Telehealth With Comprehensive Live-Fed Real-World Data as a Patient Care Platform for Lung Cancer: Implementation and Evaluation Study.

BACKGROUND: Telehealth has emerged as a popular channel for providing outpatient services in many countries. However, the majority of telehealth systems focus on operational functions and offer only a sectional patient journey at most. Experiences with incorporating longitudinal real-world medical record data into telehealth are valuable but have not been widely shared. The feasibility and usability of such a telehealth platform, with comprehensive, real-world data via a live feed, for cancer patient care are yet to be studied. OBJECTIVE: The primary purpose of this study is to understand the feasibility and usability of cancer patient care using a telehealth platform with longitudinal, real-world data via a live feed as a supplement to hospital electronic medical record systems specifically from physician's perspective. METHODS: A telehealth platform was constructed and launched for both physicians and patients. Real-world data were collected and curated using a comprehensive data model. Physician activities on the platform were recorded as system logs and analyzed. In February 2023, a survey was conducted among the platform's registered physicians to assess the specific areas of patient care and to quantify their before and after experiences, including the number of patients managed, time spent, dropout rate, visit rate, and follow-up data. Descriptive and inferential statistical analyses were performed on the data sets. RESULTS: Over a period of 15 months, 16,035 unique users (13,888 patients, 1539 friends and family members, and 174 physician groups with 608 individuals) registered on the platform. More than 382,000 messages including text, reminders, and pictures were generated by physicians when communicating with patients. The survey was completed by 78 group leaders (45% of the 174 physician groups). Of the participants, 84% (65.6/78; SD 8.7) reported a positive experience, with efficient communication, remote supervision, quicker response to questions, adverse event prevention, more complete follow-up data, patient risk reduction, cross-organization collaboration, and a reduction in in-person visits. The majority of the participants (59/78, 76% to 76/78, 97.4%) estimated improvements in time spent, number of patients managed, the drop-off rate, and access to medical history, with the average ranging from 57% to 105%. When compared with prior platforms, responses from physicians indicated better experiences in terms of time spent, the drop-off rate, and medical history, while the number of patients managed did not significantly change. CONCLUSIONS: This study suggests that a telehealth platform, equipped with comprehensive, real-world data via a live feed, is feasible and effective for cancer patient care. It enhances inpatient management by improving time efficiencies, reducing drop-off rates, and providing easy access to medical history. Moreover, it fosters a positive experience in physician-patient interactions.

Regioselective 5-exo-dig (halo)cyclization of N-propargyloxycarbonyl guanidine derivatives under mild conditions.

A highly regioselective 5-exo-dig cyclization of aromatic N-propargyloxycarbonyl guanidines was developed via an Ag(I)-catalyzed intramolecular hydroamination reaction. This method features a fast reaction rate and mild reaction conditions. Furthermore, it was extended to access halogenated analogues via a one-pot Ag(I)-catalyzed bromocyclization reaction or an I2-mediated iodocyclization reaction with high E/Z selectivity.

Prediction of CRISPR-Cas9 off-target activities with mismatches and indels based on hybrid neural network.

The CRISPR/Cas9 system has significantly advanced the field of gene editing, yet its clinical application is constrained by the considerable challenge of off-target effects. Although numerous deep learning models for off-target prediction have been proposed, most struggle to effectively extract the nuanced features of guide RNA (gRNA) and DNA sequence pairs and to mitigate information loss during data transmission within the model. To address these limitations, we introduce a novel Hybrid Neural Network (HNN) model that employs a parallelized network structure to fully extract pertinent features from different positions and types of bases in the sequence to minimize information loss. Notably, this study marks the first application of word embedding techniques to extract information from sequence pairs that contain insertions and deletions (Indels). Comprehensive evaluation across diverse datasets indicates that our proposed model outperforms existing state-of-the-art prediction methods in off-target prediction. The datasets and source codes supporting this study can be found at https://github.com/Yang-k955/CRISPR-HW.

ReACT (redox-activated chemical tagging) chemistry enables direct derivatization and fluorescence detection of S-adenosyl-L-homocysteine (SAH).

S-Adenosyl-L-homocysteine (SAH) is a universal byproduct and product inhibitor of the methyltransferase-catalyzed methylation reaction. Here based on ReACT (redox-activated chemical tagging) chemistry, direct derivatization and fluorescence measurement of SAH were achieved with features such as mild reaction conditions and simple operation.

Facile access to S-methyl dithiocarbamates with sulfonium or sulfoxonium iodide as a methylation reagent.

Efficient access to S-methyl dithiocarbamates was achieved with sulfonium or sulfoxonium iodide as a methylation reagent. This method is reliable for the synthesis of dithiocarbamates from primary or secondary amines, with sulfoxonium iodide demonstrating more robust methylation capability than sulfonium iodide. Moreover, it also enables facile access to S-trideuteromethyl dithiocarbamates via sulfoxonium metathesis between sulfoxonium iodide and DMSO-d6 with high yields.

Use of Clinical Data Interchange Standards Consortium (CDISC) Standards for Real-world Data: Expert Perspectives From a Qualitative Delphi Survey.

BACKGROUND: Real-world data (RWD) and real-world evidence (RWE) are playing increasingly important roles in clinical research and health care decision-making. To leverage RWD and generate reliable RWE, data should be well defined and structured in a way that is semantically interoperable and consistent across stakeholders. The adoption of data standards is one of the cornerstones supporting high-quality evidence for the development of clinical medicine and therapeutics. Clinical Data Interchange Standards Consortium (CDISC) data standards are mature, globally recognized, and heavily used by the pharmaceutical industry for regulatory submissions. The CDISC RWD Connect Initiative aims to better understand the barriers to implementing CDISC standards for RWD and to identify the tools and guidance needed to more easily implement them. OBJECTIVE: The aim of this study is to understand the barriers to implementing CDISC standards for RWD and to identify the tools and guidance that may be needed to implement CDISC standards more easily for this purpose. METHODS: We conducted a qualitative Delphi survey involving an expert advisory board with multiple key stakeholders, with 3 rounds of input and review. RESULTS: Overall, 66 experts participated in round 1, 56 in round 2, and 49 in round 3 of the Delphi survey. Their inputs were collected and analyzed, culminating in group statements. It was widely agreed that the standardization of RWD is highly necessary, and the primary focus should be on its ability to improve data sharing and the quality of RWE. The priorities for RWD standardization included electronic health records, such as data shared using Health Level 7 Fast Health care Interoperability Resources (FHIR), and the data stemming from observational studies. With different standardization efforts already underway in these areas, a gap analysis should be performed to identify the areas where synergies and efficiencies are possible and then collaborate with stakeholders to create or extend existing mappings between CDISC and other standards, controlled terminologies, and models to represent data originating across different sources. CONCLUSIONS: There are many ongoing data standardization efforts around human health data-related activities, each with different definitions, levels of granularity, and purpose. Among these, CDISC has been successful in standardizing clinical trial-based data for regulation worldwide. However, the complexity of the CDISC standards and the fact that they were developed for different purposes, combined with the lack of awareness and incentives to use a new standard and insufficient training and implementation support, are significant barriers to setting up the use of CDISC standards for RWD. The collection and dissemination of use cases, development of tools and support systems for the RWD community, and collaboration with other standards development organizations are potential steps forward. Using CDISC will help link clinical trial data and RWD and promote innovation in health data science.

MfeCNN: Mixture Feature Embedding Convolutional Neural Network for Data Mapping.

Data mapping plays an important role in data integration and exchanges among institutions and organizations with different data standards. However, traditional rule-based approaches and machine learning methods fail to achieve satisfactory results for the data mapping problem. In this paper, we propose a novel and sophisticated deep learning framework for data mapping called mixture feature embedding convolutional neural network (MfeCNN). The MfeCNN model converts the data mapping task to a multiple classification problem. In the model, we incorporated multimodal learning and multiview embedding into a CNN for mixture feature tensor generation and classification prediction. Multimodal features were extracted from various linguistic spaces with a medical natural language processing package. Then, powerful feature embeddings were learned by using the CNN. As many as 10 classes could be simultaneously classified by a softmax prediction layer based on multiview embedding. MfeCNN achieved the best results on unbalanced data (average F1 score, 82.4%) among the traditional state-of-the-art machine learning models and CNN without mixture feature embedding. Our model also outperformed a very deep CNN with 29 layers, which took free texts as inputs. The combination of mixture feature embedding and a deep neural network can achieve high accuracy for data mapping and multiple classification.