Aprendizaje automático aplicado en área de la salud: parte 2 / Machine Learning In Healthcare: part 2

En el artículo anterior se introdujo el tema y se desarrolló cómo es la recolección y análisis de datos, la selección y entrenamiento de modelos de aprendizaje automático supervisados y los métodos de validación interna que permiten corroborar si el modelo arroja resultados similares a los de otros conjuntos de entrenamiento y de prueba. En este artículo continuaremos con la descripción de la evaluación del rendimiento, la selección del modelo más adecuado para identificar la característica que se va a evaluar y la validación externa del modelo. Además, el artículo resume los desafíos existentes en la implementación del Machine Learning desde la investigación al uso clínico. (AU)

In the previous article, we introduced topics such as data collection and analysis, selection and training of supervised machine learning models and methods of internal validation that allow to corroborate whether the model yields similar results to other training and test sets.In this article, we will continue with the description of the performance evaluation, selecting the most appropriate model to identify the characteristic to evaluate and the external validation of the model. In addition, the article summarizes the actual challenges in the implementation of machine learning from research to clinical use. (AU)

The digital transformation of hepatology: The patient is logged in.

The rise in innovative digital health technologies has led a paradigm shift in health care toward personalized, patient-centric medicine that is reaching beyond traditional brick-and-mortar facilities into patients' homes and everyday lives. Digital solutions can monitor and detect early changes in physiological data, predict disease progression and health-related outcomes based on individual risk factors, and manage disease intervention with a range of accessible telemedicine and mobile health options. In this review, we discuss the unique transformation underway in the care of patients with liver disease, specifically examining the digital transformation of diagnostics, prediction and clinical decision-making, and management. Additionally, we discuss the general considerations needed to confirm validity and oversight of new technologies, usability and acceptability of digital solutions, and equity and inclusivity of vulnerable populations.

Digital Health Technologies for Remote Monitoring and Management of Inflammatory Bowel Disease: A Systematic Review.

INTRODUCTION: Digital health technologies may be useful tools in the management of chronic diseases. We performed a systematic review of digital health interventions in the management of patients with inflammatory bowel diseases (IBD) and evaluated its impact on (i) disease activity monitoring, (ii) treatment adherence, (iii) quality of life (QoL) measures, and/or (iv) health care utilization. METHODS: Through a systematic review of multiple databases through August 31, 2020, we identified randomized controlled trials in patients with IBD comparing digital health technologies vs standard of care (SoC) for clinical management and monitoring and reporting impact on IBD disease activity, treatment adherence, QoL, and/or health care utilization or cost-effectiveness. We performed critical qualitative synthesis of the evidence supporting digital health interventions in patients with IBD and rated certainty of evidence using Grading of Recommendations Assessment, Development and Evaluation. RESULTS: Overall, we included 14 randomized controlled trials (median, 98 patients; range 34-909 patients; follow-up <12 months) that compared web-based interventions, mobile applications, and different telemedicine platforms with SoC (clinic-based encounters). Although overall disease activity and risk of relapse were comparable between digital health technologies and SoC (very low certainty of evidence), digital health interventions were associated with lower rate of health care utilization and health care costs (low certainty of evidence). Digital health interventions did not significantly improve patients' QoL and treatment adherence compared with SoC (very low certainty of evidence). Trials may have intrinsic selection bias due to nature of digital interventions. DISCUSSION: Digital health technologies may be effective in decreasing health care utilization and costs, though may not offer advantage in reducing risk of relapse, QoL, and improving treatment adherence in patients with IBD. These techniques may offer value-based care for population health management.

Magnetic frequency mixing technological advances for the practical improvement of point-of-care testing.

Nanomaterials, especially superparamagnetic nanomaterials, have recently played essential roles in point-of-care testing due to their intrinsic magnetic, electrochemical, and optical properties. The inherent superparamagnetism of magnetic nanoparticles makes them highly sensitive for quantitative detection. Among the various magnetic detection technologies, frequency mixing technology (FMT) technology is an emerging detection technique in the nanomedical field. FMT sensors have high potential for development in the field of biomedical quantitative detection due to their simple structure, and they are not limited to the materials used. In particular, they can be applied for large-scale disease screening, early tumor marker detection, and low-dose drug detection. This review summarizes the principles of FMT and recent advances in the fields of immunoadsorption, lateral flow assay detection, magnetic imaging, and magnetic nanoparticles recognition. The advantages and limitations of FMT sensors for robust, ultrasensitive biosensing are highlighted. Finally, the future requirements and challenges in the development of this technology are described. This review provides further insights for researchers to inspire the future development of FMT by integration into biosensing and devices with a broad field of applications in analytical sensing and clinical usage.

Adoption of Advanced Microneurosurgical Technologies: An International Survey.

BACKGROUND: Operating microscopes and adjunctive technologies are continually refined to advance microneurosurgical care. How frequently these advances are used is unknown. In the present study, we assessed the international adoption of microneurosurgical technologies and discussed their value. METHODS: A 27-question electronic survey was distributed to cerebrovascular neurosurgeon members of U.S., European, and North American neurosurgical societies and social media networks of cerebrovascular and skull base neurosurgeons. The survey encompassed the surgeons' training background, surgical preferences, and standard microneurosurgical practices. RESULTS: Of the respondents, 56% (53 of 95) were attendings, 74% (70 of 95) were in their first 10 years of practice, and 67% (63 of 94) practiced at an academic teaching hospital. Vascular, endovascular, and skull base fellowships had been completed by 38% (36 of 95), 27% (26 of 95), and 32% (30 of 95) of the respondents, respectively. Most respondents did not use an exoscope (78%; 73 of 94), a mouthpiece (61%; 58 of 95), or foot pedals (56%; 55 of 94). All 95 respondents used a microscope, and 71 (75%) used Zeiss microscopes. Overall, 57 neurosurgeons (60%) used indocyanine green for aneurysms (n = 54), arteriovenous malformations (n = 43), and dural arteriovenous fistulas (n = 42). Most (80%; 75 of 94) did not use fluorescence. The respondents with a vascular-focused practice more commonly used indocyanine green, Yellow 560 fluorescence, and intraoperative 2-dimensional digital subtraction angiography. The respondents with a skull base-focused practice more commonly used foot pedals and an endoscope-assist device. CONCLUSIONS: The results from the present survey have characterized the current adoption of operative microscopes and adjunctive technologies in microneurosurgery. Despite numerous innovations to improve the symbiosis between neurosurgeon and microscope, their adoption has been underwhelming. Future advances are essential to improve surgical outcomes.

Evaluating the performance of drug-repurposing technologies.

Drug-repurposing technologies are growing in number and maturing. However, comparisons to each other and to reality are hindered because of a lack of consensus with respect to performance evaluation. Such comparability is necessary to determine scientific merit and to ensure that only meaningful predictions from repurposing technologies carry through to further validation and eventual patient use. Here, we review and compare performance evaluation measures for these technologies using version 2 of our shotgun repurposing Computational Analysis of Novel Drug Opportunities (CANDO) platform to illustrate their benefits, drawbacks, and limitations. Understanding and using different performance evaluation metrics ensures robust cross-platform comparability, enabling us to continue to strive toward optimal repurposing by decreasing the time and cost of drug discovery and development.

Artificial intelligence-enhanced drug design and development: Toward a computational precision medicine.

Artificial Intelligence (AI) relies upon a convergence of technologies with further synergies with life science technologies to capture the value of massive multi-modal data in the form of predictive models supporting decision-making. AI and machine learning (ML) enhance drug design and development by improving our understanding of disease heterogeneity, identifying dysregulated molecular pathways and therapeutic targets, designing and optimizing drug candidates, as well as evaluating in silico clinical efficacy. By providing an unprecedented level of knowledge on both patient specificities and drug candidate properties, AI is fostering the emergence of a computational precision medicine allowing the design of therapies or preventive measures tailored to the singularities of individual patients in terms of their physiology, disease features, and exposure to environmental risks.

LR-GNN: a graph neural network based on link representation for predicting molecular associations.

In biomedical networks, molecular associations are important to understand biological processes and functions. Many computational methods, such as link prediction methods based on graph neural networks (GNNs), have been successfully applied in discovering molecular relationships with biological significance. However, it remains a challenge to explore a method that relies on representation learning of links for accurately predicting molecular associations. In this paper, we present a novel GNN based on link representation (LR-GNN) to identify potential molecular associations. LR-GNN applies a graph convolutional network (GCN)-encoder to obtain node embedding. To represent associations between molecules, we design a propagation rule that captures the node embedding of each GCN-encoder layer to construct the LR. Furthermore, the LRs of all layers are fused in output by a designed layer-wise fusing rule, which enables LR-GNN to output more accurate results. Experiments on four biomedical network data, including lncRNA-disease association, miRNA-disease association, protein-protein interaction and drug-drug interaction, show that LR-GNN outperforms state-of-the-art methods and achieves robust performance. Case studies are also presented on two datasets to verify the ability to predict unknown associations. Finally, we validate the effectiveness of the LR by visualization.

Mobile health technology for remote home monitoring after surgery: a meta-analysis.

BACKGROUND: Mobile health (mHealth) technology has been proposed as a method of improving post-discharge surveillance. Little is known about how mHealth has been used to track patients after surgery and whether its use is associated with differences in postoperative recovery. METHODS: Three databases (PubMed, MEDLINE and the Cochrane Central Registry of Controlled Trials) were searched to identify studies published between January 1999 and February 2021. Mobile health was defined as any smartphone or tablet computer capable of electronically capturing health-related patient information and transmitting these data to the clinical team. Comparable outcomes were pooled via meta-analysis with additional studies compiled via narrative review. The quality of each study was assessed based on Grading of Recommendations Assessment, Development, and Evaluation (GRADE) criteria. RESULTS: Forty-five articles met inclusion criteria. While the majority of devices were designed to capture general health information, others were specifically adapted to the expected outcomes or potential complications of the index procedure. Exposure to mHealth was associated with fewer emergency department visits (odds ratio 0.42, 95 per cent c.i. 0.23 to 0.79) and readmissions (odds ratio 0.47, 95 per cent c.i. 0.29 to 0.77) as well as accelerated improvements in quality of life after surgery. There were limited data on other postoperative outcomes. CONCLUSION: Remote home monitoring via mHealth is feasible, adaptable, and may even promote more effective postoperative care. Given the rapid expansion of mHealth, physicians and policymakers need to understand these technologies better so that they can be integrated into high-quality clinical care.

A systematic review was performed to determine how mobile health (mHealth) technology is being used to track surgical patients after hospital discharge, and whether exposure to mHealth is associated with differences in postoperative recovery. Remote home monitoring via mHealth is feasible and flexible enough to meet the demands of a variety of patients and clinical teams. Exposure to mHealth also appears to be associated with a reduction in both emergency department visits and hospital readmissions as well as accelerated improvements in quality of life. mHealth represents an important next step in postoperative surveillance, although better performance data, targeted incentives and clearer guidelines are still needed.

Neurodegeneration & imperfect ageing: Technological limitations and challenges?

Cellular homeostasis is regulated by the protein quality control (PQC) machinery, comprising multiple chaperones and enzymes. Studies suggest that the loss of the PQC mechanisms in neurons may lead to the formation of abnormal inclusions that may lead to neurological disorders and defective aging. The questions could be raised how protein aggregate formation precisely engenders multifactorial molecular pathomechanism in neuronal cells and affects different brain regions? Such questions await thorough investigation that may help us understand how aberrant proteinaceous bodies lead to neurodegeneration and imperfect aging. However, these studies face multiple technological challenges in utilizing available tools for detailed characterizations of the protein aggregates or amyloids and developing new techniques to understand the biology and pathology of proteopathies. The lack of detection and analysis methods has decelerated the pace of the research in amyloid biology. Here, we address the significance of aggregation and inclusion formation, followed by exploring the evolutionary contribution of these structures. We also provide a detailed overview of current state-of-the-art techniques and advances in studying amyloids in the diseased brain. A comprehensive understanding of the structural, pathological, and clinical characteristics of different types of aggregates (inclusions, fibrils, plaques, etc.) will aid in developing future therapies.

Digital health technology for non-motor symptoms in people with Parkinson's disease: Futile or future?

INTRODUCTION: There is an ongoing digital revolution in the field of Parkinson's disease (PD) for the objective measurement of motor aspects, to be used in clinical trials and possibly support therapeutic choices. The focus of remote technologies is now also slowly shifting towards the broad but more "hidden" spectrum of non-motor symptoms (NMS). METHODS: A narrative review of digital health technologies for measuring NMS in people with PD was conducted. These digital technologies were defined as assessment tools for NMS offered remotely in the form of a wearable, downloadable as a mobile app, or any other objective measurement of NMS in PD that did not require a hospital visit and could be performed remotely. Searches were performed using peer-reviewed literature indexed databases (MEDLINE, Embase, PsycINFO, Cochrane Database of Systematic Reviews, Cochrane CENTRAL Register of Controlled Trials), as well as Google and Google Scholar. RESULTS: Eighteen studies deploying digital health technology in PD were identified, for example for the measurement of sleep disorders, cognitive dysfunction and orthostatic hypotension. In addition, we describe promising developments in other conditions that could be translated for use in PD. CONCLUSION: Unlike motor symptoms, non-motor features of PD are difficult to measure directly using remote digital technologies. Nonetheless, it is currently possible to reliably measure several NMS and further digital technology developments are underway to offer further capture of often under-reported and under-recognised NMS.

Aptamer-Functionalized DNA-Silver Nanocluster Nanofilm for Visual Detection and Elimination of Bacteria.

As a new type of nanomaterial, DNA-templated silver nanoclusters (DNA-AgNCs) have been widely studied because of their fluorescence and antibacterial properties. In this study, we combined the DNA-AgNCs with aptamers of bacteria to achieve a novel approach for the visual detection and effective elimination of bacteria. The aptamers of Staphylococcus aureus (S. aureus) were linked to G-rich sequences to achieve fluorescence enhancement when approaching the DNA-AgNCs. The capture of aptamers not only realized the visual monitoring of bacteria but also promoted the antibacterial effects. Additionally, a fluorescent nanofilm with excellent selectivity and antibacterial activity in the detection and elimination of S. aureus was developed based on the DNA-AgNCs. These aptamer-functionalized DNA-AgNCs show significant potential for many applications in food packaging and biomedical engineering.

Recent Advances in Ionic Liquids in Biomedicine.

The use of ionic liquids and deep eutectic solvents in biomedical applications has grown dramatically in recent years due to their unique properties and their inherent tunability. This review will introduce ionic liquids and deep eutectics and discuss their biomedical applications, namely solubilization of drugs, creation of active pharmaceutical ingredients, delivery of pharmaceuticals through biological barriers, stabilization of proteins and other nucleic acids, antibacterial agents, and development of new biosensors. Current challenges and future outlooks are discussed, including biocompatibility, the potential impact of the presence of impurities, and the importance of understanding the microscopic interactions in ionic liquids in order to design task-specific solvents.

Weaving Enzymes with Polymeric Shells for Biomedical Applications.

Enzyme therapeutics have received increasing attention due to their high biological specificity, outstanding catalytic efficiency, and impressive therapeutic outcomes. Protecting and delivering enzymes into target cells while retaining enzyme catalytic efficiency is a big challenge. Wrapping of enzymes with rational designed polymer shells, rather than trapping them into large nanoparticles such as liposomes, have been widely explored because they can protect the folded state of the enzyme and make post-functionalization easier. In this review, the methods for wrapping up enzymes with protective polymer shells are mainly focused on. It is aimed to provide a toolbox for the rational design of polymeric enzymes by introducing methods for the preparation of polymeric enzymes including physical adsorption and chemical conjugation with specific examples of these conjugates/hybrid applications. Finally, a conclusion is drawn and key points are emphasized.

Making the COVID-19 Pandemic a Driver for Digital Health: Brazilian Strategies.

The COVID-19 outbreak exposed several problems faced by health systems worldwide, especially concerning the safe and rapid generation and sharing of health data. However, this pandemic scenario has also facilitated the rapid implementation and monitoring of technologies in the health field. In view of the occurrence of the public emergency caused by SARS-CoV-2 in Brazil, the Department of Informatics of the Brazilian Unified Health System created a contingency plan. In this paper, we aim to report the digital health strategies applied in Brazil and the first results obtained during the fight against COVID-19. Conecte SUS, a platform created to store all the health data of an individual throughout their life, is the center point of the Brazilian digital strategy. Access to the platform can be obtained through an app by the patient and the health professionals involved in the case. Health data sharing became possible due to the creation of the National Health Data Network (Rede Nacional de Dados em Saúde, RNDS). A mobile app was developed to guide citizens regarding the need to go to a health facility and to assist in disseminating official news about the virus. The mobile app can also alert the user if they have had contact with an infected person. The official numbers of cases and available hospital beds are updated and published daily on a website containing interactive graphs. These data are obtained due to creating a web-based notification system that uses the RNDS to share information about the cases. Preclinical care through telemedicine has become essential to prevent overload in health facilities. The exchange of experiences between medical teams from large centers and small hospitals was made possible using telehealth. Brazil took a giant step toward digital health adoption, creating and implementing important initiatives; however, these initiatives do not yet cover the entire health system. It is expected that the sharing of health data that are maintained and authorized by the patient will become a reality in the near future. The intention is to obtain better clinical outcomes, cost reduction, and faster and better services in the public health network.

Stereocomplex Polylactide for Drug Delivery and Biomedical Applications: A Review.

Polylactide (PLA) is among the most common biodegradable polymers, with applications in various fields, such as renewable and biomedical industries. PLA features poly(D-lactic acid) (PDLA) and poly(L-lactic acid) (PLLA) enantiomers, which form stereocomplex crystals through racemic blending. PLA emerged as a promising material owing to its sustainable, eco-friendly, and fully biodegradable properties. Nevertheless, PLA still has a low applicability for drug delivery as a carrier and scaffold. Stereocomplex PLA (sc-PLA) exhibits substantially improved mechanical and physical strength compared to the homopolymer, overcoming these limitations. Recently, numerous studies have reported the use of sc-PLA as a drug carrier through encapsulation of various drugs, proteins, and secondary molecules by various processes including micelle formation, self-assembly, emulsion, and inkjet printing. However, concerns such as low loading capacity, weak stability of hydrophilic contents, and non-sustainable release behavior remain. This review focuses on various strategies to overcome the current challenges of sc-PLA in drug delivery systems and biomedical applications in three critical fields, namely anti-cancer therapy, tissue engineering, and anti-microbial activity. Furthermore, the excellent potential of sc-PLA as a next-generation polymeric material is discussed.

Privacy-Oriented Technique for COVID-19 Contact Tracing (PROTECT) Using Homomorphic Encryption: Design and Development Study.

BACKGROUND: Various techniques are used to support contact tracing, which has been shown to be highly effective against the COVID-19 pandemic. To apply the technology, either quarantine authorities should provide the location history of patients with COVID-19, or all users should provide their own location history. This inevitably exposes either the patient's location history or the personal location history of other users. Thus, a privacy issue arises where the public good (via information release) comes in conflict with privacy exposure risks. OBJECTIVE: The objective of this study is to develop an effective contact tracing system that does not expose the location information of the patient with COVID-19 to other users of the system, or the location information of the users to the quarantine authorities. METHODS: We propose a new protocol called PRivacy Oriented Technique for Epidemic Contact Tracing (PROTECT) that securely shares location information of patients with users by using the Brakerski/Fan-Vercauteren homomorphic encryption scheme, along with a new, secure proximity computation method. RESULTS: We developed a mobile app for the end-user and a web service for the quarantine authorities by applying the proposed method, and we verified their effectiveness. The proposed app and web service compute the existence of intersections between the encrypted location history of patients with COVID-19 released by the quarantine authorities and that of the user saved on the user's local device. We also found that this contact tracing smartphone app can identify whether the user has been in contact with such patients within a reasonable time. CONCLUSIONS: This newly developed method for contact tracing shares location information by using homomorphic encryption, without exposing the location information of patients with COVID-19 and other users. Homomorphic encryption is challenging to apply to practical issues despite its high security value. In this study, however, we have designed a system using the Brakerski/Fan-Vercauteren scheme that is applicable to a reasonable size and developed it to an operable format. The developed app and web service can help contact tracing for not only the COVID-19 pandemic but also other epidemics.

Promoção da saúde no contexto da tecnossocialidade: revisão integrativa da literatura / Health promotion in the context of technosociality: integrative literature review / Promoción de la salud en el contexto de la tecnosocialidad: una revisión integradora de la literatura

Na contemporaneidade, o uso de tecnologias pode se configurar como empecilho ou potência para a promoção da saúde. Este estudo tem como objetivo conhecer o que tem sido publicado sobre as redes sociais no quotidiano das pessoas no processo de saúde e adoecimento para a promoção da saúde. Materiais e Métodos: Revisão integrativa de literatura em cinco bases de dados, no recorte histórico de 2015 a 2019. Resultados: 12 artigos foram analisados, resultando em três categorias: 'Tecnossocialidade: Rede Social no engajamento terapêutico'; 'Tecnossocialidade: Rede Social como ferramenta de empoderamento'; 'Tecnossocialidade: A produção de conhecimento'. Discussão: Destaca-se a necessidade de avaliação para validação das informações socializadas, e debate sobre a efetividade da aplicação prática dos conhecimentos adquiridos pelo usuário. Conclusões: O enfoque do empoderamento em debate nas redes sociais volta-se majoritariamente para a perspectiva individual, ficando aquém do incentivo à participação comunitária sugerida na Política Nacional de Promoção da Saúde.(AU)

Introduction: In the contemporary world, the use of technologies can be configured as an obstacle or incentive for health promotion. This study aims to find out what has been published about social networks in people's daily lives in the health and illness process for health promotion. Materials and Methods: Integrative literature review in five databases, in the historical section from 2015 to 2019. Results: 12 articles were analyzed, resulting in three categories: 'Technosociality: Social Network in therapeutic engagement'; 'Technosociality: Social Network as an empowerment tool'; 'Technosociality: The production of knowledge. Discussion: The need for evaluation to validate socialized information is highlighted, and a debate on the effectiveness of the practical application of the knowledge acquired by the user. Conclusions: The focus on empowerment in the debate on social networks is mostly focused on the individual perspective, falling short of encouraging community participation suggested in the National Health Promotion Policy.(AU)

Introducción: En el mundo contemporáneo, el uso de tecnologías se puede configurar como obstáculo o poder para la promoción de la salud. Este estudio tiene como objetivo conocer qué se ha publicado sobre las redes sociales en la vida cotidiana de las personas en el proceso de salud y enfermedad para la promoción de la salud. Materiales y Métodos: Revisión bibliográfica integradora en cinco bases de datos, en la sección histórica de 2015 a 2019. Resultados: Se analizaron 12 artículos, resultando en tres categorías: 'Tecnosocialidad: Red social en el compromiso terapéutico'; "Tecnosocialidad: las redes sociales como herramienta de empoderamiento"; "Tecnosocialidad: la producción de conocimiento". Discusión: Es necesaria la evaluación para validar la información socializada, y debatir la efectividad de la aplicación práctica de los conocimientos adquiridos por el usuario. Conclusiones: El enfoque en el empoderamiento en el debate en las redes sociales se centra mayoritariamente en la perspectiva individual, sin llegar a fomentar la participación comunitaria sugerida en la Política Nacional de Promoción de la Salud.(AU)