-
JMIR AI Feb 2024The use of artificial intelligence (AI) for pain assessment has the potential to address historical challenges in infant pain assessment. There is a dearth of...
BACKGROUND
The use of artificial intelligence (AI) for pain assessment has the potential to address historical challenges in infant pain assessment. There is a dearth of information on the perceived benefits and barriers to the implementation of AI for neonatal pain monitoring in the neonatal intensive care unit (NICU) from the perspective of health care professionals (HCPs) and parents. This qualitative analysis provides novel data obtained from 2 large tertiary care hospitals in Canada and the United Kingdom.
OBJECTIVE
The aim of the study is to explore the perspectives of HCPs and parents regarding the use of AI for pain assessment in the NICU.
METHODS
In total, 20 HCPs and 20 parents of preterm infants were recruited and consented to participate from February 2020 to October 2022 in interviews asking about AI use for pain assessment in the NICU, potential benefits of the technology, and potential barriers to use.
RESULTS
The 40 participants included 20 HCPs (17 women and 3 men) with an average of 19.4 (SD 10.69) years of experience in the NICU and 20 parents (mean age 34.4, SD 5.42 years) of preterm infants who were on average 43 (SD 30.34) days old. Six themes from the perspective of HCPs were identified: regular use of technology in the NICU, concerns with regard to AI integration, the potential to improve patient care, requirements for implementation, AI as a tool for pain assessment, and ethical considerations. Seven parent themes included the potential for improved care, increased parental distress, support for parents regarding AI, the impact on parent engagement, the importance of human care, requirements for integration, and the desire for choice in its use. A consistent theme was the importance of AI as a tool to inform clinical decision-making and not replace it.
CONCLUSIONS
HCPs and parents expressed generally positive sentiments about the potential use of AI for pain assessment in the NICU, with HCPs highlighting important ethical considerations. This study identifies critical methodological and ethical perspectives from key stakeholders that should be noted by any team considering the creation and implementation of AI for pain monitoring in the NICU.
PubMed: 38875686
DOI: 10.2196/51535 -
JMIR AI Jun 2024The COVID-19 pandemic had a devastating global impact. In the United States, there were >98 million COVID-19 cases and >1 million resulting deaths. One consequence of...
BACKGROUND
The COVID-19 pandemic had a devastating global impact. In the United States, there were >98 million COVID-19 cases and >1 million resulting deaths. One consequence of COVID-19 infection has been post-COVID-19 condition (PCC). People with this syndrome, colloquially called long haulers, experience symptoms that impact their quality of life. The root cause of PCC and effective treatments remains unknown. Many long haulers have turned to social media for support and guidance.
OBJECTIVE
In this study, we sought to gain a better understanding of the long hauler experience by investigating what has been discussed and how information about long haulers is perceived on social media. We specifically investigated the following: (1) the range of symptoms that are discussed, (2) the ways in which information about long haulers is perceived, (3) informational and emotional support that is available to long haulers, and (4) discourse between viewers and creators. We selected YouTube as our data source due to its popularity and wide range of audience.
METHODS
We systematically gathered data from 3 different types of content creators: medical sources, news sources, and long haulers. To computationally understand the video content and viewers' reactions, we used Biterm, a topic modeling algorithm created specifically for short texts, to analyze snippets of video transcripts and all top-level comments from the comment section. To triangulate our findings about viewers' reactions, we used the Valence Aware Dictionary and Sentiment Reasoner to conduct sentiment analysis on comments from each type of content creator. We grouped the comments into positive and negative categories and generated topics for these groups using Biterm. We then manually grouped resulting topics into broader themes for the purpose of analysis.
RESULTS
We organized the resulting topics into 28 themes across all sources. Examples of medical source transcript themes were Explanations in layman's terms and Biological explanations. Examples of news source transcript themes were Negative experiences and handling the long haul. The 2 long hauler transcript themes were Taking treatments into own hands and Changes to daily life. News sources received a greater share of negative comments. A few themes of these negative comments included Misinformation and disinformation and Issues with the health care system. Similarly, negative long hauler comments were organized into several themes, including Disillusionment with the health care system and Requiring more visibility. In contrast, positive medical source comments captured themes such as Appreciation of helpful content and Exchange of helpful information. In addition to this theme, one positive theme found in long hauler comments was Community building.
CONCLUSIONS
The results of this study could help public health agencies, policy makers, organizations, and health researchers understand symptomatology and experiences related to PCC. They could also help these agencies develop their communication strategy concerning PCC.
PubMed: 38875666
DOI: 10.2196/54501 -
JMIR AI May 2024Large language models (LLMs) have the potential to support promising new applications in health informatics. However, practical data on sample size considerations for...
BACKGROUND
Large language models (LLMs) have the potential to support promising new applications in health informatics. However, practical data on sample size considerations for fine-tuning LLMs to perform specific tasks in biomedical and health policy contexts are lacking.
OBJECTIVE
This study aims to evaluate sample size and sample selection techniques for fine-tuning LLMs to support improved named entity recognition (NER) for a custom data set of conflicts of interest disclosure statements.
METHODS
A random sample of 200 disclosure statements was prepared for annotation. All "PERSON" and "ORG" entities were identified by each of the 2 raters, and once appropriate agreement was established, the annotators independently annotated an additional 290 disclosure statements. From the 490 annotated documents, 2500 stratified random samples in different size ranges were drawn. The 2500 training set subsamples were used to fine-tune a selection of language models across 2 model architectures (Bidirectional Encoder Representations from Transformers [BERT] and Generative Pre-trained Transformer [GPT]) for improved NER, and multiple regression was used to assess the relationship between sample size (sentences), entity density (entities per sentence [EPS]), and trained model performance (F-score). Additionally, single-predictor threshold regression models were used to evaluate the possibility of diminishing marginal returns from increased sample size or entity density.
RESULTS
Fine-tuned models ranged in topline NER performance from F-score=0.79 to F-score=0.96 across architectures. Two-predictor multiple linear regression models were statistically significant with multiple R ranging from 0.6057 to 0.7896 (all P<.001). EPS and the number of sentences were significant predictors of F-scores in all cases ( P<.001), except for the GPT-2_large model, where EPS was not a significant predictor (P=.184). Model thresholds indicate points of diminishing marginal return from increased training data set sample size measured by the number of sentences, with point estimates ranging from 439 sentences for RoBERTa_large to 527 sentences for GPT-2_large. Likewise, the threshold regression models indicate a diminishing marginal return for EPS with point estimates between 1.36 and 1.38.
CONCLUSIONS
Relatively modest sample sizes can be used to fine-tune LLMs for NER tasks applied to biomedical text, and training data entity density should representatively approximate entity density in production data. Training data quality and a model architecture's intended use (text generation vs text processing or classification) may be as, or more, important as training data volume and model parameter size.
PubMed: 38875593
DOI: 10.2196/52095 -
JMIR AI Mar 2024Large curated data sets are required to leverage speech-based tools in health care. These are costly to produce, resulting in increased interest in data sharing. As...
BACKGROUND
Large curated data sets are required to leverage speech-based tools in health care. These are costly to produce, resulting in increased interest in data sharing. As speech can potentially identify speakers (ie, voiceprints), sharing recordings raises privacy concerns. This is especially relevant when working with patient data protected under the Health Insurance Portability and Accountability Act.
OBJECTIVE
We aimed to determine the reidentification risk for speech recordings, without reference to demographics or metadata, in clinical data sets considering both the size of the search space (ie, the number of comparisons that must be considered when reidentifying) and the nature of the speech recording (ie, the type of speech task).
METHODS
Using a state-of-the-art speaker identification model, we modeled an adversarial attack scenario in which an adversary uses a large data set of identified speech (hereafter, the known set) to reidentify as many unknown speakers in a shared data set (hereafter, the unknown set) as possible. We first considered the effect of search space size by attempting reidentification with various sizes of known and unknown sets using VoxCeleb, a data set with recordings of natural, connected speech from >7000 healthy speakers. We then repeated these tests with different types of recordings in each set to examine whether the nature of a speech recording influences reidentification risk. For these tests, we used our clinical data set composed of recordings of elicited speech tasks from 941 speakers.
RESULTS
We found that the risk was inversely related to the number of comparisons an adversary must consider (ie, the search space), with a positive linear correlation between the number of false acceptances (FAs) and the number of comparisons (r=0.69; P<.001). The true acceptances (TAs) stayed relatively stable, and the ratio between FAs and TAs rose from 0.02 at 1 × 10 comparisons to 1.41 at 6 × 10 comparisons, with a near 1:1 ratio at the midpoint of 3 × 10 comparisons. In effect, risk was high for a small search space but dropped as the search space grew. We also found that the nature of a speech recording influenced reidentification risk, with nonconnected speech (eg, vowel prolongation: FA/TA=98.5; alternating motion rate: FA/TA=8) being harder to identify than connected speech (eg, sentence repetition: FA/TA=0.54) in cross-task conditions. The inverse was mostly true in within-task conditions, with the FA/TA ratio for vowel prolongation and alternating motion rate dropping to 0.39 and 1.17, respectively.
CONCLUSIONS
Our findings suggest that speaker identification models can be used to reidentify participants in specific circumstances, but in practice, the reidentification risk appears small. The variation in risk due to search space size and type of speech task provides actionable recommendations to further increase participant privacy and considerations for policy regarding public release of speech recordings.
PubMed: 38875581
DOI: 10.2196/52054 -
JMIR AI Jun 2023With the growing volume and complexity of laboratory repositories, it has become tedious to parse unstructured data into structured and tabulated formats for secondary...
BACKGROUND
With the growing volume and complexity of laboratory repositories, it has become tedious to parse unstructured data into structured and tabulated formats for secondary uses such as decision support, quality assurance, and outcome analysis. However, advances in natural language processing (NLP) approaches have enabled efficient and automated extraction of clinically meaningful medical concepts from unstructured reports.
OBJECTIVE
In this study, we aimed to determine the feasibility of using the NLP model for information extraction as an alternative approach to a time-consuming and operationally resource-intensive handcrafted rule-based tool. Therefore, we sought to develop and evaluate a deep learning-based NLP model to derive knowledge and extract information from text-based laboratory reports sourced from a provincial laboratory repository system.
METHODS
The NLP model, a hierarchical multilabel classifier, was trained on a corpus of laboratory reports covering testing for 14 different respiratory viruses and viral subtypes. The corpus includes 87,500 unique laboratory reports annotated by 8 subject matter experts (SMEs). The classification task involved assigning the laboratory reports to labels at 2 levels: 24 fine-grained labels in level 1 and 6 coarse-grained labels in level 2. A "label" also refers to the status of a specific virus or strain being tested or detected (eg, influenza A is detected). The model's performance stability and variation were analyzed across all labels in the classification task. Additionally, the model's generalizability was evaluated internally and externally on various test sets.
RESULTS
Overall, the NLP model performed well on internal, out-of-time (pre-COVID-19), and external (different laboratories) test sets with microaveraged F-scores >94% across all classes. Higher precision and recall scores with less variability were observed for the internal and pre-COVID-19 test sets. As expected, the model's performance varied across categories and virus types due to the imbalanced nature of the corpus and sample sizes per class. There were intrinsically fewer classes of viruses being detected than those tested; therefore, the model's performance (lowest F-score of 57%) was noticeably lower in the detected cases.
CONCLUSIONS
We demonstrated that deep learning-based NLP models are promising solutions for information extraction from text-based laboratory reports. These approaches enable scalable, timely, and practical access to high-quality and encoded laboratory data if integrated into laboratory information system repositories.
PubMed: 38875570
DOI: 10.2196/44835 -
Revista Brasileira de Psiquiatria (Sao... Jun 2024This is the second part of the Brazilian S20 mental health report. The mental health working group is dedicated to leveraging scientific insights to foster innovation...
This is the second part of the Brazilian S20 mental health report. The mental health working group is dedicated to leveraging scientific insights to foster innovation and propose actionable recommendations for implementation in Brazil and participating countries. In addressing the heightened mental health challenges in a post-pandemic world, strategies should encompass several key elements. This second part of the S20 Brazilian Mental Health Report will delve into some of these elements, including: the impact of climate change on mental health, the influence of environmental factors on neurodevelopmental disorders, the intersection of serious mental illness and precision psychiatry, the co-occurrence of physical and mental disorders, advancements in biomarkers for mental disorders, the utilization of digital health in mental healthcare, the implementation of interventional psychiatry, and the design of innovative mental health systems integrating principles of innovation and human rights. Reassessing the treatment settings for psychiatric patients within general hospitals, where their mental health and physical needs are addressed should be prioritized in mental health policy. As the S20 countries prepare for the future, we need principles that stand to advance innovation, uphold human rights, and strive for the highest standards in mental health care.
PubMed: 38875470
DOI: 10.47626/1516-4446-2024-3707 -
PloS One 2024The prevalence of depression in U.S. adults during the COVID-19 pandemic has been high overall and particularly high among persons with fewer assets. Building on...
The prevalence of depression in U.S. adults during the COVID-19 pandemic has been high overall and particularly high among persons with fewer assets. Building on previous work on assets and mental health, we document the burden of depression in groups based on income and savings during the first two years of the COVID-19 pandemic. Using a nationally representative, longitudinal panel study of U.S. adults (N = 1,271) collected in April-May 2020 (T1), April-May 2021 (T2), and April-May 2022 (T3), we estimated the adjusted odds of reporting probable depression at any time during the COVID-19 pandemic with generalized estimating equations (GEE). We explored probable depression-defined as a score of ≥10 on the Patient Health Questionnaire-9 (PHQ-9)-by four asset groups, defined by median income (≥$65,000) and savings (≥$20,000) categories. The prevalence of probable depression was consistently high in Spring 2020, Spring 2021, and Spring 2022 with 27.9% of U.S. adults reporting probable depression in Spring 2022. We found that there were four distinct asset groups that experienced different depression trajectories over the COVID-19 pandemic. Low income-low savings asset groups had the highest level of probable depression across time, reporting 3.7 times the odds (95% CI: 2.6, 5.3) of probable depression at any time relative to high income-high savings asset groups. While probable depression stayed relatively stable across time for most groups, the low income-low savings group reported significantly higher levels of probable depression at T2, compared to T1, and the high income-low savings group reported significantly higher levels of probable depression at T3 than T1. The weighted average of probable depression across time was 42.9% for low income-low savings groups, 24.3% for high income-low savings groups, 19.4% for low income-high savings groups, and 14.0% for high income-high savings groups. Efforts to ameliorate both savings and income may be necessary to mitigate the mental health consequences of pandemics.
Topics: Humans; COVID-19; Depression; Income; Longitudinal Studies; Male; Adult; Female; Middle Aged; Mental Health; United States; Pandemics; Aged; Young Adult; SARS-CoV-2; Prevalence; Adolescent
PubMed: 38875280
DOI: 10.1371/journal.pone.0304549 -
Australasian Psychiatry : Bulletin of... Jun 2024Increasing numbers of healthcare data breaches highlight the need for structured organisational responses to protect patients, trainees and psychiatrists against...
Increasing numbers of healthcare data breaches highlight the need for structured organisational responses to protect patients, trainees and psychiatrists against identity theft and blackmail. Evidence-based guidance that is informed by the COVID-19 pandemic response includes: timely and reliable information tailored to users' safety, encouragement to take protective action, and access to practical and psychological support. For healthcare organisations which have suffered a data breach, insurance essentially improves access to funded cyber security responses, risk communication and public relations. Patients, trainees and psychiatrists need specific advice on protective measures. Healthcare data security legislative reform is urgently needed.
PubMed: 38875170
DOI: 10.1177/10398562241261818 -
JAMA Health Forum Jun 2024
Topics: Humans; Cardiovascular Diseases; Private Sector; United States
PubMed: 38874961
DOI: 10.1001/jamahealthforum.2024.1478 -
Eastern Mediterranean Health Journal =... May 2024The private healthcare sector is a critical stakeholder in the provision of health care services, including noncommunicable diseases (NCDs), and engagement with the...
BACKGROUND
The private healthcare sector is a critical stakeholder in the provision of health care services, including noncommunicable diseases (NCDs), and engagement with the sector is increasingly being advocated in efforts to achieve Universal Health Coverage.
AIM
This study was conducted to explore the role of the private health sector in delivering NCD-related primary care services in selected countries of the WHO Eastern Mediterranean Region (EMR): Jordan, Oman, Pakistan, Sudan, and the Syrian Arab Republic.
METHODS
We adapted the analytical framework for this study from the "Framework for action to implement the United Nations political declaration on noncommunicable diseases". We conducted a desk review to gather evidence, identify gaps and provide direction for the subsequent stakeholder interviews. Key informant interview respondents were selected using the snowball sampling method. Data from the interviews were analysed using MAXQDA, version 2020.
RESULTS
We reviewed 26 documents and interviewed 19 stakeholders in Jordan, Oman, Pakistan, Sudan and the Syrian Arab Republic. Our results indicated increasing advocacy at the regional and national levels to align the private and public health sectors, just as there were efforts to reduce the risk factors for NCDs by implementing tobacco laws, introducing food labelling guidelines, increasing taxes on soft drinks, and promoting the healthy cities approach. NCDs health information systems varied widely among the countries, from being organized and developed to having poor recordkeeping. The private health sector is the predominant provider of care at primary level in most of the EMR countries.
CONCLUSION
Increased collaboration between the public and private sectors is essential for better management of NCDs in the EMR. Governments need to strengthen regulation and defragment the private health sector and harness the sector's strengths as part of efforts to achieve national health targets, NCD goals and Universal Health Coverage.
Topics: Noncommunicable Diseases; Humans; Private Sector; Primary Health Care; Mediterranean Region; Middle East; Interviews as Topic; Jordan
PubMed: 38874292
DOI: 10.26719/2024.30.5.333