Mayo Clinic Proceedings. Digital health最新文献

Objective

To investigate the operational outcomes and implementation effects of tiered cardiac telemetry monitoring in a hospital environment using an innovative technology.

Patients and Methods

The research focuses on assessing the precision, speed, and reliability of alerts generated by a wireless device in adult patients aged 18 and above, concurrently monitored by a hardwired, continuous cardiac monitor. Using an agile methodology, we tested and validated a nonhardwired, cellular-connected continuous cardiac monitor (InfoBionic MoMe) in 162 patients. A comparison was made between the wireless device and the standard hardwired system, conducted at Mayo Clinic Hospital with Institutional Review Board approval from June 6, 2022, to December 15, 2022.

Results

The study revealed a high correlation of events captured compared with the standard care model. Differences in algorithms, alarm parameters, and operational considerations impacting clinical implementation were observed. Connectivity improvements during the study reduced latency from 3-5 minutes to 30 seconds. Delayed alarms were attributed to device damage (4.5% of cases) and poor cellular connections (29% within 31-60 seconds).

Conclusion

The implementation of tiered cardiac telemetry in hospital environments, coupled with advancements in remote cardiac monitoring, supports expanded bedside telemetry capabilities and near real-time remote monitoring postdischarge. Although the study successfully validated the wireless device concept, improvements are needed before implementation for inpatient cardiac monitoring. Further research and technological enhancements can build on these findings to enhance health care practices in this domain.

The emergence of artificial intelligence (AI) and other digital solutions in health care has considerably altered the landscape of medical research and patient care. Rigorous evaluation in routine practice settings is fundamental to the ethical use of AI and consists of 3 stages of evaluations: technical performance, usability and acceptability, and health impact evaluation. Pragmatic trials often play a key role in the health impact evaluation. The current review introduces the concept of pragmatic trials, their role in AI evaluation, the challenges of conducting pragmatic trials, and strategies to mitigate the challenges. We also examined common designs used in pragmatic trials and highlighted examples of published or ongoing AI trials. As more health systems advance into learning health systems, where outcomes are continuously evaluated to refine processes and tools, pragmatic trials embedded into everyday practice, leveraging data and infrastructure from delivering health care, will be a critical part of the feedback cycle for learning and improvement.

Objective

To investigate a deep learning model for predicting hepatic decompensation using computed tomography (CT) imaging in patients with primary sclerosing cholangitis (PSC).

Patients and Methods

Retrospective cohort study involving 277 adult patients with large-duct PSC who underwent an abdominal CT scan. The portal venous phase CT images were used as input to a 3D-DenseNet121 model, which was trained using 5-fold crossvalidation to classify hepatic decompensation. To further investigate the role of each anatomic region in the model’s decision-making process, we trained the model on different sections of 3-dimensional CT images. This included training on the right, left, anterior, posterior, inferior, and superior halves of the image data set. For each half, as well as for the entire scan, we performed area under the receiving operating curve (AUROC) analysis.

Results

Hepatic decompensation occurred in 128 individuals after a median (interquartile range) of 1.5 years (142-1318 days) after the CT scan. The deep learning model exhibited promising results, with a mean ± SD AUROC of 0.89±0.04 for the baseline model. The mean ± SD AUROC for left, right, anterior, posterior, superior, and inferior halves were 0.83±0.03, 0.83±0.03, 0.82±0.09, 0.79±0.02, 0.78±0.02, and 0.76±0.04, respectively.

Conclusion

The study illustrates the potential of examining CT imaging using 3D-DenseNet121 deep learning model to predict hepatic decompensation in patients with PSC.

Artificial intelligence (AI)-enabled technology has the potential to expand access to high-quality health information and health care services. Learning how diverse users interact with technology enables improvements to the AI model and the user interface, maximizing its potential benefit for a greater number of people. This narrative describes how technology developers, academic researchers, and representatives from a community-based organization collaborated to conduct a community-centered project on emerging health technologies. Our project team comprised representatives from Stanford Medicine, Google, and Santa Clara Family Health Plan’s Blanca Alvarado Community Resource Center. We aimed to understand the usability and acceptability of an AI-driven dermatology tool among East San Jose, California, community members. Specifically, our objectives were as follows: to test a model for cross-sector research of AI-based health technology; to determine the utility of the tool in an ethnically and age-diverse population; to obtain in-depth user experience feedback from participants recruited during community events; to offer free skin health consultations; and to provide resources for receiving follow-up care. We describe a collaborative approach in which each party contributed expertise: knowledge of the community from the community health partner, clinical expertise from the academic research institution, and software and AI expertise from the technology company. Through an iterative process, we identified important community needs, including technological, language, and privacy support. Our approach allowed us to recruit and engage a diverse cohort of participants, over 70% of whom preferred a language other than English. We distill learnings from planning and executing this case study that may help other collaborators bridge the gap between academia, industry, and community in AI health care innovation.

The use of machine learning tools in health care is rapidly expanding. However, the processes that support these tools in deployment, that is, machine learning operations, are still emerging. The purpose of this work was not only to provide a comprehensive synthesis of existing literature in the field but also to identify gaps and offer insights for adoption in clinical practice. A scoping review was conducted using the MEDLINE, PubMed, Google Scholar, Embase, and Scopus databases. We used MeSH and non-MeSH search terms to identify pertinent articles, with the authors performing 2 screening phases and assigning relevance scores: 148 English language articles most salient to the review were eligible for inclusion; 98 offered the most unique information and these were supplemented by 50 additional sources, yielding 148 references. From the 148 references, we distilled 7 key topic areas, based on a synthesis of the available literature and how that aligned with practitioner needs. The 7 topic areas were machine learning model monitoring; automated retraining systems; ethics, equity, and bias; clinical workflow integration; infrastructure, human resources, and technology stack; regulatory considerations; and financial considerations. This review provides an overview of best practices and knowledge gaps of this domain in health care and identifies the strengths and weaknesses of the literature, which may be useful to health care machine learning practitioners and consumers.

Objective

To develop natural language processing (NLP) solutions for identifying patients’ unmet social needs to enable timely intervention.

Patients and Methods

Design: A retrospective cohort study with review and annotation of clinical notes to identify unmet social needs, followed by using the annotations to develop and evaluate NLP solutions.

Participants

A total of 1103 primary care patients seen at a large academic medical center from June 1, 2019, to May 31, 2021 and referred to a community health worker (CHW) program. Clinical notes and portal messages of 200 age and sex-stratified patients were sampled for annotation of unmet social needs.

Systems

Two NLP solutions were developed and compared. The first solution employed similarity-based classification on top of sentences represented as semantic embedding vectors. The second solution involved designing of terms and patterns for identifying each domain of unmet social needs in the clinical text.

Measures

Precision, recall, and f1-score of the NLP solutions.

Results

A total of 5675 clinical notes and 475 portal messages were annotated, with an inter-annotator agreement of 0.938. The best NLP solution achieved an f1-score of 0.95 and was applied to the entire CHW-referred cohort (n=1103), of whom >80% had at least 1 unmet social need within the 6 months before the first CHW referral. Financial strain and health literacy were the top 2 domains of unmet social needs across most of the sex and age strata.

Conclusion

Clinical text contains rich information about patients’ unmet social needs. The NLP can achieve good performance in identifying those needs for CHW referral and facilitate data-driven research on social determinants of health.

Hospital-based digital care and virtual care are becoming increasingly common and their reach and scope are expanding in terms of patient groups and technological sophistication. The objective of this viewpoint is to provide guidance on design and factors that can be decisive for the organization of virtual care from a hospital’s perspective. Relevant aspects to be taken into account are as follows: characteristics of the technology, in a broader sense, the nature and intensity of provider involvement and supervision, the degree of self-management by the patient and his environment, the relation and cooperation mechanisms with other providers as home care, general practitioner ’s and other specialist care, the matter of (economies of) scale and finally the uniformity of processes over geographic regions and providers. We provide suggestions for further research and future policy related to these aspects.

Objective

To analyze the voice of patients with lung diseases, compared with healthy individuals, to detect patterns capable of assessing dyspnea using artificial neural networks (ANNs).

Patients and Methods

This research consists of a cross-sectional prospective pilot study performed in a reference tertiary center, which included a group of patients with lung diseases, compared with a group of healthy individuals. Each patient’s voice was recorded in controlled rooms. The following techniques were applied to extract and select signals’ features: statistical analysis, fast Fourier transform, discrete wavelet transform and Mel-Cepstral analysis. In addition, data augmentation was used to avoid overfitting and improve the ANNs accuracy.

Results

A total of 195 voices were recorded: 131 from lung disease patients and 64 from healthy individuals, separated according to gender and age. Using data augmentation, 751 additional audio samples were generated: 501 from healthy individuals and 445 from patients with lung disease. Among male participants, 133 samples were related to lung diseases and 197 were related to healthy ones. From them, 264 audios were used for ANNs training, obtaining an accuracy of 89%. In the female group, 312 had lung diseases and 304 were healthy. Among them, 492 audios were used for training, resulting in an accuracy of 87.6%.

Conclusion

Spectral analysis techniques applied to voice recordings using ANNs have reported high accuracy in the efficient diagnosis of lung diseases when compared with healthy individuals.

Objective

To evaluate the impact of Information and Communication Technology (ICT) on the implementation of Integrated Management of Childhood Illness (IMCI) and integrated Community Case Management (iCCM) through a systematic review and meta-analysis (PROSPERO registration number: CRD42024517375).

Methods

We searched MEDLINE, EMBASE, Cochrane Library, and gray literature from January 2010 to February 2024, focusing on IMCI/iCCM-related terms (Integrated Management of Childhood Illness, IMCI, integrated Community Case Management, iCCM) and excluding non-ICT interventions. A meta-analysis synthesized the effect of ICT on clinical assessment, disease classification, therapy, and antibiotic prescription through odds ratio (OR; 95% CI) employing a random effects model for significant heterogeneity (I²>50%) and conducting subgroup analyses.

Results

Of 1005 initial studies, 44 were included, covering 8 interventions for IMCI, 7 for iCCM, and 2 for training. All digital interventions except 1 outperformed traditional paper-based methods. Pooling effect sizes from 16 studies found 5.7 OR for more complete clinical assessments (95% CI, 1.7-19.1; I², 95%); 2.0 for improved disease classification accuracy (95% CI, 0.9-4.4; I², 93%); 1.4 for more appropriate therapy (95% CI, 0.8-2.2; I², 93%); and 0.2 for reduced antibiotic use (95% CI, 0.06-0.55; I² 99%).

Conclusion

This review is the first to comprehensively quantify the effect of ICT on the implementation of IMCI/iCCM programs, confirming both the benefits and limitations of these technologies. The customization of digital tools for IMCI/iCCM can serve as a model for other health programs. As ICT increasingly supports the achievement of sustainable development goals, the effective digital interventions identified in this review can pave the way for future innovations.