Linzagolix therapy versus a placebo in patients with endometriosis-associated pain: a prospective, randomized, double-blind, Phase 3 study (EDELWEISS 3).

STUDY QUESTION: Does linzagolix administered orally once daily for up to 3 months at a dose of 75 mg alone or 200 mg in combination with add-back therapy (ABT) (1.0 mg estradiol; 0.5 mg norethindrone acetate, also known as norethisterone acetate [NETA]) demonstrate better efficacy than placebo in the management of endometriosis-related dysmenorrhea and non-menstrual pelvic pain? SUMMARY ANSWER: Combining 200 mg linzagolix with ABT was found to significantly reduce dysmenorrhea and non-menstrual pelvic pain at 3 months of therapy, while a daily dose of 75 mg linzagolix yielded a significant decrease only in dysmenorrhea at 3 months. WHAT IS KNOWN ALREADY?: A previously published Phase 2, dose-finding study reported that at a dose of 200 mg daily, linzagolix promotes full suppression of estradiol secretion to serum levels below 20 pg/ml and noted that the addition of ABT may be needed to manage hypoestrogenic side effects. At lower doses (75 mg and 100 mg/day), linzagolix maintains estradiol values within the target range of 20-60 pg/ml, which could be ideal to alleviate symptoms linked to endometriosis. STUDY DESIGN, SIZE, DURATION: EDELWEISS 3 was a multicenter, prospective, randomized, placebo-controlled, double-blind, double-dummy Phase 3 study to evaluate the safety and efficacy of linzagolix for the treatment of moderate-to-severe endometriosis-associated pain. Treatment was administered orally once daily for up to 6 months. PARTICIPANTS/MATERIALS, SETTING, METHODS: In the EDELWEISS 3 trial, 486 subjects with moderate-to-severe endometriosis-associated pain were randomized at a 1:1:1 ratio to one of the three study groups: placebo, 75 mg linzagolix alone or 200 mg linzagolix in association with ABT. Pain was measured daily on a verbal rating scale and recorded in an electronic diary. MAIN RESULTS AND THE ROLE OF CHANCE: At 3 months, the daily 200 mg linzagolix dose with ABT met the primary efficacy objective, showing clinically meaningful and statistically significant reductions in dysmenorrhea and non-menstrual pelvic pain, with stable or decreased use of analgesics. The proportion of responders for dysmenorrhea in the 200 mg linzagolix with ABT group was 72.9% compared with 23.5% in the placebo group (P < 0.001), while the rates of responders for non-menstrual pelvic pain were 47.3% and 30.9% (P = 0.007), respectively. The 75 mg linzagolix daily dose demonstrated a clinically meaningful and statistically significant reduction in dysmenorrhea versus placebo at 3 months. The proportion of responders for dysmenorrhea in the 75 mg linzagolix group was 44.0% compared with 23.5% in the placebo group (P < 0.001). Although the 75 mg dose showed a trend toward reduction in non-menstrual pelvic pain at 3 months relative to the placebo, it was not statistically significant (P = 0.279). Significant improvements in dyschezia and overall pelvic pain were observed in both linzagolix groups when compared to placebo. Small improvements in dyspareunia scores were observed in both linzagolix groups but they were not significant. In both groups, hypoestrogenic effects were mild, with low rates of hot flushes and bone density loss of <1%. A daily dose of 200 mg linzagolix with ABT or 75 mg linzagolix alone was found to significantly reduce dysmenorrhea and non-menstrual pelvic pain also at 6 months of therapy. LIMITATIONS, REASONS FOR CAUTION: Efficacy was compared between linzagolix groups and placebo; however, it would be useful to have results from comparative studies with estro-progestogens or progestogens. It will be important to ascertain whether gonadotropin-releasing hormone antagonists have significant benefits over traditional first-line medications. WIDER IMPLICATIONS OF THE FINDINGS: Linzagolix administered orally once daily at a dose of 200 mg in combination with add-back therapy (ABT) demonstrated better efficacy and safety than placebo in the management of moderate-to-severe endometriosis-associated pain. The quality of life was improved and the risks of bone loss and vasomotor symptoms were minimized due to the ABT. The 75 mg dose alone could be suitable for chronic treatment of endometriosis-associated pain without the need for concomitant hormonal ABT, but further research is needed to confirm this. If confirmed, it would offer a viable option for women who do not want to wish to have ABT or for whom it is contraindicated. STUDY FUNDING/COMPETING INTEREST(S): Funding for the EDELWEISS 3 study was provided by ObsEva (Geneva, Switzerland). Analysis of data and manuscript writing were partially supported by ObsEva (Geneva, Switzerland), Theramex (London, UK) and Kissei (Japan) and grant 5/4/150/5 was awarded to M.-M.D. by FNRS. J.D. was a member of the scientific advisory board of ObsEva until August 2022, a member of the scientific advisory board of PregLem, and received personal fees from Gedeon Richter, ObsEva and Theramex. J.D. received consulting fees, speakers' fees, and travel support from Gedeon Richter, Obseva and Theramex, which was paid to their institution. C.B. has received fees from Theramex, Gedeon Richter, and Myovant, and travel support from Gedeon Richter-all funds went to the University of Oxford. He was a member of the data monitoring board supervising the current study, and served at an advisory board for endometriosis studies of Myovant. H.T. has received grants from Abbvie and was past president of ASRM. F.C.H. has received fees from Gedeon Richter and Theramex. O.D. received fees for lectures from Gedeon Richter and ObsEva and research grants for clinical studies from Preglem and ObsEva independent from the current study. A.H. has received grants from NIHR, UKRI, CSO, Wellbeing of Women, and Roche Diagnostics; he has received fees from Theramex. A.H.'s institution has received honoraria for consultancy from Roche Diagnostics, Gesynta, and Joii. M.P. has nothing to declare. F.P. has received fees from Theramex. S.P.R. has been a member of the scientific advisory board of Gedeon Richter and received fees from Gedeon Richter. A.P. and M.B. are employees of Theramex. E.B. was an employee of ObsEva, sponsor chair of the data monitoring board supervising the current study, and has been working as a consultant for Theramex since December 2022; she owns stock options in ObsEva. M.-M.D. has received fees and travel support from Gedeon Richter and Theramex. TRIAL REGISTRATION NUMBER: NCT03992846. TRIAL REGISTRATION DATE: 20 June 2019. DATE OF FIRST PATIENT'S ENROLLMENT: 13 June 2019.

Discovery of MDV6058 (PF-06952229), a selective and potent TGFßR1 inhibitor: Design, synthesis and optimization.

Compound 1 is a potent TGF-ß receptor type-1 (TGFßR1 or ALK5) inhibitor but is metabolically unstable. A solvent-exposed part of this molecule was used to analogue and modulate cell activity, liver microsome stability and mouse pharmacokinetics. The evolution of SAR that led to the selection of 2 (MDV6058 / PF-06952229) as a preclinical lead compound is described.

Female sexuality before and after sacrocolpopexy or vaginal mesh: is vaginal length one of the key factors?

INTRODUCTION AND HYPOTHESIS: We aimed to demonstrate that laparoscopic sacrocolpopexy/cervicopexy (LSC-Cx) versus anterior vaginal mesh (AVM) results in a longer vaginal length without impacting sexual activity or function. METHODS: We performed a secondary analysis of sexual outcomes of a previous randomized control trial comparing LSC-Cx and AVM in 120 women (60/group) with symptomatic POP stage ≥ 3. We evaluated sexually active (SA) and non-sexually active women (NSA) using the Pelvic Organ Prolapse/Incontinence Sexual Questionnaire-IUGA-Revised (PISQ-IR) preoperatively and 1 year postoperatively. Multivariate logistic and linear regression models were built to assess the impact of different variables on sexual activity and function, respectively. RESULTS: Among 120 women included, no statistically significant differences were found between vaginal length and preoperative dyspareunia (20.7% AVM vs. 22,8% LSC-Cx) comparing SA to NSA women and LSC-Cx to AVM. Vaginal length was significantly longer after LSC-Cx versus AVM (p < 0.001). The postoperative dyspareunia rate was 17.2% AVM versus 10.5% LSC-Cx. Partnered women were significantly more likely to be SA than unpartnered women before (OR = 19.04; p = 0.006) and after surgery (OR = 36.28; p = 0.002). Only dyspareunia was independently associated with sexual function pre- (B = -0.431; p = 0.017) and postoperatively (B = -0.3 96; p = 0.007). CONCLUSIONS: Vaginal length was greater following LSC-Cx compared to AVM. While vaginal length has no impact on female sexuality pre- and postoperatively, the most important factors were "having a partner" for sexual activity and dyspareunia for sexual function. Persistence of dyspareunia was higher after AVM. LSC-Cx should be considered in women with POP undergoing mesh surgery with future sexual expectations.

Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions.

Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.

Sexual activity and function in women with advanced stages of pelvic organ prolapse, before and after laparoscopic or vaginal mesh surgery.

INTRODUCTION AND HYPOTHESIS: The differential impact of specific pelvic organ prolapse (POP) surgery on sexual activity and function is unknown. Our primary aim was to analyse sexual inactivity and function in women with symptomatic advanced stages of POP and the changes incurred after laparoscopic or vaginal mesh surgery. METHODS: We performed a secondary analysis of sexual outcomes of a previously published randomised controlled trial comparing laparoscopic sacrocolpopexy/cervicopexy (LSC-Cx) and anterior vaginal mesh (AVM) in 120 women (60/group) with symptomatic anterior POP stage ≥ 3 and apical ≥ 2. Sexual activity and function were assessed preoperatively and 1 and 2 years postoperatively using the Pelvic Organ Prolapse/Incontinence Sexual Questionnaire-IUGA-Revised (PISQ-IR). RESULTS: Sexual activity was recovered in 42.9% of non-sexually active (NSA) women 1 year postoperatively, mainly in women with higher preoperative POP-related subscale scores of the PISQ-IR, which indicated a negative preoperative sexuality by POP. Recovery of sexual activity was greater after LSC-Cx, albeit not significantly (2 years: 35.5% AVM vs. 45% LSC-Cx). Among sexually active (SA) women preoperatively remaining SA postoperatively, the difference in the mean PISQ-IR summary score significantly improved [mean baseline difference - 2 years; all: 0.3 (95% CI 0.1 to 0.5) p = 0.001; AVM 0.19 (95% CI -0.1 to -0.5) p > 0.05; LSC-Cx 0.37 (95% CI 0.1 to 0.7) p = 0.003]. Preoperative dyspareunia was significantly reduced after LSC-Cx (baseline: 24.6%, 2 years: 9.8%, p = 0.0448), but not after AVM (baseline: 20.7%, 2 years: 18.2%, p = 0.7385). CONCLUSIONS: Most women reported improved sexual activity and function 2 years after LSC-Cx or AVM, mainly because of enhanced POP-related subscales in both NSA and SA women. Recovery of sexual activity and improved sexual function were greater after LSC-Cx compared to AVM, likely related to less postoperative dyspareunia.

Laparoscopic Resection of a Symptomatic Parasitic Leiomyoma of Paravesical and Obturator Fossa.

STUDY OBJECTIVE: To show laparoscopic management of a symptomatic parasitic leiomyoma of paravesical and obturator fossa. DESIGN: Edited video demonstrating a step-by-step explanation of the surgical technique of this case. SETTING: University hospital. INTERVENTIONS: Uterine leiomyomas are the most common benign pelvic tumors in women. They occur in approximately 25% of women of reproductive age. Parasitic leiomyomas are rare, with few cases reported in the literature [1,2]. They are classified according to their location in relation to the myometrium. Parasitic leiomyomas are in group 8 of the International Federation of Gynecology and Obstetrics classification [3]. It is not clear why they are produced; it is thought that they could derive from subserous leiomyomas that achieved a blood supply from neighboring structures outside the uterus [1,3]. They can also have iatrogenic origin in patients who have undergone previous surgery such as myomectomy with power morcellation use [4]. We present the case of a 32-year-old women, gravida 1 para 1, without previous pelvic surgery. She complained of lower back and sacrum pain and nonspecific discomfort in her inner thigh. Her physical examination showed a 6- to 7-cm solid right paravaginal tumor. Ultrasonography and nuclear magnetic resonance confirmed the presence of a 7 × 5-cm solid tumor in the right paravesical and obturator fossa. The diagnosis of a probable parasitic myoma was proposed, and a laparoscopic resection was scheduled. The video demonstrates the surgical technique with special emphasis on the anatomy of the surgical site. The patient was discharged 24 hours after surgery without complications. The final pathology confirmed uterine leiomyoma. Written informed consent was requested according to the regulations of our institution. CONCLUSION: A successful laparoscopic resection of a symptomatic parasitic leiomyoma of the paravesical and obturator fossa was achieved. The importance of knowledge of the pelvic anatomy for the management of this type of case is underlined.

A panoramic view and swot analysis of artificial intelligence for achieving the sustainable development goals by 2030: progress and prospects.

The17 Sustainable Development Goals (SDGs) established by the United Nations Agenda 2030 constitute a global blueprint agenda and instrument for peace and prosperity worldwide. Artificial intelligence and other digital technologies that have emerged in the last years, are being currently applied in virtually every area of society, economy and the environment. Hence, it is unsurprising that their current role in the pursuance or hampering of the SDGs has become critical. This study aims at providing a snapshot and comprehensive view of the progress made and prospects in the relationship between artificial intelligence technologies and the SDGs. A comprehensive review of existing literature has been firstly conducted, after which a series SWOT (Strengths, Weaknesses, Opportunities and Threats) analyses have been undertaken to identify the strengths, weaknesses, opportunities and threats inherent to artificial intelligence-driven technologies as facilitators or barriers to each of the SDGs. Based on the results of these analyses, a subsequent broader analysis is provided, from a position vantage, to (i) identify the efforts made in applying AI technologies in SDGs, (ii) pinpoint opportunities for further progress along the current decade, and (iii) distill ongoing challenges and target areas for important advances. The analysis is organized into six categories or perspectives of human needs: life, economic and technological development, social development, equality, resources and natural environment. Finally, a closing discussion is provided about the prospects, key guidelines and lessons learnt that should be adopted for guaranteeing a positive shift of artificial intelligence developments and applications towards fully supporting the SDGs attainment by 2030.

Revisiting crowd behaviour analysis through deep learning: Taxonomy, anomaly detection, crowd emotions, datasets, opportunities and prospects.

Crowd behaviour analysis is an emerging research area. Due to its novelty, a proper taxonomy to organise its different sub-tasks is still missing. This paper proposes a taxonomic organisation of existing works following a pipeline, where sub-problems in last stages benefit from the results in previous ones. Models that employ Deep Learning to solve crowd anomaly detection, one of the proposed stages, are reviewed in depth, and the few works that address emotional aspects of crowds are outlined. The importance of bringing emotional aspects into the study of crowd behaviour is remarked, together with the necessity of producing real-world, challenging datasets in order to improve the current solutions. Opportunities for fusing these models into already functioning video analytics systems are proposed.

Surveying alignment-free features for Ortholog detection in related yeast proteomes by using supervised big data classifiers.

BACKGROUND: The development of new ortholog detection algorithms and the improvement of existing ones are of major importance in functional genomics. We have previously introduced a successful supervised pairwise ortholog classification approach implemented in a big data platform that considered several pairwise protein features and the low ortholog pair ratios found between two annotated proteomes (Galpert, D et al., BioMed Research International, 2015). The supervised models were built and tested using a Saccharomycete yeast benchmark dataset proposed by Salichos and Rokas (2011). Despite several pairwise protein features being combined in a supervised big data approach; they all, to some extent were alignment-based features and the proposed algorithms were evaluated on a unique test set. Here, we aim to evaluate the impact of alignment-free features on the performance of supervised models implemented in the Spark big data platform for pairwise ortholog detection in several related yeast proteomes. RESULTS: The Spark Random Forest and Decision Trees with oversampling and undersampling techniques, and built with only alignment-based similarity measures or combined with several alignment-free pairwise protein features showed the highest classification performance for ortholog detection in three yeast proteome pairs. Although such supervised approaches outperformed traditional methods, there were no significant differences between the exclusive use of alignment-based similarity measures and their combination with alignment-free features, even within the twilight zone of the studied proteomes. Just when alignment-based and alignment-free features were combined in Spark Decision Trees with imbalance management, a higher success rate (98.71%) within the twilight zone could be achieved for a yeast proteome pair that underwent a whole genome duplication. The feature selection study showed that alignment-based features were top-ranked for the best classifiers while the runners-up were alignment-free features related to amino acid composition. CONCLUSIONS: The incorporation of alignment-free features in supervised big data models did not significantly improve ortholog detection in yeast proteomes regarding the classification qualities achieved with just alignment-based similarity measures. However, the similarity of their classification performance to that of traditional ortholog detection methods encourages the evaluation of other alignment-free protein pair descriptors in future research.

Novel 3-methylindoline inhibitors of EZH2: Design, synthesis and SAR.

EZH2 (enhancer of zeste homologue 2) is the catalytic subunit of the polycomb repressive complex 2 (PRC2) that catalyzes the methylation of lysine 27 of histone H3 (H3K27). Dysregulation of EZH2 activity is associated with several human cancers and therefore EZH2 inhibition has emerged as a promising therapeutic target. Several small molecule EZH2 inhibitors with different chemotypes have been reported in the literature, many of which use a bicyclic heteroaryl core. Herein, we report the design and synthesis of EZH2 inhibitors containing an indoline core. Partial saturation of an indole to an indoline provided lead compounds with nanomolar activity against EZH2, while also improving solubility and oxidative metabolic stability.

Design, synthesis and optimization of bis-amide derivatives as CSF1R inhibitors.

Signaling via the receptor tyrosine kinase CSF1R is thought to play an important role in recruitment and differentiation of tumor-associated macrophages (TAMs). TAMs play pro-tumorigenic roles, including the suppression of anti-tumor immune response, promotion of angiogenesis and tumor cell metastasis. Because of the role of this signaling pathway in the tumor microenvironment, several small molecule CSF1R kinase inhibitors are undergoing clinical evaluation for cancer therapy, either as a single agent or in combination with other cancer therapies, including immune checkpoint inhibitors. Herein we describe our lead optimization effort that resulted in the identification of a potent, cellular active and orally bioavailable bis-amide CSF1R inhibitor. Docking and biochemical analysis allowed the removal of a metabolically labile and poorly permeable methyl piperazine group from an early lead compound. Optimization led to improved metabolic stability and Caco2 permeability, which in turn resulted in good oral bioavailability in mice.

Shell shape variation of queen conch Strombus gigas (Mesograstropoda: Strombidae) from Southwest Caribbean.

The endangered species Strombus gigas is a marine gastropod of significant economic importance through the Greater Caribbean region. In contrast to phenotypic plasticity, the role of genetics on shell variations in S. gigas has not been addressed so far, despite its importance in evolution, management and conservation of this species. This work used geometric morphometrics to investigate the phenotypic variation of 219 shells of S. gigas from eight sites of the Colombian Southwest Caribbean. Differences in mean size between sexes and among sites were contrasted by analysis of variance. Allometry was tested by multivariate regression and the hypothesis of common slope was contrasted by covariance multivariate analysis. Differences in the shell shape among sites were analyzed by principal component analysis. Sexual size dimorphism was not significant, whereas sexual shape dimorphism was significant and variable across sites. Differences in the shell shape among sites were concordant with genetic differences based on microsatellite data, supporting its genetic background. Besides, differences in the shell shape between populations genetically similar suggest a role of phenotypic plasticity in the morphometric variation of the shell shape. These outcomes evidence the role of genetic background and phenotypic plasticity in the shell shape of S. gigas. Thus, geometric morphometrics of shell shape may constitute a complementary tool to explore the genetic diversity of this species.

Factors Related to the Development of Infective Endocarditis in Hemodialysis Patients in a Third-Level Hospital in Panama.

INTRODUCTION: Venous access for hemodialysis (HD) makes patients more susceptible to transient bacteremia, predisposing them to the development of infective endocarditis (IE). Among the risk factors observed in this population are temporary access to HD, hypoalbuminemia, diabetes mellitus, female gender, anemia, and colonization by methicillin-resistant Staphylococcus aureus (MRSA). METHODOLOGY: A retrospective case-control study with a one-to-two ratio was carried out on patients with chronic kidney disease (CKD) undergoing renal replacement therapy with at least one vascular access for HD at Complejo Hospitalario Dr. Arnulfo Arias Madrid (CHDrAAM) from 2010 to 2020. Sociodemographic variables, past medical history, and data on current HD were studied. The odds ratio (OR) and adjusted odds ratio (aOR) were calculated for the collected variables. RESULTS: No statistically significant differences between the groups were observed in sociodemographic variables. In terms of past medical history, the cases showed a predominance of coronary disease (47.6% vs 4.8%; OR: 37.27), valvular disease (23.8% vs 0%), and heart failure (33.3% vs 4.8%; OR: 10). In the cases, the use of a temporary catheter was more prevalent (61.9% vs 33.3%; OR: 3.25), and subclavian access was more frequently recorded (28.6% vs 2.4%; OR: 14.4). A short duration of venous access (<30 days) was found in a greater proportion of cases (23.8% vs 4.8%; OR: 6.25). The main pathogen isolated was S. aureus (33.3%), and the most affected valve was the aortic valve (59.1%). Fever was found in 100% of the reported cases, and up to 47.6% presented with a recent murmur. DISCUSSION: Similar to previous studies conducted in other countries, we identified a history of pre-existing valve disease, the use of a temporary catheter, and recent venous access as risk factors. Contrary to what has been reported in the literature, this study did not find female sex, diabetes mellitus, and hypoalbuminemia as risks. CONCLUSION: Factors such as a history of coronary artery disease, heart failure, preexisting valvular disease, the use of a temporary catheter, subclavian venous access, and short duration of venous access (<30 days) were identified as risk factors for the development of IE in patients with CKD on HD.

Handling Imbalanced Classification Problems With Support Vector Machines via Evolutionary Bilevel Optimization.

Support vector machines (SVMs) are popular learning algorithms to deal with binary classification problems. They traditionally assume equal misclassification costs for each class; however, real-world problems may have an uneven class distribution. This article introduces EBCS-SVM: evolutionary bilevel cost-sensitive SVMs. EBCS-SVM handles imbalanced classification problems by simultaneously learning the support vectors and optimizing the SVM hyperparameters, which comprise the kernel parameter and misclassification costs. The resulting optimization problem is a bilevel problem, where the lower level determines the support vectors and the upper level the hyperparameters. This optimization problem is solved using an evolutionary algorithm (EA) at the upper level and sequential minimal optimization (SMO) at the lower level. These two methods work in a nested fashion, that is, the optimal support vectors help guide the search of the hyperparameters, and the lower level is initialized based on previous successful solutions. The proposed method is assessed using 70 datasets of imbalanced classification and compared with several state-of-the-art methods. The experimental results, supported by a Bayesian test, provided evidence of the effectiveness of EBCS-SVM when working with highly imbalanced datasets.

A Trust Risk Dynamic Management Mechanism Based on Third-Party Monitoring for the Conflict-Eliminating Process of Social Network Group Decision Making.

Every decision may involve risks. Real-world risk issues are usually supervised by third parties. Decision-making may be affected by the absence of sufficient or reasonable trust or to the opposite, an unconditional, excessive, or blind trust, which is called trust risks. The conflict-eliminating process (CEP) aims to facilitate satisfactory consensus by decision makers (DMs) through continuous reconciliation between their opinion differences on the subject matter. This article addresses trust risks in CEP of social network group decision making (SNGDM) through third-party monitoring. A trust risk analysis-based conflict-eliminating model for SNGDM is developed. It is assumed that a third-party agency monitors the DMs' credibility and performance, which is recorded in an objective evaluation matrix and multi-attribute trust assessment matrix (MTAM). A trust risk measurement methodology is proposed to classify the DMs' different trust risk types and to measure the trust risk index (TRI) of a group of DMs. When TRI is unacceptable, a trust risk management mechanism that controls TRI is activated. Different management policies are applicable to DMs' different trust risk types. There are two main methods: 1) dynamically update the MTAM based on DMs' performance and 2) provide suggestions for modifying the DM's information with high TRI. Besides, as part of the integrated CEP, this model includes an optimization approach to dynamically derive DMs' reliable aggregation weights from their MTAM. Simulation experiments and an illustrative example support the feasibility and validity of the proposed model for managing trust risks in CEP of SNGDM.

EvoPruneDeepTL: An evolutionary pruning model for transfer learning based deep neural networks.

In recent years, Deep Learning models have shown a great performance in complex optimization problems. They generally require large training datasets, which is a limitation in most practical cases. Transfer learning allows importing the first layers of a pre-trained architecture and connecting them to fully-connected layers to adapt them to a new problem. Consequently, the configuration of the these layers becomes crucial for the performance of the model. Unfortunately, the optimization of these models is usually a computationally demanding task. One strategy to optimize Deep Learning models is the pruning scheme. Pruning methods are focused on reducing the complexity of the network, assuming an expected performance penalty of the model once pruned. However, the pruning could potentially be used to improve the performance, using an optimization algorithm to identify and eventually remove unnecessary connections among neurons. This work proposes EvoPruneDeepTL, an evolutionary pruning model for Transfer Learning based Deep Neural Networks which replaces the last fully-connected layers with sparse layers optimized by a genetic algorithm. Depending on its solution encoding strategy, our proposed model can either perform optimized pruning or feature selection over the densely connected part of the neural network. We carry out different experiments with several datasets to assess the benefits of our proposal. Results show the contribution of EvoPruneDeepTL and feature selection to the overall computational efficiency of the network as a result of the optimization process. In particular, the accuracy is improved, reducing at the same time the number of active neurons in the final layers.

Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation.

Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.

A review on architectures and communications technologies for wearable health-monitoring systems.

Nowadays society is demanding more and more smart healthcare services that allow monitoring patient status in a non-invasive way, anywhere and anytime. Thus, healthcare applications are currently facing important challenges guided by the u-health (ubiquitous health) and p-health (pervasive health) paradigms. New emerging technologies can be combined with other widely deployed ones to develop such next-generation healthcare systems. The main objective of this paper is to review and provide more details on the work presented in "LOBIN: E-Textile and Wireless-Sensor-Network-Based Platform for Healthcare Monitoring in Future Hospital Environments", published in the IEEE Transactions on Information Technology in Biomedicine, as well as to extend and update the comparison with other similar systems. As a result, the paper discusses the main advantages and disadvantages of using different architectures and communications technologies to develop wearable systems for pervasive healthcare applications.

Reducing Data Complexity Using Autoencoders With Class-Informed Loss Functions.

Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher's discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task.