Biomedical subjects

Guilherme Del Fiol

Publications and source records attributed to Guilherme Del Fiol.

11 recordsLinked to original sources

PubMed2026

The Impact of Chatbot Type and Normative Messaging on Chatbot Usage Intention Based on the Health Technology Acceptance Model: Randomized Controlled Trial.

BACKGROUND: Digital health tools, such as health chatbots, may improve access to scalable health support, but adoption remains inconsistent. Existing models do not fully integrate technology acceptance factors with health motivation factors relevant to digital health use. OBJECTIVE: This study proposed and tested the health technology acceptance model and examined whether normative message framing and chatbot type were associated with health motivation, technology acceptance, and intention to use a health chatbot. METHODS: In October 2025, we conducted a 4 × 2 between-participants online experiment with 1000 US adults recruited from a nationally representative YouGov panel. Participants were randomized to 1 of 8 conditions varying norm message type (self-oriented, peer-oriented, expert-oriented, or family-oriented) and chatbot type (AI-powered or rule-based) in a cancer prevention and genetic risk information scenario. Outcomes included descriptive norms, injunctive norms, perceived susceptibility, perceived severity, perceived benefits, self-efficacy, perceived ease of use, trust, privacy concerns, and usage intention. Data were analyzed using a multivariate ANOVA with Bonferroni-adjusted post hoc tests and multiple linear regression. RESULTS: Peer-oriented and family-oriented messages produced higher usage intention than expert-oriented messages, and peer-oriented messages also increased descriptive norms, injunctive norms, self-efficacy, and trust. AI-powered chatbots were associated with higher usage intention (P=.02) and greater trust (P=.008) than rule-based chatbots. In regression analyses, the model explained 50.8% of the variance in usage intention. Usage intention was positively associated with descriptive norms (β=0.087; P=.003), injunctive norms (β=0.078; P=.009), perceived susceptibility (β=0.051; P=.03), perceived benefits (β=0.253; P<.001), and trust (β=0.33; P<.001), and negatively associated with perceived severity (β=-0.047; P=.049) and privacy concerns (β=-0.11; P<.001). Perceived ease of use and self-efficacy were not significant predictors. CONCLUSIONS: The health technology acceptance model was a useful framework for explaining the intention to use a health chatbot by combining technology acceptance and health motivation constructs. Both social design features and chatbot design features shaped adoption-related beliefs, with peer-oriented and family-oriented framing and AI-powered chatbots showing particular promise. Trust and privacy concerns remained central determinants of intended use.

Humans↗

PubMed2006

Integration of interdisciplinary guidelines with clinical applications: Current and future scenarios.

Intermountain Healthcare (Intermountain) has developed a referential free-text interdisciplinary document collection to define standards for patient care. In order to improve access and use in bedside clinician workflow, Intermountain converted the document collection into a ubiquitous web-compatible format. The content has been structured using XML so it can be utilized by Intermountain's existing clinical applications, as well as positioning it for use in future deployed applications. It has become evident the strategy of structuring the content in this web-compatible format will support its use to drive current and future system functionality. As Intermountain moves forward in creating and deploying clinical applications, it is important to maintain and improve the current collection structure, sustaining the efficient integration and use of the content necessary to support clinician workflow and to meet information needs.

Documentation↗

PubMed2006

Knowledge management strategies: Enhancing knowledge transfer to clinicians and patients.

At Intermountain Healthcare (Intermountain), executive clinical content experts are responsible for disseminating consistent evidence-based clinical content throughout the enterprise at the point-of-care. With a paper-based system it was difficult to ensure that current information was received and was being used in practice. With electronic information systems multiple applications were supplying similar, but different, vendor-licensed and locally-developed content. These issues influenced the consistency of clinical practice within the enterprise, jeopardized patient and clinician safety, and exposed the enterprise and its employees to potential financial penalties. In response to these issues Intermountain is developing a knowledge management infrastructure providing tools and services to support clinical content development, deployment, maintenance, and communication. The Intermountain knowledge management philosophy includes strategies guiding clinicians and consumers of health information to relevant best practice information with the intention of changing behaviors. This paper presents three case studies describing different information management problems identified within Intermountain, methods used to solve the problems, implementation challenges, and the current status of each project.

Decision Support Systems, Clinical↗

PubMed2005

KAT: a flexible XML-based knowledge authoring environment.

As part of an enterprise effort to develop new clinical information systems at Intermountain Health Care, the authors have built a knowledge authoring tool that facilitates the development and refinement of medical knowledge content. At present, users of the application can compose order sets and an assortment of other structured clinical knowledge documents based on XML schemas. The flexible nature of the application allows the immediate authoring of new types of documents once an appropriate XML schema and accompanying Web form have been developed and stored in a shared repository. The need for a knowledge acquisition tool stems largely from the desire for medical practitioners to be able to write their own content for use within clinical applications. We hypothesize that medical knowledge content for clinical use can be successfully created and maintained through XML-based document frameworks containing structured and coded knowledge.

Artificial Intelligence↗

PubMed2005

An XML model that enables the development of complex order sets by clinical experts.

Medication errors are significant and well-known problems in health care. Despite the evidence supporting the use of computerized physician order entering (CPOE) to help reduce medication errors, only a small number of hospitals in the U.S. have successfully implemented a CPOE system. Different authors have indicated that the utilization of order sets derived from best-practice standards can reduce medication errors and improve physicians' acceptance of CPOE systems. However, a variety of issues related to the development and continuous maintenance of best-practice order sets still need to be understood. This paper presents a model that supports an order set development process driven by clinical experts. Model requirements and details are presented and discussed.

Computer Simulation↗

PubMed2005

Customized document validation to support a flexible XML-based knowledge management framework.

This paper describes a validation architecture used within Intermountain Health Care's Clinical Knowledge Repository (CKR). The architecture provides additional functionality that complements XML Schema validation, producing user-friendly error messages and enabling validation rules reuse. The validation architecture helps document authors to fix their own errors. As a result, less than 1% of all documents in the CKR are considered invalid.

Information Management↗

PubMed2005

Development and validation of XML-based calculations within order sets.

We have developed two XML Schemas to support the implementation of calculations within XML-based order sets. The models support the representation of variable-based algorithms and include data elements designed to support ancillary functions such as input range checking, rounding, and minimum/maximum value constraints. Two clinicians successfully authored 57 unique calculated orders derived from a set of 11 calculations using the models within our authoring environment. The resultant knowledge base content was subsequently tested and found to produce the desired results within the electronic physician order entry environment.

Algorithms↗

PubMed2005

Using XML technologies to organize electronic reference resources.

Provision of access to reference electronic resources to clinicians is becoming increasingly important. We have created a framework for librarians to manage access to these resources at an enterprise level, rather than at the individual hospital libraries. We describe initial project requirements, implementation details, and some preliminary results.

Information Storage and Retrieval↗

PubMed2005

Integration of HTML documents into an XML-based knowledge repository.

The Emergency Patient Instruction Generator (EPIG) is an electronic content compiler / viewer / editor developed by Intermountain Health Care. The content is vendor-licensed HTML patient discharge instructions. This work describes the process by which discharge instructions where converted from ASCII-encoded HTML to XML, then loaded to a database for use by EPIG.

Database Management Systems↗

PubMed2004

Exploratory case method to determine the frequency of redundant orders within manually consolidated order lists.

A computerized provider order entry (CPOE) system can provide an efficient means of retrieving and consolidating order lists from multiple electronic clinical practice standards and protocols. However, the consolidated order list may contain exact duplicate or overlapping orders. Benner's framework for levels of nursing expertise can be used to explicate the variability of the nurse's responses to redundancies in order lists and the potential compromise to patient safety. An exploratory case method was performed to consolidate 74 orders from 11 sources. The consolidated order list contained 35% fewer orders after the redundant orders were removed. Our work has shown that many redundant orders may arise by consolidating order lists from multiple electronic standards. It is imperative that consolidated electronic order lists be manageable by the nurse according to their level of clinical and computer expertise, and that redundant orders are resolved before being displayed to the nurse.

Humans↗

PubMed2003

Application of an XML-based document framework to knowledge content authoring and clinical information system development.

The role of XML in health care is evolving rapidly. Coupled with other W3C standards, informaticists can design systems that may be used not only for storage and retrieval of structured knowledge, but also for quick transformation of such knowledge into many different usable formats. At Intermountain Health Care, we are currently developing an XML-based document framework to accommodate both the capture of structured knowledge as well as its transformation into several usable formats. Our objective relies upon the premise that information systems can be implemented using workflows based on structured documents.

Artificial Intelligence↗