Concept-drifts adaptation for machine learning EEG epilepsy seizure prediction

Seizure prediction remains a challenge, with approximately 30% of patients unresponsive to conventional treatments. Addressing this issue is crucial for improving patients' quality of life, as timely intervention can mitigate the impact of seizures. In this research field, it is critical to identify the preictal interval, the transition from regular brain activity to a seizure. While previous studies have explored various Electroencephalogram (EEG) based methodologies for prediction, few have been clinically applicable. Recent studies have underlined the dynamic nature of EEG data, characterised by data changes with time, known as concept drifts, highlighting the need for automated methods to detect and adapt to these changes. In this study, we investigate the effectiveness of automatic concept drift adaptation methods in seizure prediction. Three patient-specific seizure prediction approaches with a 10-minute prediction horizon are compared: a seizure prediction algorithm incorporating a window adjustment method by optimising performance with Support Vector Machines (Backwards-Landmark Window), a seizure prediction algorithm incorporating a data-batch (seizures) selection method using a logistic regression (Seizure-batch Regression), and a seizure prediction algorithm with a dynamic integration of classifiers (Dynamic Weighted Ensemble). These methods incorporate a retraining process after each seizure and use a combination of univariate linear features and SVM classifiers. The Firing Power was used as a post-processing technique to generate alarms before seizures. These methodologies were compared with a control approach based on the typical machine learning pipeline, considering a group of 37 patients with Temporal Lobe Epilepsy from the EPILEPSIAE database. The best-performing approach (Backwards-Landmark Window) achieved results of 0.75 ± 0.33 for sensitivity and 1.03 ± 1.00 for false positive rate per hour. This new strategy performed above chance for 89% of patients with the surrogate predictor, whereas the control approach only validated 46%.

EEG as a potential ground truth for the assessment of cognitive state in software development activities: A multimodal imaging study

Cognitive human error and recent cognitive taxonomy on human error causes of software defects support the intuitive idea that, for instance, mental overload, attention slips, and working memory overload are important human causes for software bugs. In this paper, we approach the EEG as a reliable surrogate to MRI-based reference of the programmer's cognitive state to be used in situations where heavy imaging techniques are infeasible. The idea is to use EEG biomarkers to validate other less intrusive physiological measures, that can be easily recorded by wearable devices and useful in the assessment of the developer's cognitive state during software development tasks. Herein, our EEG study, with the support of fMRI, presents an extensive and systematic analysis by inspecting metrics and extracting relevant information about the most robust features, best EEG channels and the best hemodynamic time delay in the context of software development tasks. From the EEG-fMRI similarity analysis performed, we found significant correlations between a subset of EEG features and the Insula region of the brain, which has been reported as a region highly related to high cognitive tasks, such as software development tasks. We concluded that despite a clear inter-subject variability of the best EEG features and hemodynamic time delay used, the most robust and predominant EEG features, across all the subjects, are related to the Hjorth parameter Activity and Total Power features, from the EEG channels F4, FC4 and C4, and considering in most of the cases a hemodynamic time delay of 4 seconds used on the hemodynamic response function. These findings should be taken into account in future EEG-fMRI studies in the context of software debugging.

Comparison between epileptic seizure prediction and forecasting based on machine learning

Epilepsy affects around 1% of the population worldwide. Anti-epileptic drugs are an excellent option for controlling seizure occurrence but do not work for around one-third of patients. Warning devices employing seizure prediction or forecasting algorithms could bring patients new-found comfort and quality of life. These algorithms would attempt to detect a seizure's preictal period, a transitional moment between regular brain activity and the seizure, and relay this information to the user. Over the years, many seizure prediction studies using Electroencephalogram-based methodologies have been developed, triggering an alarm when detecting the preictal period. Recent studies have suggested a shift in view from prediction to forecasting. Seizure forecasting takes a probabilistic approach to the problem in question instead of the crisp approach of seizure prediction. In this field of study, the triggered alarm to symbolize the detection of a preictal period is substituted by a constant risk assessment analysis. The present work aims to explore methodologies capable of seizure forecasting and establish a comparison with seizure prediction results. Using 40 patients from the EPILEPSIAE database, we developed several patient-specific prediction and forecasting algorithms with different classifiers (a Logistic Regression, a 15 Support Vector Machines ensemble, and a 15 Shallow Neural Networks ensemble). Results show an increase of the seizure sensitivity in forecasting relative to prediction of up to 146% and in the number of patients that displayed an improvement over chance of up to 300%. These results suggest that a seizure forecasting methodology may be more suitable for seizure warning devices than a seizure prediction one.

EEG epilepsy seizure prediction: the post-processing stage as a chronology

Almost one-third of epileptic patients fail to achieve seizure control through anti-epileptic drug administration. In the scarcity of completely controlling a patient's epilepsy, seizure prediction plays a significant role in clinical management and providing new therapeutic options such as warning or intervention devices. Seizure prediction algorithms aim to identify the preictal period that Electroencephalogram (EEG) signals can capture. However, this period is associated with substantial heterogeneity, varying among patients or even between seizures from the same patient. The present work proposes a patient-specific seizure prediction algorithm using post-processing techniques to explore the existence of a set of chronological events of brain activity that precedes epileptic seizures. The study was conducted with 37 patients with Temporal Lobe Epilepsy (TLE) from the EPILEPSIAE database. The designed methodology combines univariate linear features with a classifier based on Support Vector Machines (SVM) and two post-processing techniques to handle pre-seizure temporality in an easily explainable way, employing knowledge from network theory. In the Chronological Firing Power approach, we considered the preictal as a sequence of three brain activity events separated in time. In the Cumulative Firing Power approach, we assumed the preictal period as a sequence of three overlapping events. These methodologies were compared with a control approach based on the typical machine learning pipeline. We considered a Seizure Prediction horizon (SPH) of 5 mins and analyzed several values for the Seizure Occurrence Period (SOP) duration, between 10 and 55 mins. Our results showed that the Cumulative Firing Power approach may improve the seizure prediction performance. This new strategy performed above chance for 62% of patients, whereas the control approach only validated 49% of its models.

Computational methods applied to syphilis: where are we, and where are we going?

Syphilis is an infectious disease that can be diagnosed and treated cheaply. Despite being a curable condition, the syphilis rate is increasing worldwide. In this sense, computational methods can analyze data and assist managers in formulating new public policies for preventing and controlling sexually transmitted infections (STIs). Computational techniques can integrate knowledge from experiences and, through an inference mechanism, apply conditions to a database that seeks to explain data behavior. This systematic review analyzed studies that use computational methods to establish or improve syphilis-related aspects. Our review shows the usefulness of computational tools to promote the overall understanding of syphilis, a global problem, to guide public policy and practice, to target better public health interventions such as surveillance and prevention, health service delivery, and the optimal use of diagnostic tools. The review was conducted according to PRISMA 2020 Statement and used several quality criteria to include studies. The publications chosen to compose this review were gathered from Science Direct, Web of Science, Springer, Scopus, ACM Digital Library, and PubMed databases. Then, studies published between 2015 and 2022 were selected. The review identified 1,991 studies. After applying inclusion, exclusion, and study quality assessment criteria, 26 primary studies were included in the final analysis. The results show different computational approaches, including countless Machine Learning algorithmic models, and three sub-areas of application in the context of syphilis: surveillance (61.54%), diagnosis (34.62%), and health policy evaluation (3.85%). These computational approaches are promising and capable of being tools to support syphilis control and surveillance actions.

Digital Alternative Communication for Individuals with Amyotrophic Lateral Sclerosis: What We Have

Amyotrophic Lateral Sclerosis is a disease that compromises the motor system and the functional abilities of the person in an irreversible way, causing the progressive loss of the ability to communicate. Tools based on Augmentative and Alternative Communication are essential for promoting autonomy and improving communication, life quality, and survival. This Systematic Literature Review aimed to provide evidence on eye-image-based Human-Computer Interaction approaches for the Augmentative and Alternative Communication of people with Amyotrophic Lateral Sclerosis. The Systematic Literature Review was conducted and guided following a protocol consisting of search questions, inclusion and exclusion criteria, and quality assessment, to select primary studies published between 2010 and 2021 in six repositories: Science Direct, Web of Science, Springer, IEEE Xplore, ACM Digital Library, and PubMed. After the screening, 25 primary studies were evaluated. These studies showcased four low-cost, non-invasive Human-Computer Interaction strategies employed for Augmentative and Alternative Communication in people with Amyotrophic Lateral Sclerosis. The strategies included Eye-Gaze, which featured in 36% of the studies; Eye-Blink and Eye-Tracking, each accounting for 28% of the approaches; and the Hybrid strategy, employed in 8% of the studies. For these approaches, several computational techniques were identified. For a better understanding, a workflow containing the development phases and the respective methods used by each strategy was generated. The results indicate the possibility and feasibility of developing Human-Computer Interaction resources based on eye images for Augmentative and Alternative Communication in a control group. The absence of experimental testing in people with Amyotrophic Lateral Sclerosis reiterates the challenges related to the scalability, efficiency, and usability of these technologies for people with the disease. Although challenges still exist, the findings represent important advances in the fields of health sciences and technology, promoting a promising future with possibilities for better life quality.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

On the accuracy of code complexity metrics: A neuroscience-based guideline for improvement

Complexity is the key element of software quality. This article investigates the problem of measuring code complexity and discusses the results of a controlled experiment to compare different views and methods to measure code complexity. Participants (27 programmers) were asked to read and (try to) understand a set of programs, while the complexity of such programs is assessed through different methods and perspectives: (a) classic code complexity metrics such as McCabe and Halstead metrics, (b) cognitive complexity metrics based on scored code constructs, (c) cognitive complexity metrics from state-of-the-art tools such as SonarQube, (d) human-centered metrics relying on the direct assessment of programmers' behavioral features (e.g., reading time, and revisits) using eye tracking, and (e) cognitive load/mental effort assessed using electroencephalography (EEG). The human-centered perspective was complemented by the subjective evaluation of participants on the mental effort required to understand the programs using the NASA Task Load Index (TLX). Additionally, the evaluation of the code complexity is measured at both the program level and, whenever possible, at the very low level of code constructs/code regions, to identify the actual code elements and the code context that may trigger a complexity surge in the programmers' perception of code comprehension difficulty. The programmers' cognitive load measured using EEG was used as a reference to evaluate how the different metrics can express the (human) difficulty in comprehending the code. Extensive experimental results show that popular metrics such as V(g) and the complexity metric from SonarSource tools deviate considerably from the programmers' perception of code complexity and often do not show the expected monotonic behavior. The article summarizes the findings in a set of guidelines to improve existing code complexity metrics, particularly state-of-the-art metrics such as cognitive complexity from SonarSource tools.

Similarity Analysis in Understanding Online News in Response to Public Health Crisis

BACKGROUND

The "Syphilis No!" campaign the Brazilian Ministry of Health (MoH) launched between November 2018 and March 2019, brought forward the concept "Test, Treat and Cure" to remind the population of the importance of syphilis prevention. In this context, this study aims to analyze the similarity of syphilis online news to comprehend how public health communication interventions influence media coverage of the syphilis issue.

METHODS

This paper presented a computational approach to assess the effectiveness of communication actions on a public health problem. Data were collected between January 2015 and December 2019 and processed using the Hermes ecosystem, which utilizes text mining and machine learning algorithms to cluster similar content.

RESULTS

Hermes identified 1049 google-indexed web pages containing the term 'syphilis' in Brazil. Of these, 619 were categorized as news stories. In total, 157 were grouped into clusters of at least two similar news items and a single cluster with 462 news classified as "single" for not featuring similar news items. From these, 19 clusters were identified in the pre-campaign period, 23 during the campaign, and 115 in the post-campaign.

CONCLUSIONS

The findings presented in this study show that the volume of syphilis-related news reports has increased in recent years and gained popularity after the SNP started, having been boosted during the campaign and escalating even after its completion.

Patient reported outcomes for phosphomannomutase 2 congenital disorder of glycosylation (PMM2-CDG): listening to what matters for the patients and health professionals

Background

Congenital disorders of glycosylation (CDG) are a growing group of rare genetic disorders. The most common CDG is phosphomannomutase 2 (PMM2)-CDG which often has a severe clinical presentation and life-limiting consequences. There are no approved therapies for this condition. Also, there are no validated disease-specific quality of life (QoL) scales to assess the heterogeneous clinical burden of PMM2-CDG which presents a challenge for the assessment of the disease severity and the impact of a certain treatment on the course of the disease.

Aim and methods

This study aimed to identify the most impactful clinical signs and symptoms of PMM2-CDG, and specific patient and observer reported outcome measures (PROMs and ObsROMs, respectively) that can adequately measure such impact on patients’ QoL. The most burdensome signs and symptoms were identified through input from the CDG community using a survey targeting PMM2-CDG families and experts, followed by family interviews to understand the real burden of these symptoms in daily life. The list of signs and symptoms was then verified and refined by patient representatives and medical experts in the field. Finally, a literature search for PROMs and ObsROMs used in other rare or common diseases with similar signs and symptoms to those of PMM2-CDG was performed.

Results

Twenty-four signs/symptoms were identified as the most impactful throughout PMM2-CDG patients’ lifetime. We found 239 articles that included tools to measure those community-selected PMM2-CDG symptoms. Among them, we identified 80 QoL scales that address those signs and symptoms and, subsequently, their psychometric quality was analysed. These scales could be applied directly to the PMM2-CDG population or adapted to create the first PMM2-CDG-specific QoL questionnaire.

Conclusion

Identifying the impactful clinical manifestations of PMM2-CDG, along with the collection of PROMs/ObsROMs assessing QoL using a creative and community-centric methodology are the first step towards the development of a new, tailored, and specific PMM2-CDG QoL questionnaire. These findings can be used to fill a gap in PMM2-CDG clinical development. Importantly, this methodology is transferable to other CDG and rare diseases with multiple signs and symptoms.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13023-022-02551-y.

Maternal care experience and postpartum depressive symptoms among migrant and native in Portugal

Background

Migration is a risk factor for both, poor maternal experience with healthcare services (MEHCS) and postpartum depressive symptoms (PPDS), a matter of concern due to their adverse consequences. We aimed to assess the association between MEHCS and PPDS taking into account the migration status.

Methods

This is part of a population-based study (baMBINO project), enrolling native (PT; n = 1568), permanent migrant (PM; n = 676) and temporary migrant (TM; n = 757) women recruited at delivery (2017-2019) in 32 Portuguese public hospitals. MEHCS was assessed based on 39 items of the Migrant Friendly Maternal Care Questionnaire asking about how women have experienced maternal care during pregnancy, during delivery and after birth. Items were grouped into 9 components each one assessing a different issue of MEHCS. For each component women were classified as having “good” or “less than good” experience. PPDS were assessed using the Edinburgh Postnatal Depression Scale (cut-off≥12). Multivariate logistic regression model was fitted to estimate the association between MEHCS and PPDS. Adjusted odds ratio (aOR) and respective 95% confidence interval were obtained.

Results

PPDS were reported by 3.8%, 5.8% and 8.2% of PT, PM and TM women, respectively (p < 0.001). After adjustment, 4 out 9 components of MEHCS appeared related with PPDS, such that women reporting less than good experience with “understanding information” (aOR=1.72 95%CI:1.14-2.60), “decisions according to maternal wishes” (aOR=1.56 95% CI:1.04-2.34), “time waiting for healthcare” (aOR=1.50 95%CI:1.04-2.18) and “healthcare provider's attitudes during pregnancy” (aOR=1.58 95%CI:1.01-2.47) showed higher odds of PPDS than women reporting good experience.

Conclusions

Further than the migration status, poor experience with some issues of maternal care seems play a role in the risk of PPDS

Key messages

How Reliable Are Ultra-Short-Term HRV Measurements during Cognitively Demanding Tasks?

Ultra-short-term HRV features assess minor autonomous nervous system variations such as variations resulting from cognitive stress peaks during demanding tasks. Several studies compare ultra-short-term and short-term HRV measurements to investigate their reliability. However, existing experiments are conducted in low cognitively demanding environments. In this paper, we propose to evaluate these measurements' reliability under cognitively demanding tasks using a near real-life setting. For this purpose, we selected 31 HRV features, extracted from data collected from 21 programmers performing code comprehension, and compared them across 18 different time frames, ranging from 3 min to 10 s. Statistical significance and correlation tests were performed between the features extracted using the larger window (3 min) and the same features extracted with the other 17 time frames. We paired these analyses with Bland-Altman plots to inspect how the extraction window size affects the HRV features. The main results show 13 features that presented at least 50% correlation when using 60-second windows. The HF and mNN features achieved around 50% correlation using a 30-second window. The 30-second window was the smallest time frame considered to have reliable measurements. Furthermore, the mNN feature proved to be quite robust to the shortening of the time resolution.

EPIC: Annotated epileptic EEG independent components for artifact reduction

Scalp electroencephalogram is a non-invasive multi-channel biosignal that records the brain’s electrical activity. It is highly susceptible to noise that might overshadow important data. Independent component analysis is one of the most used artifact removal methods. Independent component analysis separates data into different components, although it can not automatically reject the noisy ones. Therefore, experts are needed to decide which components must be removed before reconstructing the data. To automate this method, researchers have developed classifiers to identify noisy components. However, to build these classifiers, they need annotated data. Manually classifying independent components is a time-consuming task. Furthermore, few labelled data are publicly available. This paper presents a source of annotated electroencephalogram independent components acquired from patients with epilepsy (EPIC Dataset). This dataset contains 77,426 independent components obtained from approximately 613 hours of electroencephalogram, visually inspected by two experts, which was already successfully utilised to develop independent component classifiers.

Measurement(s)	Electroencephalogram Independent Components
Technology Type(s)	MATLAB and Python

Hemostasis of the radial artery after coronary angiography: a scoping review

Funding Acknowledgements

Type of funding sources: None.

Background/Introduction

Nowadays, most interventional cardiology procedures are made via radial artery. There is significant variability of haemostasis methods, devices, and protocols. All of them try to avoid radial artery occlusion while maintaining patent haemostasis. Summarizing the available evidence about haemostasis of the radial artery after coronary angiography will allow us to challenge our current practice.

Purpose

The focus of this scoping review is to map the literature on haemostasis of the radial artery after coronary angiography. To date, no previous reviews addressing this purpose have been found.

Methods

This review follows the Joanna Briggs Institute methodology for scoping reviews. Two reviewers will independently perform the study selection regarding their eligibility. Data extraction will be accomplished using a researcher's developed tool to address the objectives and reviews questions. Any disagreements arisen between the reviewers will be resolved by discussion or consulting a third reviewer. Data synthesis will be presented in tabular form and a narrative summary that align with the review's objective. Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension to scoping reviews guidelines will be used to report the results. A set of relevant electronic databases and grey literature will be searched.

Results

Twenty-four studies were included, of various types: randomized clinical trials, case-reports, case series, narrative reviews. Three methods were described: compression devices, compression band and haemostatic patch. Sometimes more than one method is used, and there are various protocols that vary according to the institutional practice.

Conclusion

There are multiple radial artery haemostasis methods and protocols currently in use after a coronary angiography with no method overwhelmingly predominant. Few were associated with clearly defined haemostasis protocols, even though these protocols exist, often associated with compression devices. The institutional practice plays a decisive role on the use and modification of these protocols, with no clear evidence to support it. Such variability in protocols might have a detrimental effect in having a standardized one that can be used across various institutions/countries, facilitating broader multicentric studies.

Automatic segmentation and classification of mice ultrasonic vocalizations

This paper addresses the development of a system for classifying mouse ultrasonic vocalizations (USVs) present in audio recordings. The automatic labeling process for USVs is usually divided into two main steps: USV segmentation followed by the matching classification. Three main contributions can be highlighted: (i) a new segmentation algorithm, (ii) a new set of features, and (iii) the discrimination of a higher number of classes when compared to similar studies. The developed segmentation algorithm is based on spectral entropy analysis. This novel segmentation approach can detect USVs with 94% and 74% recall and precision, respectively. When compared to other methods/software, our segmentation algorithm achieves a higher recall. Regarding the classification phase, besides the traditional features from time, frequency, and time-frequency domains, a new set of contour-based features were extracted and used as inputs of shallow machine learning classification models. The contour-based features were obtained from the time-frequency ridge representation of USVs. The classification methods can differentiate among ten different syllable types with 81.1% accuracy and 80.5% weighted F1-score. The algorithms were developed and evaluated based on a large dataset, acquired on diverse social interaction conditions between the animals, to stimulate a varied vocal repertoire.

Lactiplantibacillus plantarum 299v (LP299V®): three decades of research

This review aims to provide a comprehensive overview of the in vitro, animal, and clinical studies with the bacterial strain Lactiplantibacillus plantarum 299v (L. plantarum 299v; formerly named Lactobacillus plantarum 299v) published up until June 30, 2020. L. plantarum 299v is the most documented L. plantarum strain in the world, described in over 170 scientific publications out of which more than 60 are human clinical studies. The genome sequence of L. plantarum 299v has been determined and is available in the public domain (GenBank Accession number: NZ_LEAV01000004). The probiotic strain L. plantarum 299v was isolated from healthy human intestinal mucosa three decades ago by scientists at Lund University, Sweden. Thirty years later, a wealth of data coming from in vitro, animal, and clinical studies exist, showing benefits primarily for gastrointestinal health, such as reduced flatulence and abdominal pain in patients with irritable bowel syndrome (IBS). Moreover, several clinical studies have shown positive effects of L. plantarum 299v on iron absorption and more recently also on iron status. L. plantarum 299v is safe for human consumption and does not confer antibiotic resistance. It survives the harsh conditions of the human gastrointestinal tract, adheres to mannose residues on the intestinal epithelial cells and has in some cases been re-isolated more than ten days after administration ceased. Besides studying health benefits, research groups around the globe have investigated L. plantarum 299v in a range of applications and processes. L. plantarum 299v is used in many different food applications as well as in various dietary supplements. In a freeze-dried format, L. plantarum 299v is robust and stable at room temperature, enabling long shelf-lives of consumer healthcare products such as capsules, tablets, or powder sachets. The strain is patent protected for a wide range of indications and applications worldwide as well as trademarked as LP299V^®.

National registry for amyotrophic lateral sclerosis: a systematic review for structuring population registries of motor neuron diseases

BACKGROUND

This article comprises a systematic review of the literature that aims at researching and analyzing the frequently applied guidelines for structuring national databases of epidemiological surveillance for motor neuron diseases, especially Amyotrophic Lateral Sclerosis (ALS).

METHODS

We searched for articles published from January 2015 to September 2019 on online databases as PubMed - U.S. National Institutes of Health's National Library of Medicine, Scopus, Science Direct, and Springer. Subsequently, we analyzed studies that considered risk factors, demographic data, and other strategic data for directing techno-scientific research, calibrating public health policies, and supporting decision-making by managers through a systemic panorama of ALS.

RESULTS

2850 studies were identified. 2400 were discarded for not satisfying the inclusion criteria, and 435 being duplicated or published in books or conferences. Hence, 15 articles were elected. By applying quality criteria, we then selected six studies to compose this review. Such researches featured registries from the American (3), European (2), and Oceania (1) continent. All the studies specified the methods for data capture and the patients' recruitment process for the registers.

DISCUSSIONS

From the analysis of the selected papers and reported models, it is noticeable that most studies focused on the prospect of obtaining data to characterize research on epidemiological studies. Demographic data (ID01) are present in all the registries, representing the main collected data category. Furthermore, the general health history (ID02) is present in 50% of the registries analyzed. Characteristics such as access control, confidentiality and data curation. We observed that 50% of the registries comprise a patient-focused web-based self-report system.

CONCLUSION

The development of robust, interoperable, and secure electronic registries that generate value for research and patients presents itself as a solution and a challenge. This systematic review demonstrated the success of a population register requires actions with well-defined development methods, as well as the involvement of various actors of civil society.

Biomedical signals and machine learning in amyotrophic lateral sclerosis: a systematic review

INTRODUCTION

The use of machine learning (ML) techniques in healthcare encompasses an emerging concept that envisages vast contributions to the tackling of rare diseases. In this scenario, amyotrophic lateral sclerosis (ALS) involves complexities that are yet not demystified. In ALS, the biomedical signals present themselves as potential biomarkers that, when used in tandem with smart algorithms, can be useful to applications within the context of the disease.

METHODS

This Systematic Literature Review (SLR) consists of searching for and investigating primary studies that use ML techniques and biomedical signals related to ALS. Following the definition and execution of the SLR protocol, 18 articles met the inclusion, exclusion, and quality assessment criteria, and answered the SLR research questions.

DISCUSSIONS

Based on the results, we identified three classes of ML applications combined with biomedical signals in the context of ALS: diagnosis (72.22%), communication (22.22%), and survival prediction (5.56%).

CONCLUSIONS

Distinct algorithmic models and biomedical signals have been reported and present promising approaches, regardless of their classes. In summary, this SLR provides an overview of the primary studies analyzed as well as directions for the construction and evolution of technology-based research within the scope of ALS.

Can EEG Be Adopted as a Neuroscience Reference for Assessing Software Programmers' Cognitive Load?

An emergent research area in software engineering and software reliability is the use of wearable biosensors to monitor the cognitive state of software developers during software development tasks. The goal is to gather physiologic manifestations that can be linked to error-prone scenarios related to programmers’ cognitive states. In this paper we investigate whether electroencephalography (EEG) can be applied to accurately identify programmers’ cognitive load associated with the comprehension of code with different complexity levels. Therefore, a controlled experiment involving 26 programmers was carried. We found that features related to Theta, Alpha, and Beta brain waves have the highest discriminative power, allowing the identification of code lines and demanding higher mental effort. The EEG results reveal evidence of mental effort saturation as code complexity increases. Conversely, the classic software complexity metrics do not accurately represent the mental effort involved in code comprehension. Finally, EEG is proposed as a reference, in particular, the combination of EEG with eye tracking information allows for an accurate identification of code lines that correspond to peaks of cognitive load, providing a reference to help in the future evaluation of the space and time accuracy of programmers’ cognitive state monitored using wearable devices compatible with software development activities.

Prediction of disease progression and outcomes in multiple sclerosis with machine learning

Multiple Sclerosis is a chronic inflammatory disease, affecting the Central Nervous System and leading to irreversible neurological damage, such as long term functional impairment and disability. It has no cure and the symptoms vary widely, depending on the affected regions, amount of damage, and the ability to activate compensatory mechanisms, which constitutes a challenge to evaluate and predict its course. Additionally, relapsing-remitting patients can evolve its course into a secondary progressive, characterized by a slow progression of disability independent of relapses. With clinical information from Multiple Sclerosis patients, we developed a machine learning exploration framework concerning this disease evolution, more specifically to obtain three predictions: one on conversion to secondary progressive course and two on disease severity with rapid accumulation of disability, concerning the 6th and 10th years of progression. For the first case, the best results were obtained within two years: AUC=[Formula: see text], sensitivity=[Formula: see text] and specificity=[Formula: see text]; and for the second, the best results were obtained for the 6th year of progression, also within two years: AUC=[Formula: see text], sensitivity=[Formula: see text], and specificity=[Formula: see text]. The Expanded Disability Status Scale value, the majority of functional systems, affected functions during relapses, and age at onset were described as the most predictive features. These results demonstrate the possibility of predicting Multiple Sclerosis progression by using machine learning, which may help to understand this disease's dynamics and thus, advise physicians on medication intake.

Process mining tools: where should we build another PCI centre to reduce STEMI mortality?

Introduction

The expected delay of transport between patient location and percutaneous coronary intervention (PCI) centre is paramount for choosing the adequate reperfusion therapy in ST-segment elevation myocardial infarction (STEMI). The central region of Portugal has heterogeneity in PCI assess due to geographical reasons. However, this data is usually presented numerically without providing a visual distribution of patients.

Purpose

We aimed to analyse the impact of distance to PCI centres on mortality in patients with STEMI through visual maps of patients' flow by using an experimental process mining tool, integrated in EIT Health's project PATHWAYS.

Methods

Using the Portuguese Registry of Acute Coronary Syndromes (ProACS), we retrospectively assessed patients with an established diagnosis of STEMI, geographical presentation specified, reperfusion option identified (PCI, fibrinolysis or no reperfusion), short-term outcomes defined as discharge or in-hospital death. With the 2 317 patients that fulfilled the criteria, we used a process mining tool to build national and regional models that represent the flow of patients in a healthcare system, enhancing differences between groups.

Results

Colour gradient in nodes and arrows changes from green to red, with green representing a lower number of patients as opposed to red. In the national model, most patients from all regions had PCI. Mortality was similar between PCI and fibrinolysis groups (4%) but higher in those without reperfusion (9%). In the central region model, one third of the patients were more than 120 minutes away from a PCI centre. Despite that, almost one third of these patients had PCI instead of fibrinolysis. In this model, fibrinolytic therapy had higher in-hospital survival rate than PCI (98% vs. 94%). Overall mortality was higher in the central model compared with the national model (6.92% vs. 5%). Central region had less PCI (53% vs. 73%), more fibrinolysis (15% vs. 7%) and more patients with no reperfusion (32% vs. 20%).

Conclusion

In the ProACS registry, mortality was higher in the central region compared with national data. Even though global interpretation of these findings is limited by underrepresentation from certain central areas, process mining offers an easily understandable view of patients flow. With its statistical upgrade and continuous development, this tool will facilitate the analysis of big data and comparison between groups.

Funding Acknowledgement

Type of funding source: Public grant(s) – EU funding. Main funding source(s): EIT Health

Equitable perinatal healthcare for migrants, Portugal: Comparative analysis of a self-assessment tool

Migration is seen as a common risk factor in obstetric management. Migrants often have a higher risk of experience worse pregnancy outcomes, higher rates of operative delivery, and a higher likelihood to receive less adequate postpartum care when compared to native women. This study evaluates self-perceived assessment of migrant women and hospital directors on equitable migrant friendly perinatal healthcare quality and access during intrapartum and postpartum period at public maternity units across Portuguese mainland between 2017-2019.

This cross-sectional study analyses perinatal health data from migrant women over 18 years giving birth in public maternity units from between April 2017 and March 2019 as part of the baMBINO project. Data on the assessments of maternity units' directors on equitable migrant friendly healthcare was collected in a self-assessment tool. Two standards on healthcare access and on healthcare quality were developed by: 1) scoring 25 and 30 questions, respectively, from 0 (worst) to 5 (best); 2) calculating the average of each score. The One-Sample Wilcoxon Test (non-parametric) was applied to compare the assessment of hospital directors with the migrant mothers and the Kruskal-Wallis one-way analysis of variance to test for regional differences.

Significant differences between migrant woman and healthcare directors' assessments on migrant friendly healthcare access and quality of care were found. Directors rated healthcare access with a median score of 2.4, twice as good as migrant women (1.3). Migrant women rated healthcare quality with a median score of 4.0 (directors: 3.2). Significant differences between the regions for quality of care and healthcare access were found. Statistically significant difference between migrants from Portuguese and non-Portuguese speaking countries was identified for healthcare access (p-value < 0.001) and healthcare quality (p-value < 0.05).

Key messages

The need to guarantee equitable healthcare access and quality contemplates as a first step to overcome health inequalities for migrant women in Portugal. The comparison between patients and healthcare providers’ assessments assists in the understanding of existent barriers in access to health care and improves quality assurance.

0529 Behavioral Therapy Components for Insomnia and Fatigue in COPD

Introduction

Insomnia contributes to fatigue, a common symptom in COPD. Our study aims were: (1) to determine the efficacy of a) cognitive behavioral therapy for insomnia (CBT-I) and b) COPD education (COPD-ED) on insomnia and fatigue, and (2) to define potential mechanistic contributors to pre/post intervention change in insomnia and fatigue in patients with COPD and insomnia.

Methods

A randomized 2x2 factorial design was used with factors representing CBT-I (yes/no) and COPD-ED (yes/no). Attention control (health videos) were used in the absence of CBT-I or COPD-ED. All patients received 6, 75-minute weekly sessions. Dependent variables included insomnia severity (Sleep Impairment Index (SII), range 0-28) and fatigue (Chronic Respiratory Disease Questionnaire (CRQ) range 1-7) measured at baseline, just post-intervention, and at 3-months post-intervention.

Results

One hundred nine patients (FEV1% predicted 67 ± 24% (mean ± SD), age 65 ± 8 years, SII 15.9 ± 8, CRQ 3.7 ± 1.1) participated in the study. After 6 sessions, insomnia decreased more in patients who received CBT-I (-5.8) than those who did not (-2.2; p=0.0002). This effect was sustained at the 3-month follow-up (p=0.0003). Fatigue showed no significant differences for CBT-I at 6-weeks (p=.27) but at 3-months patients receiving CBT-I showed marginally better improvement (.75, a clinically important difference) compared to those who did not receive CBT-I (.43; p=.09). COPD-ED showed no effect on insomnia or fatigue. Two main effects suggest mechanisms for the pre-post efficacy of CBT-I: improved sleep beliefs (p=0.0257) and self-efficacy for sleep (p=0.0619) after 6 sessions which were sustained at 3 months (p=0.0184 and p=0.0431 respectively).

Conclusion

CBT-I produced sustained decreases in insomnia in patients with COPD. Results suggest that changes in beliefs about sleep and improved self-efficacy for managing sleep may mediate CBT-I associated decreases in insomnia.

Support

This research was supported by the National Institute of Nursing Research of the National Institutes of Health R01NR013937.

VPA/PLGA microfibers produced by coaxial electrospinning for the treatment of central nervous system injury

The central nervous system shows limited regenerative capacity after injury. Spinal cord injury (SCI) is a devastating traumatic injury resulting in loss of sensory, motor, and autonomic function distal from the level of injury. An appropriate combination of biomaterials and bioactive substances is currently thought to be a promising approach to treat this condition. Systemic administration of valproic acid (VPA) has been previously shown to promote functional recovery in animal models of SCI. In this study, VPA was encapsulated in poly(lactic-co-glycolic acid) (PLGA) microfibers by the coaxial electrospinning technique. Fibers showed continuous and cylindrical morphology, randomly oriented fibers, and compatible morphological and mechanical characteristics for application in SCI. Drug-release analysis indicated a rapid release of VPA during the first day of the in vitro test. The coaxial fibers containing VPA supported adhesion, viability, and proliferation of PC12 cells. In addition, the VPA/PLGA microfibers induced the reduction of PC12 cell viability, as has already been described in the literature. The biomaterials were implanted in rats after SCI. The groups that received the implants did not show increased functional recovery or tissue regeneration compared to the control. These results indicated the cytocompatibility of the VPA/PLGA core-shell microfibers and that it may be a promising approach to treat SCI when combined with other strategies.

Linking contaminant distribution to hydrodynamic patterns in an urban estuary: The Douro estuary test case

An increase in anthropogenic activities in coastal regions can put at risk their flora and fauna and their ecosystem services. Therefore, it is important to evaluate possible impacts. In particular, we need to understand the links between contaminants concentrations and the hydrodynamic patterns of these highly productive regions to anticipate the effects of contaminants in the environment. Towards that aim there is the need to carry out regular campaigns to monitor the evolution of the coastal systems. In this work we analyse in-situ measurements of physico-chemical parameters, and look for possible relations between observed contaminants patterns and estuarine hydrodynamics. Data collected in the Douro estuary, one of the main estuarine regions of the Iberian western coast, revealed the presence of 5 hazardous and noxious substances (HNS), 14 polycyclic aromatic hydrocarbons (PAHs) and 6 trace metals in water and sediment samples. Water temperature and salinity analysis revealed a strong variability, which can affect the water solubility properties and the organisms' tolerance to certain toxins. A relationship between the salinity and the HNS and PAHs concentrations was found, caused by the existence of a salt-wedge that triggers the salting-out effect. Sinker contaminants (PAHs and trace metals) can be re-suspended both during low and high flow conditions associated with the salt-wedge and with strong river flows. Floater contaminants (HNS) are completely depended on the tide, which has the capacity to distribute them through the entire estuary, during low river flow regimes. However, strong river flows, with associated river plumes, can distribute both sinker and floater contaminants to the coastal region trapping them over the inner-shelf. The results clearly show that hydrodynamic patterns are a major driver for contaminants dispersion and pathways in coastal areas, inducing harmful effects to the flora and fauna and, consequently, to the ecosystem services of these regions.

Software code complexity assessment using EEG features

This paper provides a study using Electroencephalography (EEG) to investigate the brain activity during code comprehension tasks. Three different code complexity levels according to five complexity metrics were considered. The use of EEG for this purpose is relevant, since the existing studies were mostly focused on neuroimaging techniques. Using Leave-One-Subject-Out cross-validation procedure for 30 subjects, it was found that the features related with the Gamma activity were the most common in all the folds. Regarding the brain regions, right parietal was the most frequent region contributing with more features. A Linear Discriminant Analysis Classifier for task classification, obtained a F-Measure of 92.71% for Code complexity easy, 52.25% for Code complexity intermediate and 53.13% for Code complexity advanced, revealing an evidence of mental effort saturation with the code complexity degree. This suggests that current code complexity metrics do not capture cognitive load and might not be the best approach to assess bug risk.

Latent states extraction through Kalman Filter for the prediction of heart failure decompensation events

Cardiac function deterioration of heart failure patients is frequently manifested by the occurrence of decompensation events. One relevant step to adequately prevent cardiovascular status degradation is to predict decompensation episodes in order to allow preventive medical interventions.In this paper we introduce a methodology with the goal of finding onsets of worsening progressions from multiple physiological parameters which may have predictive value in decompensation events. The best performance was obtained for the model composed by only two features using a telemonitoring dataset (myHeart) with 41 patients. Results were achieved by applying leave-one-subject-out validation and correspond to a geometric mean of 83.67%. The obtained performance suggests that the methodology has the potential to be used in decision support solutions and assist in the prevention of this public health burden.

P724 The mysteries of sinus of Valsalva

Sinus of Valsalva aneurysms are a rare pathology that can be clinically silent during years and/or become suddenly symptomatic. We described 3 cases with different clinical presentation, complications and surgical treatment.

A 26-year-old male, competitive cyclist was admitted with a 1.5 month history of fatigue, palpitations, and nocturnal cough and sweating. At physical examination he was apyretic, blood pressure 157/49mmHg and radial pulse 96 bpm; jugular vein engorgement and continuous heart murmur, were noticed. Blood samples only revealed a mild raised BNP. EKG showed sinus tachycardia and right intraventricular conduction delay and the transthoracic echocardiography (TTE) revealed high velocity systolic-diastolic shunt (image) between a non-dilated right coronary sinus (RCS) and the right atrium (RA); moderate left ventricle dilation, severe right atrium and mild right ventricle enlargement with mild pulmonary hypertension and normal biventricular systolic function. He was referred to angioCT that showed a large communication between a non-dilated RCS and RA with signs of right ventricular overload. He was submitted to surgery, where ruptured aneurysm sac was found. Fistula closure, aneurysm sac suture and tricuspid annuloplasty were performed.

A 45-year-old male asymptomatic, with no relevant medical background went to a Cardiology consultation after detection of a holossistolic murmur in the physical exam. EKG showed sinus rhythm arrhythmia with a nonspecific intraventricular conduction delay and the TTE revealed a communication between a dilated noncoronary sinus (NCS) and RA; the biventricular systolic function was normal. He was referred to angioCT which confirmed the diagnosis. He was submitted to surgery where an exeresis and closure of the fistula was performed.

A 38-year-old male with no relevant medical background was admitted to emergence room for an intermittent anterior thoracic pain radiating to the neck (2 days of evolution). The EKG showed sinus tachycardia, incomplete right bundle branch block and the high-sensitivity troponin assays were negative. The TTE revealed severe sinus of Valsalva aneurysm, particularly of the NCS with mild aortic regurgitation. The patient performed transesophageal echocardiography and angioCT which excluded an acute aortic syndrome. He was oriented to surgery where a contained rupture of the RCS and a non-visualization of the ostium right coronary artery were detected, suggesting an intimal dissection. The patient was submitted to Bentall procedure and a bypass with internal mammary artery to right coronary artery.

In spite of the unclear etiology, all the cases had a good clinical and echocardiographic evolution at follow-up. The difficulty in making a timely diagnosis is related to the variability of clinical presentation and the need of high clinical suspicion. Echocardiography and angioTC have demonstrated its value, in providing a prompt diagnosis and appropriate management guidance.

Abstract P724 Figure. Ruptured aneurysm sac and fistula

Obstetric interventions among native and migrant women: a survey of episiotomy in Portugal

Introduction

It is unclear whether migrant women experience worse pregnancy outcomes than native women. A better comprehension of obstetric care provision, including controversial interventions such as episiotomy, is important to improve equity of service provision, overall maternal and neonatal health and to support evidence-informed perinatal health policy-making. We aimed to determine if migrant and native women giving birth vaginally have different risks of episiotomy and if the risk differs by migrant sub-groups.

Methods

This study is based on a cross-sectional survey of foreign-born women with a random sample of native women, implemented in 32 public maternity units in mainland Portugal. We included 3583 women with vaginal delivery. Migrant status was defined by the woman’s country of birth (migrants, born abroad, vs natives, born in Portugal), then as subgroups of migrants from Brasil, Portuguese-speaking African countries (PSAC) and non Portuguese-speaking countries vs natives. The association between migrant status and episiotomy was assessed using multilevel logistic regression models, stratified by delivery mode, and adjusted for main risk factors of episiotomy.

Results

The overall frequencies of episiotomy were 52.6% and 48.2% among the 1707 natives and the 1876 migrants, respectively (p = 0.01). With spontaneous delivery, migrant women had decreased odds of having an episiotomy (adjusted OR 0.70 [95% CI 0.58-0.83]), especially those from PSAC (aOR 0.57 [0.46-0.71]). However, with instrumental delivery, migrant women had increased odds of episiotomy (aOR 2.47 [95% CI 1.50-4.07]), especially those from Brasil (aOR 3.24 [1.18-8.92]) and non Portuguese-speaking countries (aOR 3.75 [1.82-7.71]).

Conclusions

These results suggest non-medically justified differential care during childbirth and highlight the importance of developing evidence-based recommendations for episiotomy use, in a country with a high frequency of medical intervention during delivery.

Key messages

Portugal displays a high frequency of medical interventions during delivery, including episiotomy, highlighting the need for developing evidence-based recommendations. Migrant and native women have different risks of episiotomy, suggesting non-medically justified differential care.

Risk Prediction of Heart Failure Decompensation Events in Multiparametric Feature Spaces

Cardiac function deterioration of heart failure patients is frequently manifested by the occurrence of decompensation events. One relevant step to adequately prevent cardiovascular status degradation is to predict decompensation episodes in order to allow preventive medical interventions. In this paper we introduce a methodology with the goal of finding relevant feature spaces from multiple physiological parameters which may have predictive value in decompensation events. The best performance was obtained for the feature space comprising the following features: mean weight, standard deviation of the blood pressure and mean of extra-thoracic impedance in a time window of 20 days. Results were achieved by applying leave-one-out validation and correspond to a geometric mean of 88.32%. The obtained performance suggests that the methodology has the potential to be used in decision support solutions and assist in the prevention of this public health burden.

Interval colorectal cancer after colonoscopy

INTRODUCTION AND AIMS

Interval colorectal cancer (iCRC) can occur due to missed lesions or to a newly developed lesion. The present study aimed to assess the iCRC rate and its characteristics in our population and find possible explanations.

MATERIALS AND METHODS

A retrospective study was conducted on patients with colorectal cancer (CRC) diagnosed between January 2011 and January 2015 at our department. Demographics, endoscopic data, and tumor characteristics (location, histology, staging) were collected. We identified patients diagnosed with CCR who underwent colonoscopy at our department in the previous 10years and presented the disease (iCRC) before the date of their next recommended exam. The cases of iCRC were characterized and compared with other CRC cases. Possible explanations for the appearance of iCRC were analyzed.

RESULTS

A total of 266 patients presented with CRC, 61.7% were men, and mean patient age was 70.7years. We identified 10 patients with iCRC: 6 were men, and mean patient age was 71.1years. Mean time for iCRC diagnosis after index colonoscopy was 3.5±1.84years. Tumor was located in the right colon in 50% of the patients with iCRC and in 24.5% of the patients without iCRC (P=.091). More patients with iCRC had a family history of CRC (50%) than the patients with reference CRC (3.1%) (P=.000).

CONCLUSIONS

In our case series, 3.76% of all CRC were iCRC. There were no statistically significant differences between patients with or without iCRC, with the exception of family history of CRC.

Detection of wheezes using their signature in the spectrogram space and musical features

In this work thirty features were tested in order to identify the best feature set for the robust detection of wheezes. The features include the detection of the wheezes signature in the spectrogram space (WS-SS) and twenty-nine musical features usually used in the context of Music Information Retrieval. The method proposed to detect the signature of wheezes imposes a temporal Gaussian regularization and a reduction of the false positives based on the (geodesic) morphological opening by reconstruction operator. Our dataset contains wheezes, crackles and normal breath sounds. Four selection algorithms were used to rank the features. The performance of the features was asserted having into account the Matthews correlation coefficient (MCC). All the selection algorithms ranked the WS-SS feature as the most important. A significant boost in performance was obtained by using around ten features. This improvement was independent of the selection algorithm. The use of more than ten features only allows for a small increase of the MCC value.

Identification of XLRS1 Gene Mutation (608C>T) in a Portuguese Family with Juvenile Retinoschisis

Purpose

To characterize electroretinogram (ERG) and molecular genetic findings in a family with XLRS1 mutation. The authors present two cases of a Portuguese family with juvenile retinoschisis with a mutation in exon 6.

Methods

Two brothers and their parents, grandmother, and uncle underwent a full ophthalmic examination. The two brothers with ophthalmic disease were evaluated with color fundus photography, fluorescein angiography, optical coherence tomography (OCT), molecular genetic study (Group VI of Retinoschisis Consortium), pattern visual evoked potential (PVEP), and full field ERG.

Results

Both patients presented funduscopic manifestations of vitreoretinal degeneration. They presented peripheral schisis and retinal detachment. However, foveal schisis had never been observed at funduscopy. A negative ERG was recorded in both. Six months after that, the younger brother showed a typical foveal schisis at fundus examination. A retinoschisis gene (XLRS1) mutation with transition of cytosine by thymine at position 608 (608C>T) had been identified in both.

Conclusions

Negative ERG is the most secure clinical marker to establish the diagnosis of juvenile retinoschisis. XLRS1 gene 608C>T mutation was described for the first time in a Portuguese family.

Pattern discovery and similarity assessment for robust heart sound segmentation

Heart Sound Segmentation plays a fundamental role in pathology detection in Phonocardiogram (PCG) signals. This matter of study has been widely studied in the past decades, however the majority of algorithms' results correspond only to small databases, composed by only quality signals or signals specific to one acquisition system. In this work we proposed a robust segmentation algorithm integrated with clinical information, based on a pattern recognition approach for segmentation of the fundamental heart sounds, which is validated in several databases from different countries and with different acquisition instrumentations. The database comprises a total of 3153 recordings from 764 patients with a variety of pathological conditions. The general results were 95% and 96% of sensitivity and positive predictivity, respectively. Based on the results the algorithm is able to perform with accuracy maintaining generalization capabilities.

Pattern discovery and similarity assessment for robust Heart Sound Segmentation

Heart Sound Segmentation plays a fundamental role in pathology detection in Phonocardiogram (PCG) signals. This matter of study has been widely studied in the past decades, however the majority of algorithms' results correspond only to small databases, composed by only quality signals or signals specific to one acquisition system. In this work we proposed a robust segmentation algorithm integrated with clinical information, based on a pattern recognition approach for segmentation of the fundamental heart sounds, which is validated in several databases from different countries and with different acquisition instrumentations. The database comprises a total of 3153 recordings from 764 patients with a variety of pathological conditions. The general results were 95% and 96% of sensitivity and positive predictivity, respectively. Based on the results the algorithm is able to perform with accuracy maintaining generalization capabilities.