially during the onset of puberty. There is a need for more accurate non-invasive methods for height prediction that are easily applicable in the fields of sports and physical education, as well as in endocrinology. We developed a novel method, called Growth Curve Comparison (GCC), for height prediction, based on a large cohort of > 16,000 Slovenian schoolchildren followed yearly from ages 8 to 18. We compared the GCC method to the percentile method, linear regressor, decision tree regressor, and extreme gradient boosting. The GCC method outperformed the predictions of other methods over the entire age span both in boys and girls. The method was incorporated into a publicly available web application. We anticipate our method to be applicable also to other models predicting developmental outcomes of children and adolescents, such as for comparison of any developmental curves of anthropometric as well as fitness data. It can serve as a useful tool for assessment, planning, implementation, and monitoring of somatic and motor development of children and youth.

Identification of decompensation episodes in chronic heart failure patients based solely on heart sounds.

Decompensation episodes in chronic heart failure patients frequently result in unplanned outpatient or emergency room visits or even hospitalizations. Early detection of these episodes in their pre-symptomatic phase would likely enable the clinicians to manage this patient cohort with the appropriate modification of medical therapy which would in turn prevent the development of more severe heart failure decompensation thus avoiding the need for heart failure-related hospitalizations. Currently, heart failure worsening is recognized by the clinicians through characteristic changes of heart failure-related symptoms and signs, including the changes in heart sounds. The latter has proven to be largely unreliable as its interpretation is highly subjective and dependent on the clinicians' skills and preferences. Previous studies have indicated that the algorithms of artificial intelligence are promising in distinguishing the heart sounds of heart failure patients from those of healthy individuals. In this manuscript, we focus on the analysis of heart sounds of chronic heart failure patients in their decompensated and recompensated phase. The data was recorded on 37 patients using two types of electronic stethoscopes. Using a combination of machine learning approaches, we obtained up to 72% classification accuracy between the two phases, which is better than the accuracy of the interpretation by cardiologists, which reached 50%. Our results demonstrate that machine learning algorithms are promising in improving early detection of heart failure decompensation episodes.

Observing short-range orientational order in small-molecule liquids.

Local molecular ordering in liquids has attracted a lot of interest from researchers investigating crystallization, but is still poorly understood on the molecular scale. Classical nucleation theory (CNT), a macroscopic thermodynamic description of condensation, has shortcomings when dealing with clusters consisting of tens of molecules. Cluster formation and local order fluctuations in liquid media are difficult to study due to the limited spatial resolution of electron- and photon-imaging methods. We used NMR relaxometry to demonstrate the existence of dynamic clusters with short-range orientational order in nominally isotropic liquids consisting of elongated molecules. We observed clusters in liquids where the local ordering is driven by polar, steric, and hydrogen-bond interactions between the molecules. In the case of a liquid crystal, measuring the local orientational order fluctuations allowed us to observe the size of these clusters diverging when approaching the phase transition from the isotropic to the nematic phase. These fluctuations are described in terms of rotational elasticity as a consequence of the correlated reorientations of the neighbouring molecules. Our quantitative observations of the dynamic clusters in liquids, numbering about ten or fewer molecules, indicate that this is a general phenomenon in various types of liquids.

Holistic health record for Hidradenitis suppurativa patients.

Hidradenitis suppurativa (HS) is a recurrent inflammatory skin disease with a complex etiopathogenesis whose treatment poses a challenge in the clinical practice. Here, we present a novel integrated pipeline produced by the European consortium BATMAN (Biomolecular Analysis for Tailored Medicine in Acne iNversa) aimed at investigating the molecular pathways involved in HS by developing new diagnosis algorithms and building cellular models to pave the way for personalized treatments. The objectives of our european Consortium are the following: (1) identify genetic variants and alterations in biological pathways associated with HS susceptibility, severity and response to treatment; (2) design in vitro two-dimensional epithelial cell and tri-dimensional skin models to unravel the HS molecular mechanisms; and (3) produce holistic health records HHR to complement medical observations by developing a smartphone application to monitor patients remotely. Dermatologists, geneticists, immunologists, molecular cell biologists, and computer science experts constitute the BATMAN consortium. Using a highly integrated approach, the BATMAN international team will identify novel biomarkers for HS diagnosis and generate new biological and technological tools to be used by the clinical community to assess HS severity, choose the most suitable therapy and follow the outcome.

Machine Learning Prediction Models for Chronic Kidney Disease Using National Health Insurance Claim Data in Taiwan.

Chronic kidney disease (CKD) represents a heavy burden on the healthcare system because of the increasing number of patients, high risk of progression to end-stage renal disease, and poor prognosis of morbidity and mortality. The aim of this study is to develop a machine-learning model that uses the comorbidity and medication data obtained from Taiwan's National Health Insurance Research Database to forecast the occurrence of CKD within the next 6 or 12 months before its onset, and hence its prevalence in the population. A total of 18,000 people with CKD and 72,000 people without CKD diagnosis were selected using propensity score matching. Their demographic, medication and comorbidity data from their respective two-year observation period were used to build a predictive model. Among the approaches investigated, the Convolutional Neural Networks (CNN) model performed best with a test set AUROC of 0.957 and 0.954 for the 6-month and 12-month predictions, respectively. The most prominent predictors in the tree-based models were identified, including diabetes mellitus, age, gout, and medications such as sulfonamides and angiotensins. The model proposed in this study could be a useful tool for policymakers in predicting the trends of CKD in the population. The models can allow close monitoring of people at risk, early detection of CKD, better allocation of resources, and patient-centric management.

Sensitivity of Proton NMR Relaxation and Proton NMR Diffusion Measurements to Olive Oil Adulterations with Vegetable Oils.

Olive oils and, in particular, extra-virgin olive oils (EVOOs) are one of the most frauded food. Among the different adulterations of EVOOs, the mixture of high-quality olive oils with vegetable oils is one of the most common in the market. The need for fast and cheap techniques able to detect extra-virgin olive oil adulterations was the main motivation for the present research work based on 1H NMR relaxation and diffusion measurements. In particular, the 1H NMR relaxation times, T1 and T2, measured at 2 and 100 MHz on about 60 EVOO samples produced in Italy are compared with those measured on four different vegetable oils, produced from macadamia nuts, linseeds, sunflower seeds, and soybeans. Self-diffusion coefficients on this set of olive oils and vegetable oil samples were measured by means of the 1H NMR diffusion ordered spectroscopy (DOSY) technique, showing that, except for the macadamia oil, other vegetable oils are characterized by an average diffusion coefficient sensibly different from extra-virgin olive oils. Preliminary tests based on both NMR relaxation and diffusometry methods indicate that eventual adulterations of EVOO with linseed oil and macadamia oil are the easiest and the most difficult frauds to be detected, respectively.

Analysis of Extra Virgin Olive Oils from Two Italian Regions by Means of Proton Nuclear Magnetic Resonance Relaxation and Relaxometry Measurements.

The interest in development of new non-destructive methods for characterization of extra virgin olive oils (EVOOs) has been increasing in the recent years. Among different experimental techniques, nuclear magnetic resonance (NMR) relaxation measurements are very promising in the field of food characterization and authentication. In this study, we focused on relaxation times T1 and T2 measured at different magnetic field strengths (namely, 2, 100, and 400 MHz) and 1H NMR T1 relaxometry dispersions directly on olive oil samples without any chemical/physical treatments. A large set of EVOO samples produced in two regions of Italy, Tuscany and Apulia, were investigated by means of 1H NMR relaxation techniques. The relaxation studies reported here show several common features between the two sets of EVOO samples, thus indicating that relaxation properties, namely, the ranges of values of T1 and T2 at 2 and 100 MHz, are characteristic of EVOOs, independently from the cultivars, climate, and geographic origin. This is a promising result in view of quality control and monitoring.

Size- and Time-Dependent Particle Removal Efficiency of Face Masks and Improvised Respiratory Protection Equipment Used during the COVID-19 Pandemic.

Size- and time-dependent particle removal efficiency (PRE) of different protective respiratory masks were determined using a standard aerosol powder with the size of particles in the range of an uncoated SARS-CoV-2 virus and small respiratory droplets. Number concentration of particles was measured by a scanning mobility particle sizer. Respiratory protective half-masks, surgical masks, and cotton washable masks were tested. The results show high filtration efficiency of FFP2, FFP3, and certified surgical masks for all sizes of tested particles, while protection efficiency of washable masks depends on their constituent fabrics. Measurements showed decreasing PRE of all masks over time due to transmission of nanoparticles through the mask-face interface. On the other hand, the PRE of the fabric is governed by deposition of the aerosols, consequently increasing the PRE.

Sterilization of polypropylene membranes of facepiece respirators by ionizing radiation.

Ionizing radiation has been identified as an option for sterilization of disposable filtering facepiece respirators in situations where the production of the respirators cannot keep up with demand. Gamma radiation and high energy electrons penetrate deeply into the material and can be used to sterilize large batches of masks within a short time period. In relation to reports that sterilization by ionizing radiation reduces filtration efficiency of polypropylene membrane filters on account of static charge loss, we have demonstrated that both gamma and electron beam irradiation can be used for sterilization, provided that the respirators are recharged afterwards.

Nuclear quadrupole resonance supported by periodic quantum calculations: a sensitive tool for precise structural characterization of short hydrogen bonds.

Systems with short hydrogen bonds (H-bonds) are notoriously difficult to describe even using cutting edge experimental techniques supported by advanced computational protocols. One of the most challenging issues is the highly dislocated H-bonded proton, which is typically smeared over a large area, featuring complex dynamics governed by pronounced nuclear quantum effects. Thus, in combination with experimental results, these systems offer a rich platform for the benchmarking of various computational approaches and methods. Herein, we present a methodology combining experimental and computational assessment of H-bond observables probed by the nuclear quadrupole resonance technique. Focusing on the case of picolinic acid N-oxide featuring one of the shortest known hydrogen bonds (ROO ∼ 2.425 Å), we compare the predictions of nuclear quadrupole coupling constants (NQCCs) for a series of computational models differing in fine structural details of the H-bond. By comparing the computed 14N and 17O NQCCs with the measured ones and by analyzing the sensitivity of NQCCs to H-bond geometry variations, we demonstrate that NQCCs represent a very sensitive probe for H-bond geometry, particularly the proton location, thereby offering, in conjunction with computations, an accurate and reliable tool for the fine structural characterization of short H-bonds. Importantly, the present methodology is a good compromise between accuracy and computational cost.

Author Correction: Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Using machine learning models to predict the initiation of renal replacement therapy among chronic kidney disease patients.

Starting renal replacement therapy (RRT) for patients with chronic kidney disease (CKD) at an optimal time, either with hemodialysis or kidney transplantation, is crucial for patient's well-being and for successful management of the condition. In this paper, we explore the possibilities of creating forecasting models to predict the onset of RRT 3, 6, and 12 months from the time of the patient's first diagnosis with CKD, using only the comorbidities data from National Health Insurance from Taiwan. The goal of this study was to see whether a limited amount of data (including comorbidities but not considering laboratory values which are expensive to obtain in low- and medium-income countries) can provide a good basis for such predictive models. On the other hand, in developed countries, such models could allow policy-makers better planning and allocation of resources for treatment. Using data from 8,492 patients, we obtained the area under the receiver operating characteristic curve (AUC) of 0.773 for predicting RRT within 12 months from the time of CKD diagnosis. The results also show that there is no additional advantage in focusing only on patients with diabetes in terms of prediction performance. Although these results are not as such suitable for adoption into clinical practice, the study provides a strong basis and a variety of approaches for future studies of forecasting models in healthcare.

Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data.

Cell Population Data (CPD) provides various blood cell parameters that can be used for differential diagnosis. Data analytics using Machine Learning (ML) have been playing a pivotal role in revolutionizing medical diagnostics. This research presents a novel approach of using ML algorithms for screening hematologic malignancies using CPD. The data collection was done at Konkuk University Medical Center, Seoul. A total of (882 cases: 457 hematologic malignancy and 425 hematologic non-malignancy) were used for analysis. In our study, seven machine learning models, i.e., SGD, SVM, RF, DT, Linear model, Logistic regression, and ANN, were used. In order to measure the performance of our ML models, stratified 10-fold cross validation was performed, and metrics, such as accuracy, precision, recall, and AUC were used. We observed outstanding performance by the ANN model as compared to other ML models. The diagnostic ability of ANN achieved the highest accuracy, precision, recall, and AUC ± Standard Deviation as follows: 82.8%, 82.8%, 84.9%, and 93.5% ± 2.6 respectively. ANN algorithm based on CPD appeared to be an efficient aid for clinical laboratory screening of hematologic malignancies. Our results encourage further work of applying ML to wider field of clinical practice.