Machine learning and integrative multi-omics network analysis for survival prediction in acute myeloid leukemia

BACKGROUND

Acute myeloid leukemia (AML) is the most common malignant myeloid disorder in adults and the fifth most common malignancy in children, necessitating advanced technologies for outcome prediction.

METHOD

This study aims to enhance prognostic capabilities in AML by integrating multi-omics data, especially gene expression and methylation, through network-based feature selection methodologies. By employing artificial intelligence and network analysis, we are exploring different methods to build a machine learning model for predicting AML patient survival. We evaluate the effectiveness of combining omics data, identify the most informative method for network integration and compare the performance with standard feature selection methods.

RESULTS

Our findings demonstrate that integrating gene expression and methylation data significantly improves prediction accuracy compared to single omics data. Among network integration methods, our study identifies the best approach that improves informative feature selection for predicting patient outcomes in AML. Comparative analyses demonstrate the superior performance of the proposed network-based methods over standard techniques.

CONCLUSIONS

This research presents an innovative and robust methodology for building a survival prediction model tailored to AML patients. By leveraging multilayer network analysis for feature selection, our approach contributes to improving the understanding and prognostic capabilities in AML and laying the foundation for more effective personalized therapeutic interventions in the future.

Association of beat-to-beat P-wave analysis index to the extent of left atrial low-voltage areas in patients with paroxysmal atrial fibrillation

BACKGROUND

Left atrial (LA) fibrosis has been shown to be associated with atrial fibrillation (AF) recurrence. Beat-to-beat (B2B) index is a non-invasive classifier, based on B2B P-wave morphological and wavelet analysis, shown to be associated with AF incidence and recurrence. In this study, we tested the hypothesis that the B2B index is associated with the extent of LA low-voltage areas (LVAs) on electroanatomical mapping.

METHODS

Patients with paroxysmal AF scheduled for pulmonary vein isolation, without evident structural remodeling, were included. Pre-ablation electroanatomical voltage maps were used to calculate the surface of LVAs (<0.5 mV). B2B index was compared between patients with small versus large LVAs.

RESULTS

35 patients were included (87% male, median age 62). The median surface area of LVAs was 7.7 (4.4-15.8) cm2 corresponding to 5.6 (3.3-12.1) % of LA endocardial surface. B2B index was 0.57 (0.52-0.59) in patients with small LVAs (below the median) compared to 0.65 (0.56-0.77) in those with large LVAs (above the median) (p = 0.009). In the receiver operator characteristic curve analysis for predicting large LVAs, the c-statistic was 0.75 (p = 0.006) for B2B index and 0.81 for the multivariable model including B2B index (multivariable p = 0.04) and P-wave duration.

CONCLUSION

In patients with paroxysmal AF without overt atrial myopathy, B2B P-wave analysis appears to be a useful non-invasive correlate of low-voltage areas-and thus fibrosis-in the LA. This finding establishes a pathophysiological basis for B2B index and its potential usefulness in the selection process of patients who are likely to benefit most from further invasive treatment.

Association between antihypertensive treatment, blood pressure variability, and stroke severity and outcomes in acute ischemic stroke

OBJECTIVES

The management of blood pressure (BP) and the role of antihypertensive medications (AHT) in acute ischemic stroke (AIS) remain uncertain. This study aimed to investigate the impact of pre- and intra-stroke AHT use on systolic (SBP), diastolic (DBP), and blood pressure variability (BPV).

MATERIALS AND METHODS

A post-hoc analysis was conducted on 228 AIS patients from the PREVISE study. All patients underwent 24-hour ambulatory blood pressure monitoring within 48 h of symptom onset. Clinical and laboratory data, as well as AHT details, were recorded. Mean BP parameters and BPV for SBP and DBP were computed. The study endpoint was 3-month mortality.

RESULTS

The majority of stroke patients (84.2%) were already taking AHTs. Beta blockers and ACE inhibitors use before and after stroke were linked to higher DBP variability. Prior angiotensin receptor blockers (ARBs) and vasodilators use correlated with increased SBP variability and lower daytime SBP/DBP levels, respectively. The continuation, discontinuation, or change of AHTs after stroke onset did not significantly affect outcomes. Patients under AHTs during AIS exhibited reduced mortality, with those previously using calcium channel blockers experiencing less severe strokes, and those previously using ARBs showing better outcomes at three months.

CONCLUSIONS

These findings advocate for personalized BP management in AIS, based on a patient's antihypertensive history. These insights could enhance treatment efficacy, guide research, and improve care for acute ischemic stroke patients.

Towards Automating Personal Exercise Assessment and Guidance with Affordable Mobile Technology

Physical activity (PA) offers many benefits for human health. However, beginners often feel discouraged when introduced to basic exercise routines. Due to lack of experience and personal guidance, they might abandon efforts or experience musculoskeletal injuries. Additionally, due to phenomena such as pandemics and limited access to supervised exercise spaces, especially for the elderly, the need to develop personalized systems has become apparent. In this work, we develop a monitored physical exercise system that offers real-time guidance and recommendations during exercise, designed to assist users in their home environment. For this purpose, we used posture estimation interfaces that recognize body movement using a computer or smartphone camera. The chosen pose estimation model was BlazePose. Machine learning and signal processing techniques were used to identify the exercise currently being performed. The performances of three machine learning classifiers were evaluated for the exercise recognition task, achieving test-set accuracy between 94.76% and 100%. The research methodology included kinematic analysis (KA) of five selected exercises and statistical studies on performance and range of motion (ROM), which enabled the identification of deviations from the expected exercise execution to support guidance. To this end, data was collected from 57 volunteers, contributing to a comprehensive understanding of exercise performance. By leveraging the capabilities of the BlazePose model, an interactive tool for patients is proposed that could support rehabilitation programs remotely.

P-wave Indices as Predictors of Atrial Fibrillation: The Lion from a Claw

The P wave, representing the electrical fingerprint of atrial depolarization, contains information regarding spatial and temporal aspects of atrial electrical-and potentially structural-properties. However, technical and biological reasons, including-but not limited to-the low amplitude of the P wave and large interindividual variations in normal or pathologic atrial electrical activity, make gathering and utilizing this information for clinical purposes a rather cumbersome task. However, even crude ECG descriptors, such as P-wave dispersion, have been shown to be of predictive value for assessing the probability that a patient already has or will shortly present with AF. More sophisticated methods of analyzing the ECG signal, on a single- or multi- beat basis, along with novel approaches to data handling, namely machine learning, seem to be leading up to more accurate and robust ways to obtain clinically useful information from the humble P wave.

Methylation haplotypes of the insulin gene promoter in children and adolescents with type 1 diabetes: Can a dimensionality reduction approach predict the disease?

DNA methylation of cytosine-guanine sites (CpGs) is associated with type 1 diabetes (T1D). The sequence of methylated and non-methylated sites in a specific genetic region constitutes its methyl-haplotype. The aim of the present study was to identify insulin gene promoter (IGP) methyl-haplotypes among children and adolescents with T1D and suggest a predictive model for the discrimination of cases and controls according to methyl-haplotypes. A total of 40 individuals (20 T1D) participated. The IGP region from peripheral whole blood DNA of 40 participants (20 T1D) was sequenced using next-generation sequencing, sequences were read using FASTQ files and methylation status was calculated by python-based pipeline for targeted deep bisulfite sequenced amplicons (ampliMethProfiler). Methylation profile at 10 CpG sites proximal to transcription start site of the IGP was recorded and coded as 0 for unmethylation or 1 for methylation. A single read could result in '1111111111' methyl-haplotype (all methylated), '000000000' methyl-haplotype (all unmethylated) or any other combination. Principal component analysis was applied to the generated methyl-haplotypes for dimensionality reduction, and the first three principal components were employed as features with five different classifiers (random forest, decision tree, logistic regression, Naive Bayes, support vector machine). Naive Bayes was the best-performing classifier, with 0.9 accuracy. Predictive models were evaluated using receiver operating characteristics (AUC 0.96). Methyl-haplotypes '1111111111', '1111111011', '1110111111', '1111101111' and '1110101111' were revealed to be the most significantly associated with T1D according to the dimensionality reduction method. Methylation-based biomarkers such as IGP methyl-haplotypes could serve to identify individuals at high risk for T1D.

Midday Dipping and Circadian Blood Pressure Patterns in Acute Ischemic Stroke

The purpose of this study was to investigate the alterations in blood pressure (BP) during midday and the changes in circadian BP patterns in the acute phase of ischemic stroke (AIS) with the severity of stroke and their predictive role outcomes within 3 months. A total of 228 AIS patients (a prospective multicenter follow-up study) underwent 24 h ambulatory blood pressure monitoring (ABPM). Mean BP parameters during the day (7:00-22:59), the midday (13:00-16:59), and the night (23:00-6:59), and midday and nocturnal dipping were calculated. Midday SBP dippers had less severe stroke, lower incidence of hypertension and SBP/DBP on admission, lower levels of serum glucose and WBCs, and delayed initiation of ABPM compared to risers. There was a reverse relation between midday SBP dipping and both nocturnal dipping and stroke severity. The "double dippers" (midday and nocturnal dipping) had the least severe stroke, the lowest SBP/DBP on admission, the lowest heart rate from ABPM, and a lower risk of an unfavorable outcome, while the "double risers" had the opposite results, by an approximately five-fold risk of death/disability at 3 months. These findings indicate different circadian BP patterns during the acute phase of AIS, which could be considered a marker of stroke severity and prognosis.

Prognostic significance of 24-h blood pressure and variability indices in the outcome of acute ischaemic stroke

BACKGROUND

The association between blood pressure (BP) levels and BP variability (BPV) following acute ischaemic stroke (AIS) and outcome remains controversial.

AIMS

To investigate the predictive value of systolic BP (SBP) and diastolic BP (DBP) and BPV measured using 24-h ambulatory blood pressure monitoring (ABPM) methods during AIS regarding outcome.

METHODS

A total of 228 AIS patients (175 without prior disability) underwent ABPM every 20 min within 48 h from onset using an automated oscillometric device (TM 2430, A&D Company Ltd) during day time (7:00-22:59) and night time (23:00-6:59). Risk factors, stroke subtypes, clinical and laboratory findings were recorded. Mean BP parameters and several BPV indices were calculated. End-points were death and unfavourable functional outcome (disability/death) at 3 months.

RESULTS

A total of 61 (26.7%) patients eventually died. Multivariate logistic regression analysis revealed that only mean night-time DBP (hazard ratio (HR): 1.04; 95% confidence interval (CI): 1.00-1.07) was an independent prognostic factor of death. Of the 175 patients without prior disability, 79 (45.1%) finally met the end-point of unfavourable functional outcome. Mean 24-h SBP (HR: 1.03; 95% CI: 1.00-1.05), day-time SBP (HR: 1.02; 95% CI: 1.00-1.05) and night-time SBP (HR: 1.03; 95% CI: 1.01-1.05), SBP nocturnal decline (HR: 0.93; 95% CI: 0.88-0.99), mean 24-h DBP (HR: 1.08; 95% CI: 1.03-1.13), day-time DBP (HR: 1.07; 95% CI: 1.03-1.12) and night-time DBP (HR: 1.06; 95% CI: 1.02-1.10) were independent prognostic factors of an unfavourable functional outcome.

CONCLUSIONS

In contrast with BPV indices, ABPM-derived BP levels and lower or absence of BP nocturnal decline in the acute phase are prognostic factors of outcome in AIS patients.

Gamifying rehabilitation: MILORD platform as an upper limb motion rehabilitation service

Motor learning is based on the correct repetition of specific movements for their permanent storage in the central nervous system (CNS). Rehabilitation relies heavily on the repetition of specific movements, and game scenarios are ideal environments to build routines of repetitive exercises that have entertaining characteristics. In this respect, the gamification of the rehabilitation program, through the introduction of game-specific techniques and design concepts, has gained attention as a complementary or alternative to routine rehabilitation programs. A gamified rehabilitation program promises to gain the patient's attention, to reduce the monotony of the process and preserve motivation to attend, and to create virtual incentives through the game, toward maintaining compliance to the “prescribed” program. This is often achieved through goal-oriented tasks and real-time feedback in the form of points and other in-game rewards. This paper describes MILORD rehabilitation platform, an affordable technological solution, which aims to support health professionals and enable remote rehabilitation, while maintaining health service characteristics and monitoring. MILORD is an end-to-end platform that consists of an interactive computer game, utilizing a leap motion sensor, a centralized user management system, an analysis platform that processes the data generated by the game, and an analysis dashboard presenting a set of meaningful features that describe upper limb movement. Our solution facilitates the monitoring of the patients' progress and provides an alternative way to analyze hand movement. The system was tested with normal subjects and patients and experts to record user's experience, receive feedback, identify any problems, and understand the system's value in monitoring and support motion defect and progress. This small-scale study indicated the capacity of the analysis to quantify the movement in a meaningful way and express the differences between normal and pathological movement, and the user experience was positive with both patients and normal subjects.

P-wave beat-to-beat analysis to predict atrial fibrillation recurrence after catheter ablation

Introduction

Identification of patients prone to atrial fibrillation (AF) relapse after catheter ablation is essential for better patient selection and risk stratification.

Purpose

The current prospective cohort study aims to validate a novel P-wave index based on beat-to-beat (B2B) P-wave morphological and wavelet analysis designed to detect patients with low burden AF, as a predictor of AF recurrence within a year after successful catheter ablation.

Methods

12-lead ECG and 10-minute vectorcardiogram (VCG) recordings were obtained from 138 consecutive patients scheduled for AF ablation. Pre-ablation B2B P-wave index, along with standard P-wave indices, clinical scores and patients history and physical examination parameters were evaluated as AF recurrence predictors.

Results

Univariate analysis revealed that patients with higher B2B P-wave index had a two-fold risk for AF recurrence (HR: 2.35, 95% CI: 1.24–4.44, p: 0.010). Prolonged P-wave, interatrial block, early AF recurrence, female gender, heart failure history, previous stroke, and CHA2DS2-VASc score ≥2 were also found to be related to higher recurrence rate. Multivariate analysis of predictors that can be assessed before ablation revealed that B2B P-wave index, along with heart failure history and history of previous stroke or transient ischemic attack are independent predicting factors of AF relapse.

Conclusion

B2B P-wave morphology and wavelet analysis, is a promising, non-invasive technique, able to identify patients prone to AF recurrence after pulmonary veins ablation. Further studies are needed to assess the predictive value of B2B index with greater accuracy and evaluate a possible relationship with atrial substrate analysis.

Funding Acknowledgement

Type of funding sources: Public Institution(s). Main funding source(s): Hellenic Society of Cardiology

Assessment of Singularities in the EEG During A-Phases of Sleep Based on Wavelet Decomposition

Electroencephalography (EEG) signals convey information related to different processes that take place in the brain. From the EEG fluctuations during sleep, it is possible to establish the sleep stages and identify short events, commonly related to a specific physiological process or pathology. Some of these short events (called A-phases) present an organization and build up the concept of the Cyclic Alternating Pattern (CAP) phenomenon. In general, the A-phases abruptly modify the EEG fluctuations, and a singular behavior could occur. With the aim to quantify the abrupt changes during A-phases, in this work the wavelet analysis is considered to compute Hölder exponents, which measure the singularity strength. We considered time windows of 2s outside and 5s inside A-phases onset (or offset). A total number of 5121 A-phases from 9 healthy participants and 10 patients with periodic leg movements were analyzed. Within an A-phase the Hölder numerical value tends to be 0.6, which implies a less abrupt singularity. Whereas outside of A-phases, it is observed that the Hölder value is approximately equal to 0.3, which implies stronger singularities, i.e., a more evident discontinuity in the signal behavior. In addition, it seems that the number of singularities increases inside of A-phases. The numerical results suggest that the EEG naturally conveys singularities modified by the A-phase occurrence, and this information could help to conceptualize the CAP phenomenon from a new perspective based on the sharpness of the EEG instead of the oscillatory way.

The Effects of a Visual Stimuli Training Program on Reaction Time, Cognitive Function, and Fitness in Young Soccer Players

The purpose of the present study was to examine whether a visual stimuli program during soccer training can affect reaction time (RT), cognitive function, and physical fitness in adolescent soccer players. Thirty-eight male soccer players aged 10−15 were randomly assigned to either the intervention (Group A) or the control group (Group B). At baseline and at the end of the 6-month study FITLIGHT Trainer, the Cognitive Function Scanner Mobile Test Suite, a Virtual Reality (VR) game, and the ALPHA—Fitness and the Eurofit test batteries were used to measure participants’ abilities. After the baseline assessment, Group A followed their regular soccer training combined with a visual stimuli program, while Group B continued their regular soccer training program alone for 6 months. At the end of the 6-month study, Group A showed statistically significant improvements in simple RT by 11.8% (p = 0.002), repeated sprints by 13.4% (p ≤ 0.001), and Pen-to-Point Cognitive Function by 71.62% (p < 0.001) and 72.51% for dominant and non-dominant hands, respectively. However, a between-groups analysis showed that there was no statistically significant difference between the two groups in most of the measurements studied. In conclusion, a visual stimuli training program does not seem to add any value to the traditional soccer training program for adolescents. Nevertheless, this study helps to underline the potential of newly emerging technology as a tool for the assessment of RT.

Data Quality Check in Cancer Imaging Research: Deploying and Evaluating the DIQCT Tool

Data harmonization is one of the greatest challenges in cancer imaging studies, especially when it comes to multi-source data provision. Properly integrated data deriving from various sources can ensure data fairness on one side and can lead to a trusted dataset that will enhance AI engine development on the other side. Towards this direction, we are presenting a data integration quality check tool that ensures that all data uploaded to the repository are homogenized and share the same principles. The tool's aim is to report any human-induced errors and propose corrective actions. It focuses on checking the data prior to their upload to the repository in five levels: (i) clinical metadata integrity, (ii) template-imaging consistency, (iii) anonymization protocol applied, (iv) imaging analysis requirements, (v) case completeness. The tool produces reports with the corrective actions that must be followed by the user. This way the tool ensures that the data that will become available to the developers of the AI engine are homogenized, properly structured and contain all the necessary information needed for the analysis. The tool was validated in two rounds, internal and external, and at the user experience level. Clinical Relevance- Supporting the harmonized preparation and provision of medical imaging data and related clinical data will ensure data fairness and enhance the AI development.

Position of the AI for Health Imaging (AI4HI) network on metadata models for imaging biobanks

A huge amount of imaging data is becoming available worldwide and an incredible range of possible improvements can be provided by artificial intelligence algorithms in clinical care for diagnosis and decision support. In this context, it has become essential to properly manage and handle these medical images and to define which metadata have to be considered, in order for the images to provide their full potential. Metadata are additional data associated with the images, which provide a complete description of the image acquisition, curation, analysis, and of the relevant clinical variables associated with the images. Currently, several data models are available to describe one or more subcategories of metadata, but a unique, common, and standard data model capable of fully representing the heterogeneity of medical metadata has not been yet developed. This paper reports the state of the art on metadata models for medical imaging, the current limitations and further developments, and describes the strategy adopted by the Horizon 2020 "AI for Health Imaging" projects, which are all dedicated to the creation of imaging biobanks.

Diagnosis of Alzheimer's disease and Mild Cognitive Impairment using EEG and Recurrent Neural Networks

Alzheimer's disease (AD) is the main cause of dementia and Mild cognitive impairment (MCI) is a prodromal stage of AD whose early detection is considered crucial as it can contribute in slowing the progression of AD. In our study we attempted to classify a subject into AD, MCI, or Healthy Control (HC) groups with the use of electroencephalogram (EEG) data. Due to the time-series nature of EEG we exper-imented with the powerful recurrent neural network (RNN) classifiers and more specifically with models including basic or bidirectional Long Short-Term Memory (LSTM) modules. The EEG signals from 17 channels were preprocessed using a 0.1-32 Hz band-pass filter and then segmented into 2-second epochs during which, the subject had closed eyes. Finally, on each segment Fast Fourier Transform (FFT) was applied. To evaluate our models we studied four different classification problems: problem 1: separating subject into three classes (HC, MCI, AD) and problems 2-4: pairwise classifications AD vs. MCI, AD vs. HC and MCI vs. HC. For each problem we employed two different cross-validation approaches ( a) by segment and (b) by patient. In the first one, segments from a subject EEG may exist in both training and validations set, while in the second one, all the EEG segments of a subject can only exist in either the training or the validation set. In the AD-MCI-HC classification we achieved an accuracy of 99% by segment cross-validation, which was an improvement to earlier studies that utilized recurrent neural network models. In the pairwise classification problems we achieved over 90% accuracy by segment and over 80% by subject.

P-Wave Beat-to-Beat Analysis to Predict Atrial Fibrillation Recurrence after Catheter Ablation

The identification of patients prone to atrial fibrillation (AF) relapse after catheter ablation is essential for better patient selection and risk stratification. The current prospective cohort study aims to validate a novel P-wave index based on beat-to-beat (B2B) P-wave morphological and wavelet analysis designed to detect patients with low burden AF as a predictor of AF recurrence within a year after successful catheter ablation. From a total of 138 consecutive patients scheduled for AF ablation, 12-lead ECG and 10 min vectorcardiogram (VCG) recordings were obtained. Univariate analysis revealed that patients with higher B2B P-wave index had a two-fold risk for AF recurrence (HR: 2.35, 95% CI: 1.24–4.44, p: 0.010), along with prolonged P-wave, interatrial block, early AF recurrence, female gender, heart failure history, previous stroke, and CHA₂DS₂-VASc score. Multivariate analysis of assessable predictors before ablation revealed that B2B P-wave index, along with heart failure history and a history of previous stroke or transient ischemic attack, are independent predicting factors of atrial fibrillation recurrence. Further studies are needed to assess the predictive value of the B2B index with greater accuracy and evaluate a possible relationship with atrial substrate analysis.

Combining Machine Learning and Network Analysis Pipelines: The Case of Microbiome and Metabolomics Data in Colorectal Cancer

This study analyzes samples of intestinal microbiome and metabolites, from healthy individuals (HE) and patients with adenomas (AD) or colorectal carcinomas (CRC). A network analysis (NetAn) method was applied to the data, to identify the metabolites and microbial genera associated with the 3 classes and then 7 classification models were used. The models were initially trained with classic feature selection vs features resulting from NetAn. The distinction of HE and AD is successful, while CRC distinction presented lower success.

Towards Data Integration for AI in Cancer Research. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:2054-2057. [PMID: 34891692 DOI: 10.1109/embc46164.2021.9629675]

Cancer research is increasing relying on data-driven methods and Artificial Intelligence (AI), to increase accuracy and efficiency in decision making. Such methods can solve a variety of clinically relevant problems in cancer diagnosis and treatment, provided that an adequate data availability is ensured. The generation of multicentric data repositories poses a series of integration and harmonization challenges. This work discusses the strategy, solutions and further issues identified along this procedure within the EU project INCISIVE that aims to generate an interoperable pan-European federated repository of medical images and an AI-based toolbox for medical imaging in cancer diagnosis and treatment.Clinical Relevance- Supporting the integration of medical imaging data and related clinical data into large interoperable repositories will enable the development, and validation, and wider adoption of AI-based methods in cancer diagnosis, prediction, treatment and follow-up.

Beat-to-beat P-wave analysis outperforms conventional P-wave indices in identifying patients with a history of paroxysmal atrial fibrillation, during sinus rhythm

Introduction

Atrial fibrillation (AF) is the most common arrhythmia and is associated with high risk of morbidity and mortality. In many patients, AF is of episodic character (paroxysmal AF – PAF), which makes the identification of these patients during sinus rhythm (SR) challenging.

Purpose

The aim of the present study is to compare the performance of beat-to-beat P-wave analysis with P-wave indices used as predictors of PAF, such as P-wave duration, area, voltage, axis, terminal force in V1, inter-atrial block or orthogonal type, in identifying patients with history of PAF during sinus rhythm.

Methods

Standard 12-lead ECG and 10-minute orthogonal ECG recordings were obtained from 40 consecutive patients with short history of PAF under no antiarrhythmic medication and 60 age- and sex- matched healthy controls. The P-waves on the 10-minute recordings were analyzed on a beat-to-beat basis and classified as belonging to a primary or secondary morphology according to previous study. Wavelet transform used to further analyze P-wave orthogonal signals of main morphology on a beat-to-beat basis.

Results

38 out of 327 studied features were found to differ significantly among the two groups. These features were tested for their diagnostic ability and receiver operating characteristic curves were ploted. Only 3 of them performed adequetly, with an area under curve (AUC) above 0.65; Two of them came from morphology analysis (percentage of beats following main morphology in axis X and Y) and one from wavelet analysis (max energy in high frequency zone -Y axis). Among standard P-wave indices, P-wave area in lead II was the one with the highest AUC (0.64).

Conclusion

Novel indices derived from beat-to-beat analysis outperform stadard P-wave markers in identifying patients with PAF history during sinus rhythm.

Funding Acknowledgement

Type of funding sources: None. ROC curves of most significant featuresAUC characteristics of P-wave indices

Network analysis with biological data of cancer patients: A scoping review

BACKGROUND & OBJECTIVE

Network Analysis (NA) is a mathematical method that allows exploring relations between units and representing them as a graph. Although NA was initially related to social sciences, the past two decades was introduced in Bioinformatics. The recent growth of the networks' use in biological data analysis reveals the need to further investigate this area. In this work, we attempt to identify the use of NA with biological data, and specifically: (a) what types of data are used and whether they are integrated or not, (b) what is the purpose of this analysis, predictive or descriptive, and (c) the outcome of such analyses, specifically in cancer diseases.

METHODS & MATERIALS

The literature review was conducted on two databases, PubMed & IEEE, and was restricted to journal articles of the last decade (January 2010 - December 2019). At a first level, all articles were screened by title and abstract, and at a second level the screening was conducted by reading the full text article, following the predefined inclusion & exclusion criteria leading to 131 articles of interest. A table was created with the information of interest and was used for the classification of the articles. The articles were initially classified to analysis studies and studies that propose a new algorithm or methodology. Each one of these categories was further screened by the following clustering criteria: (a) data used, (b) study purpose, (c) study outcome. Specifically for the studies proposing a new algorithm, the novelty presented in each one was detected.

RESULTS

& Conclusions: In the past five years researchers are focusing on creating new algorithms and methodologies to enhance this field. The articles' classification revealed that only 25% of the analyses are integrating multi-omics data, although 50% of the new algorithms developed follow this integrative direction. Moreover, only 20% of the analyses and 10% of the newly developed methodologies have a predictive purpose. Regarding the result of the works reviewed, 75% of the studies focus on identifying, prognostic or not, gene signatures. Concluding, this review revealed the need for deploying predictive and multi-omics integrative algorithms and methodologies that can be used to enhance cancer diagnosis, prognosis and treatment.

P-wave beat-to-beat morphology analysis outperforms conventional P-wave indices in detecting patients with paroxysmal atrial fibrillation

Funding Acknowledgements

Type of funding sources: None.

Background

Atrial fibrillation (AF) - the most common sustained cardiac arrhythmia - while not a life-threatening condition itself, leads to an increased risk of stroke and high rates of mortality. Early detection and diagnosis of AF is a critical issue for all health stakeholders.

Purpose

The aim of this study is to compare the performance of standard P-wave indices with beat-to-beat P-wave morphological variability parameters in identifying patients with history of Paroxysmal Atrial Fibrillation (PAF).

Methods

Three-dimensional 1000Hz ECG digital recordings of 10 minutes duration were obtained from a total of 39 PAF patients and 60 healthy individuals. Following artifacts and ectopic beats removal, P‑wave morphology analysis was performed based on the dynamic application of the k‑means clustering process and main and secondary P-wave morphologies were identified. The percentage of P-waves following the main or the secondary morphology in each lead was calculated, as well as established indices such as Advanced Interatrial Block, P-wave duration, axis and area, P-wave Terminal Force in lead V1 and Orthogonal Leads Type 1, 2 or 3.

Results

9 out of 24 parameters studied, were found to be significantly different between the two groups. 7 of these indices were derived from morphology analysis and 2 from P-wave area. Logistic regression revealed that the percentage of P-waves allocated to main morphology in X axis performed better than all other indices in identifying patients with PAF history from healthy volunteers in terms of total accuracy and F1 measure.

Conclusion

P-wave beat-to-beat morphology analysis can identify PAF patients during normal sinus rhythm more efficiently than standard P-wave indices. Abstract Figure.

An Early Stage Researcher's Primer on Systems Medicine Terminology

Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic.

Serious Gaming Technology in Upper Extremity Rehabilitation: Scoping Review

Background

Serious gaming has increasingly gained attention as a potential new component in clinical practice. Specifically, its use in the rehabilitation of motor dysfunctions has been intensively researched during the past three decades.

Objective

The aim of this scoping review was to evaluate the current role of serious games in upper extremity rehabilitation, and to identify common methods and practice as well as technology patterns. This objective was approached via the exploration of published research efforts over time.

Methods

The literature search, using the PubMed and Scopus databases, included articles published from 1999 to 2019. The eligibility criteria were (i) any form of game-based arm rehabilitation; (ii) published in a peer-reviewed journal or conference; (iii) introduce a game in an electronic format; (iv) published in English; and (v) not a review, meta-analysis, or conference abstract. The search strategy identified 169 relevant articles.

Results

The results indicated an increasing research trend in the domain of serious gaming deployment in upper extremity rehabilitation. Furthermore, differences regarding the number of publications and the game approach were noted between studies that used commercial devices in their rehabilitation systems and those that proposed a custom-made robotic arm, glove, or other devices for the connection and interaction with the game platform. A particularly relevant observation concerns the evaluation of the introduced systems. Although one-third of the studies evaluated their implementations with patients, in most cases, there is the need for a larger number of participants and better testing of the rehabilitation scheme efficiency over time. Most of the studies that included some form of assessment for the introduced rehabilitation game mentioned user experience as one of the factors considered for evaluation of the system. Besides user experience assessment, the most common evaluation method involving patients was the use of standard medical tests. Finally, a few studies attempted to extract game features to introduce quantitative measurements for the evaluation of patient improvement.

Conclusions

This paper presents an overview of a significant research topic and highlights the current state of the field. Despite extensive attempts for the development of gamified rehabilitation systems, there is no definite answer as to whether a serious game is a favorable means for upper extremity functionality improvement; however, this certainly constitutes a supplementary means for motivation. The development of a unified performance quantification framework and more extensive experiments could generate richer evidence and contribute toward this direction.

Challenges and opportunities for telehealth in the management of chronic obstructive pulmonary disease: a qualitative case study in Greece

BACKGROUND

Telehealth (TH) was introduced as a promising tool to support integrated care for the management of chronic obstructive pulmonary disease (COPD). It aims at improving self-management and providing remote support for continuous disease management. However, it is often not clear how TH-supported services fit into existing pathways for COPD management. The objective of this study is to uncover where TH can successfully contribute to providing care for COPD patients exemplified in a Greek care pathway. The secondary objective is to identify what conditions need to be considered for successful implementation of TH services.

METHODS

Building on a single case study, we used a two-phase approach to identify areas in a Greek COPD care pathway where care services that are recommended in clinical guidelines are currently not implemented (challenges) and areas that are not explicitly recommended in the guidelines but that would benefit from TH services (opportunities). In phase I, we used the care delivery value chain framework to identify the divergence between the clinical guidelines and the actual practice captured by a survey with COPD healthcare professionals. In phase II, we conducted in-depth interviews with the same healthcare professionals based on the discovered divergences. The responses were analyzed with respect to identified opportunities for TH and care pathway challenges.

RESULTS

Our results reveal insights in two areas. First, several areas with challenges were identified: patient education, self-management, medication adherence, physical activity, and comorbidity management. TH opportunities were perceived as offering better bi-directional communication and a tool for reassuring patients. Second, considering the identified challenges and opportunities together with other case context details a set of conditions was extracted that should be fulfilled to implement TH successfully.

CONCLUSIONS

The results of this case study provide detailed insights into a care pathway for COPD in Greece. Addressing the identified challenges and opportunities in this pathway is crucial for adopting and implementing service innovations. Therefore, this study contributes to a better understanding of requirements for the successful implementation of integrated TH services in the field of COPD management. Consequently, it may encourage healthcare professionals to implement TH-supported services as part of routine COPD management.