This paper presents an adaBoost approach for schizophrenia relapse prediction. The data for the adaBoost are extracted from patients answers to Early Warning Signs questionnaires sent regularly via mobile phone messages. The performance of the adaBoost algorithm is confronted with current ITAREPS system with sensitivity 0.65 and specificity 0.73. AdaBoost has the same sensitivity 0.65 but higher specificity 0.84 and is then ready to became the part of the ITAREPS care program.

• MeSH
• Patient Compliance MeSH
• Algorithms MeSH
• Time Factors MeSH
• Behavior MeSH
• Diagnosis, Computer-Assisted methods   MeSH
• Hospitalization MeSH
• Remote Consultation methods   MeSH
• Humans MeSH
• Text Messaging MeSH
• Recurrence MeSH
• Program Development methods   MeSH
• Schizophrenic Psychology MeSH
• Schizophrenia diagnosis   prevention & control   MeSH
• Software MeSH
• Decision Support Systems, Clinical * MeSH
• Telemedicine methods   MeSH
• Patient Readmission MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

While understanding the structure of RNA molecules is vital for deciphering their functions, determining RNA structures experimentally is exceptionally hard. At the same time, extant approaches to computational RNA structure prediction have limited applicability and reliability. In this paper we provide a method to solve a simpler yet still biologically relevant problem: prediction of secondary RNA structure using structure of different molecules as a template. Our method identifies conserved and unconserved subsequences within an RNA molecule. For conserved subsequences, the template structure is directly transferred into the generated structure and combined with de-novo predicted structure for the unconserved subsequences with low evolutionary conservation. The method also determines, when the generated structure is unreliable. The method is validated using experimentally identified structures. The accuracy of the method exceeds that of classical prediction algorithms and constrained prediction methods. This is demonstrated by comparison using large number of heterogeneous RNAs. The presented method is fast and robust, and useful for various applications requiring knowledge of secondary structures of individual RNA sequences.

• Keywords
• RNA, homology, prediction, secondary structure, template structure,
• Publication type
• Journal Article MeSH

OBJECTIVES: Warfarin use is limited by a low therapeutic index and significant interindividual variability of the daily dose. The most important factor predicting daily warfarin dose is individual genotype, polymorphisms of genes CYP2C9 (warfarin metabolism) and VKORC1 (sensitivity for warfarin). Algorithms using clinical and genetic variables could predict the daily dose before the initiation of therapy. The aim of this study was to develop and validate an algorithm for the prediction of warfarin daily dose in Czech patients. METHODS: Detailed clinical data of patients with known and stable warfarin daily dose were collected. All patients were genotyped for polymorphisms in genes CYP2C9 and VKORC1. RESULTS: Included patients were divided into derivation (n=175) and validation (n=223) cohorts. The final algorithm includes the following variables: Age, height, weight, treatment with amiodarone and presence of variant alleles of genes CYP2C9 and VKORC1. The adjusted coefficient of determination is 72.4% in the derivation and 62.3% in the validation cohort (p<0.001). CONCLUSIONS: Our validated algorithm for warfarin daily dose prediction in our Czech cohort had higher precision than other currently published algorithms. Pharmacogenetics of warfarin has the potential in the clinical practice in specialized centers.

• Keywords
• CYP2C9, VKORC1, daily dose prediction algorithm, pharmacogenetics, warfarin,
• Publication type
• Journal Article MeSH

In this paper, we propose an innovative Federated Learning-inspired evolutionary framework. Its main novelty is that this is the first time that an Evolutionary Algorithm is employed on its own to directly perform Federated Learning activity. A further novelty resides in the fact that, differently from the other Federated Learning frameworks in the literature, ours can efficiently deal at the same time with two relevant issues in Machine Learning, i.e., data privacy and interpretability of the solutions. Our framework consists of a master/slave approach in which each slave contains local data, protecting sensible private data, and exploits an evolutionary algorithm to generate prediction models. The master shares through the slaves the locally learned models that emerge on each slave. Sharing these local models results in global models. Being that data privacy and interpretability are very significant in the medical domain, the algorithm is tested to forecast future glucose values for diabetic patients by exploiting a Grammatical Evolution algorithm. The effectiveness of this knowledge-sharing process is assessed experimentally by comparing the proposed framework with another where no exchange of local models occurs. The results show that the performance of the proposed approach is better and demonstrate the validity of its sharing process for the emergence of local models for personal diabetes management, usable as efficient global models. When further subjects not involved in the learning process are considered, the models discovered by our framework show higher generalization capability than those achieved without knowledge sharing: the improvement provided by knowledge sharing is equal to about 3.03% for precision, 1.56% for recall, 3.17% for F1, and 1.56% for accuracy. Moreover, statistical analysis reveals the statistical superiority of model exchange with respect to the case of no exchange taking place.

• Keywords
• diabetes, evolutionary algorithms, federated learning, interpretable machine learning,
• MeSH
• Algorithms * MeSH
• Glucose MeSH
• Humans MeSH
• Privacy MeSH
• Machine Learning * MeSH
• Knowledge MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Names of Substances
• Glucose MeSH

MOTIVATION: G-quadruplex is a DNA or RNA form in which four guanine-rich regions are held together by base pairing between guanine nucleotides in coordination with potassium ions. G-quadruplexes are increasingly seen as a biologically important component of genomes. Their detection in vivo is problematic; however, sequencing and spectrometric techniques exist for their in vitro detection. We previously devised the pqsfinder algorithm for PQS identification, implemented it in C++ and published as an R/Bioconductor package. We looked for ways to optimize pqsfinder for faster and user-friendly sequence analysis. RESULTS: We identified two weak points where pqsfinder could be optimized. We modified the internals of the recursive algorithm to avoid matching and scoring many sub-optimal PQS conformations that are later discarded. To accommodate the needs of a broader range of users, we created a website for submission of sequence analysis jobs that does not require knowledge of R to use pqsfinder. AVAILABILITY AND IMPLEMENTATION: https://pqsfinder.fi.muni.cz, https://bioconductor.org/packages/pqsfinder. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

• MeSH
• Algorithms MeSH
• G-Quadruplexes * MeSH
• Genome MeSH
• RNA MeSH
• Software MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• RNA MeSH

Diet, stress, genetics, and a sedentary lifestyle may all contribute to heart disease rates. Although recent studies propose comprehensive automated diagnostic systems, these systems tend to focus on one aspect, such as feature selection, prioritization, or predictive accuracy. A more complete approach that considers all of these factors can improve the efficiency of a cardiac prediction system. This study uses an appropriate strategy to overcome potential network design problems, design challenges, overfitting, and lack of robustness that can interfere with system performance. The research introduces an ideally designed deep trust network called ID-DTN to improve system performance. The Ruzzo-Tompa method is used to eliminate noncontributory features. The Seagull Optimization Algorithm (SOA) is introduced to optimize the trust depth network to achieve optimal network design. The study scrutinizes the deep trust network (ID-DTN) and the restricted Boltzmann machine (RBM) and sheds light on the system's operation. This proposal can optimize both network architecture and feature selection, which is the main novelty. The proposed method is analyzed using the below-mentioned metrics: Matthew's correlation coefficient, F1 score, accuracy, sensitivity, specificity, and accuracy. ID-DTN performs well compared to other state-of-the-art methods. The validation results confirm that the proposed method improves the prediction accuracy to 97.11% and provides reliable recommendations for patients with cardiovascular disease.

• Keywords
• Artificial Intelligence, Boltzmann machine, Deep learning, Heart disease prediction, Ruzzo-Tompa, Seagull optimization,
• MeSH
• Algorithms * MeSH
• Humans MeSH
• Heart Diseases * diagnosis   MeSH
• Neural Networks, Computer * MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

BACKGROUND: Despite the established value of genomic testing strategies, practice guidelines for their use do not exist in many indications. OBJECTIVES: We sought to validate a recently introduced scoring algorithm for dystonia, predicting the diagnostic utility of whole-exome sequencing (WES) based on individual phenotypic aspects (age-at-onset, body distribution, presenting comorbidity). METHODS: We prospectively enrolled a set of 209 dystonia-affected families and obtained summary scores (0-5 points) according to the algorithm. Singleton (N = 146), duo (N = 11), and trio (N = 52) WES data were generated to identify genetic diagnoses. RESULTS: Diagnostic yield was highest (51%) among individuals with a summary score of 5, corresponding to a manifestation of early-onset segmental or generalized dystonia with coexisting non-movement disorder-related neurological symptoms. Sensitivity and specificity at the previously suggested threshold for implementation of WES (3 points) was 96% and 52%, with area under the curve of 0.81. CONCLUSIONS: The algorithm is a useful predictive tool and could be integrated into dystonia routine diagnostic protocols. © 2021 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson Movement Disorder Society.

• Keywords
• diagnostic yield, dystonia, exome sequencing, prediction, rare disease, scoring algorithm,
• MeSH
• Algorithms MeSH
• Dystonic Disorders * genetics   MeSH
• Dystonia * diagnosis   genetics   MeSH
• Genetic Testing MeSH
• Humans MeSH
• Parkinson Disease * MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

OBJECTIVES: The objective of this study was to assess the robustness of a novel test bolus (TB)-based computed tomographic angiography (CTA) contrast-enhancement-prediction (CEP) algorithm by retrospectively quantifying the systematic and random errors between the predicted and true enhancements. MATERIALS AND METHODS: All local institutional review boards approved this retrospective study, in which a total of 72 (3 × 24) anonymized cardiac CTA examinations were collected from 3 hospitals. All patients (46 men; median age, 62 years [range, 31-81 years]) underwent a TB scan and a cardiac CTA according to local scan and injection protocols. For each patient, a shorter TB signal and TB signals with lower temporal resolution were derived from the original TB signal. The CEP algorithm predicted the enhancement in the descending aorta (DAo) on the basis of the TB signals in the DAo, the injection protocols and kilovolt settings, as well as population-averaged blood circulation characteristics. The true enhancement was extracted with a region of interest along the DAo centerline. For each patient, the errors in timing and amplitude were calculated; differences between the hospitals were assessed using the 1-way analysis of variance (P < 0.05) and variations between the TB signals were assessed using the within-subject standard deviation. RESULTS: No significant differences were found between the 3 hospitals for any of the TB signals. With errors in the amplitude and timing of 0.3% ± 15.6% and -0.2 ± 2.0 seconds, respectively, no clinically relevant systematic errors existed. Shorter- and coarser-time-sampled TB signals introduced a within-subject standard deviation of 4.0% and 0.5 seconds, respectively. CONCLUSIONS: This TB-based CEP algorithm has no systematic errors in the timing and amplitude of predicted enhancements and is robust against coarser-time-sampled and incomplete TB scans.

• MeSH
• Algorithms * MeSH
• Adult MeSH
• Iopamidol analogs & derivatives   MeSH
• Contrast Media * MeSH
• Coronary Angiography methods   MeSH
• Middle Aged MeSH
• Humans MeSH
• Coronary Artery Disease diagnostic imaging   MeSH
• Tomography, X-Ray Computed methods   MeSH
• Image Processing, Computer-Assisted methods   MeSH
• Predictive Value of Tests MeSH
• Reproducibility of Results MeSH
• Retrospective Studies MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Radiographic Image Enhancement methods   MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Evaluation Study MeSH
• Names of Substances
• iomeprol MeSH Browser
• Iopamidol MeSH
• Contrast Media * MeSH

The fast-growing quantity of information hinders the process of machine learning, making it computationally costly and with substandard results. Feature selection is a pre-processing method for obtaining the optimal subset of features in a data set. Optimization algorithms struggle to decrease the dimensionality while retaining accuracy in high-dimensional data set. This article proposes a novel chaotic opposition fruit fly optimization algorithm, an improved variation of the original fruit fly algorithm, advanced and adapted for binary optimization problems. The proposed algorithm is tested on ten unconstrained benchmark functions and evaluated on twenty-one standard datasets taken from the Univesity of California, Irvine repository and Arizona State University. Further, the presented algorithm is assessed on a coronavirus disease dataset, as well. The proposed method is then compared with several well-known feature selection algorithms on the same datasets. The results prove that the presented algorithm predominantly outperform other algorithms in selecting the most relevant features by decreasing the number of utilized features and improving classification accuracy.

• MeSH
• Algorithms MeSH
• COVID-19 * MeSH
• Drosophila MeSH
• Machine Learning MeSH
• Animals MeSH
• Check Tag
• Animals MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Geographicals
• Arizona MeSH

Seizure prediction is feasible, but greater accuracy is needed to make seizure prediction clinically viable across a large group of patients. Recent work crowdsourced state-of-the-art prediction algorithms in a worldwide competition, yielding improvements in seizure prediction performance for patients whose seizures were previously found hard to anticipate. The aim of the current analysis was to explore potential performance improvements using an ensemble of the top competition algorithms. The results suggest that minor increments in performance may be possible; however, the outcomes of statistical testing limit the confidence in these increments. Our results suggest that for the specific algorithms, evaluation framework, and data considered here, incremental improvements are achievable but there may be upper bounds on machine learning-based seizure prediction performance for some patients whose seizures are challenging to predict. Other more tailored approaches that, for example, take into account a deeper understanding of preictal mechanisms, patient-specific sleep-wake rhythms, or novel measurement approaches, may still offer further gains for these types of patients.

• Keywords
• Open Data Ecosystem for the Neurosciences, ensemble methods, epilepsy, intracranial EEG, refractory epilepsy, seizure prediction,
• MeSH
• Algorithms * MeSH
• Crowdsourcing MeSH
• Electroencephalography MeSH
• Electrocorticography methods   MeSH
• Epilepsies, Partial diagnosis   MeSH
• Middle Aged MeSH
• Humans MeSH
• Young Adult MeSH
• Predictive Value of Tests MeSH
• Drug Resistant Epilepsy diagnosis   MeSH
• Reproducibility of Results MeSH
• Sensitivity and Specificity MeSH
• Sleep MeSH
• Machine Learning MeSH
• Feasibility Studies MeSH
• Seizures diagnosis   MeSH
• Check Tag
• Middle Aged MeSH
• Humans MeSH
• Young Adult MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH