Frontiers in digital health最新文献

Inherent to the experience of loneliness is a significant change of meaningful relatedness that (usually negatively) affects a person's relationship to self and others. This paper goes beyond a purely subjective-phenomenological description of individual suffering by emphasizing loneliness as a symptomatic expression of distortions of social recognition relations. Where there is loneliness, a recognition relation has changed. Most societies face an increase in loneliness among all groups of their population, and this sheds light on the reproduction conditions of social integration and inclusion. These functions are essential lifeworldly components of social cohesion and wellbeing. This study asks whether "social" AI promotes these societal success goals of social integration of lonely people. The increasing tendency to regard AI Companions (AICs) as reproducers of adequate recognition is critically discussed with this review. My skepticism requires further justification, especially as a large portion of sociopolitical prevention efforts aim to fight an increase of loneliness primarily with digital strategies. I will argue that AICs rather reproduce than sustainably reduce the pathodynamics of loneliness: loneliness gets simply "digitized."

Background: With the rise of smartphone ownership and increasing evidence to support the suitability of smartphone usage in healthcare, the light source and smartphone camera could be utilized to perform photoplethysmography (PPG) for the assessment of vital signs, such as heart rate (HR). However, until rigorous validity assessment has been conducted, PPG will have limited use in clinical settings.

Objective: We aimed to conduct a scoping review assessing the validity of resting heart rate (RHR) acquisition from PPG utilizing contact-based smartphone devices. Our four specific objectives of this scoping review were to (1) conduct a systematic search of the published literature concerning contact-based smartphone device-derived PPG, (2) map study characteristics and methodologies, (3) identify if methodological and technological advancements have been made, and (4) provide recommendations for the advancement of the investigative area.

Methods: ScienceDirect, PubMed and SPORTDiscus were searched for relevant studies between January 1st, 2007, and November 6th, 2022. Filters were applied to ensure only literature written in English were included. Reference lists of included studies were manually searched for additional eligible studies.

Results: In total 10 articles were included. Articles varied in terms of methodology including study characteristics, index measurement characteristics, criterion measurement characteristics, and experimental procedure. Additionally, there were variations in reporting details including primary outcome measure and measure of validity. However, all studies reached the same conclusion, with agreement ranging between good to very strong and correlations ranging from r = .98 to 1.

Conclusions: Smartphone applications measuring RHR derived from contact-based smartphone PPG appear to agree with gold standard electrocardiography (ECG) in healthy subjects. However, agreement was established under highly controlled conditions. Future research could investigate their validity and consider effective approaches that transfer these methods from laboratory conditions into the "real-world", in both healthy and clinical populations.

Clinical narratives commonly use acronyms without explicitly defining their long forms. This makes it difficult to automatically interpret their sense as acronyms tend to be highly ambiguous. Supervised learning approaches to their disambiguation in the clinical domain are hindered by issues associated with patient privacy and manual annotation, which limit the size and diversity of training data. In this study, we demonstrate how scientific abstracts can be utilised to overcome these issues by creating a large automatically annotated dataset of artificially simulated global acronyms. A neural network trained on such a dataset achieved the F1-score of 95% on disambiguation of acronym mentions in scientific abstracts. This network was integrated with multi-word term recognition to extract a sense inventory of acronyms from a corpus of clinical narratives on the fly. Acronym sense extraction achieved the F1-score of 74% on a corpus of radiology reports. In clinical practice, the suggested approach can be used to facilitate development of institution-specific inventories.

[This corrects the article DOI: 10.3389/fdgth.2022.966174.].

Clinical text and documents contain very rich information and knowledge in healthcare, and their processing using state-of-the-art language technology becomes very important for building intelligent systems for supporting healthcare and social good. This processing includes creating language understanding models and translating resources into other natural languages to share domain-specific cross-lingual knowledge. In this work, we conduct investigations on clinical text machine translation by examining multilingual neural network models using deep learning such as Transformer based structures. Furthermore, to address the language resource imbalance issue, we also carry out experiments using a transfer learning methodology based on massive multilingual pre-trained language models (MMPLMs). The experimental results on three sub-tasks including (1) clinical case (CC), (2) clinical terminology (CT), and (3) ontological concept (OC) show that our models achieved top-level performances in the ClinSpEn-2022 shared task on English-Spanish clinical domain data. Furthermore, our expert-based human evaluations demonstrate that the small-sized pre-trained language model (PLM) outperformed the other two extra-large language models by a large margin in the clinical domain fine-tuning, which finding was never reported in the field. Finally, the transfer learning method works well in our experimental setting using the WMT21fb model to accommodate a new language space Spanish that was not seen at the pre-training stage within WMT21fb itself, which deserves more exploitation for clinical knowledge transformation, e.g. to investigate into more languages. These research findings can shed some light on domain-specific machine translation development, especially in clinical and healthcare fields. Further research projects can be carried out based on our work to improve healthcare text analytics and knowledge transformation. Our data is openly available for research purposes at: https://github.com/HECTA-UoM/ClinicalNMT.

Cardiac rehabilitation (CR) represents an important steppingstone for many cardiac patients into a more heart-healthy lifestyle to prevent premature death and improve quality of life years. However, CR is underutilized worldwide. In order to support the development of targeted digital health interventions, this narrative review (I) provides understandings of factors influencing CR utilization from a behavioral perspective, (II) discusses the potential of digital health technologies (DHTs) to address barriers and reinforce facilitators to CR, and (III) outlines how DHTs could incorporate shared decision-making to support CR utilization. A narrative search of reviews in Web of Science and PubMed was conducted to summarize evidence on factors influencing CR utilization. The factors were grouped according to the Behaviour Change Wheel. Patients' Capability for participating in CR is influenced by their disease knowledge, awareness of the benefits of CR, information received, and interactions with healthcare professionals (HCP). The Opportunity to attend CR is impacted by healthcare system factors such as referral processes and HCPs' awareness, as well as personal resources including logistical challenges and comorbidities. Patients' Motivation to engage in CR is affected by emotions, factors such as gender, age, self-perception of fitness and control over the cardiac condition, as well as peer comparisons. Based on behavioral factors, this review identified intervention functions that could support an increase of CR uptake: Future DHTs aiming to support CR utilization may benefit from incorporating information for patients and HCP education, enabling disease management and collaboration along the patient pathway, and enhancing social support from relatives and peers. To conclude, considerations are made how future innovations could incorporate such functions.

Trustworthy medical AI requires transparency about the development and testing of underlying algorithms to identify biases and communicate potential risks of harm. Abundant guidance exists on how to achieve transparency for medical AI products, but it is unclear whether publicly available information adequately informs about their risks. To assess this, we retrieved public documentation on the 14 available CE-certified AI-based radiology products of the II b risk category in the EU from vendor websites, scientific publications, and the European EUDAMED database. Using a self-designed survey, we reported on their development, validation, ethical considerations, and deployment caveats, according to trustworthy AI guidelines. We scored each question with either 0, 0.5, or 1, to rate if the required information was "unavailable", "partially available," or "fully available." The transparency of each product was calculated relative to all 55 questions. Transparency scores ranged from 6.4% to 60.9%, with a median of 29.1%. Major transparency gaps included missing documentation on training data, ethical considerations, and limitations for deployment. Ethical aspects like consent, safety monitoring, and GDPR-compliance were rarely documented. Furthermore, deployment caveats for different demographics and medical settings were scarce. In conclusion, public documentation of authorized medical AI products in Europe lacks sufficient public transparency to inform about safety and risks. We call on lawmakers and regulators to establish legally mandated requirements for public and substantive transparency to fulfill the promise of trustworthy AI for health.

The use of artificial intelligence (AI) and machine learning (ML) in anesthesiology and perioperative medicine is quickly becoming a mainstay of clinical practice. Anesthesiology is a data-rich medical specialty that integrates multitudes of patient-specific information. Perioperative medicine is ripe for applications of AI and ML to facilitate data synthesis for precision medicine and predictive assessments. Examples of emergent AI models include those that assist in assessing depth and modulating control of anesthetic delivery, event and risk prediction, ultrasound guidance, pain management, and operating room logistics. AI and ML support analyzing integrated perioperative data at scale and can assess patterns to deliver optimal patient-specific care. By exploring the benefits and limitations of this technology, we provide a basis of considerations for evaluating the adoption of AI models into various anesthesiology workflows. This analysis of AI and ML in anesthesiology and perioperative medicine explores the current landscape to understand better the strengths, weaknesses, opportunities, and threats (SWOT) these tools offer.