Developing a decision support tool for responding to patients’ reported levels of information needs, family anxiety, depression, and breathlessness.

2014 ◽  
Vol 32 (31_suppl) ◽  
pp. 173-173
Author(s):  
Liesbeth van Vliet ◽  
Richard Harding ◽  
Claudia Bausewein ◽  
Sheila Payne ◽  
Irene J. Higginson ◽  
...  
Keyword(s):  
Palliative Care ◽  
Decision Support ◽  
Delphi Study ◽  
Information Needs ◽  
Clinical Care ◽  
Decision Support Tool ◽  
Psychosocial Interventions ◽  
Social Needs ◽  
Support Tool ◽  
Patient Reported

173 Background: Routine clinical use of Patient Reported Outcome Measures (PROMs) such as the Palliative Care Outcome Scale (POS) may be prevented by a lack of guidance on how to respond to reported symptoms. When using POS in clinical care, clinicians encounter the most difficulties with responding to information needs, depression and family anxiety while breathlessness remains a difficult to treat symptom. We aimed to create a Decision Support Tool (DST) on how to respond to different levels of these patient-reported symptoms. Methods: A systematic search for guidelines and systematic reviews on these topics was conducted (in Pubmed, Cochrane and York DARE databases, Googlescholar, NICE, National Guideline Clearinghouse, Canadian Medical Association, Google.com). In a two-round online Delphi study purposefully sampled international experts (clinicians, researchers, patient representatives) judged the appropriateness (1-9 scale + do not know option) of drafted recommendations for each POS answer category (0-4) and provided qualitative remarks. Recommendations with a median of 7-9 and <30% of scores between 1-3 and 7-9 were included in the DST. Quality was assessed using an adapted GRADE approach. Results: Twenty-five out of 38 (66%) experts participated in round 1, 23 out of 37 (62%) in round 2. Higher POS scores were related to more included recommendations. The DST consists of both a manual and flow-charts of included recommendations for each topic. Overall, psychosocial interventions were recommended for lower levels of depression and breathlessness than drug interventions (e.g., goal-setting/coping versus morphine for breathlessness). Good communication and emotional support were recommended for low family anxiety levels, but a social needs assessment only for higher levels. For information needs recommendations were least discriminative; almost all recommendations (e.g., assess patients’ understanding of information, show empathy) seemed always relevant. Conclusions: The developed DST can assist clinical responses to patient-reported symptoms in palliative care. Future work is needed to test the effect of using the DST on patients’ outcomes.

VP163 Patient Involvement In The Development Of Multi-Criteria Decision Tool

2017 ◽  
Vol 33 (S1) ◽  
pp. 223-223
Author(s):  
Marie-Pierre Gagnon ◽  
Sylvain L'Espérance ◽  
Carmen Lindsay ◽  
Marc Rhainds ◽  
Martin Coulombe ◽  
...  
Keyword(s):  
Decision Support ◽  
Delphi Study ◽  
Value Added ◽  
Decision Support Tool ◽  
Strategic Choices ◽  
Healthcare Organizations ◽  
Support Tool ◽  
Health Technologies ◽  
Modified Delphi ◽  
Patient Representatives

INTRODUCTION:Healthcare organizations should assess the relevance of both existing and new practices. Involving patients in decisions regarding which health technologies and interventions should be prioritized could favor a better fit between strategic choices and patients needs.METHODS:Following a systematic review of existing multi-criteria decision support tools and a consultation with hospital clinicians and managers, a set of potentially relevant criteria was identified. A three-round modified Delphi study was then conducted among four groups (hospital managers, heads of department, clinicians, and patient representatives) in order to reach consensus on criteria that should be considered in the tool.RESULTS:In total, seventy-four participants completed the third round of the Delphi study. Consensus was obtained on twelve criteria. There were some significant differences between groups in priority scores given to criteria. Patient representatives differed significantly from other groups on two criteria. Their ranking of the accessibility criteria was higher, and their ranking of the organizational aspect criteria was lower than for the other groups.CONCLUSIONS:Patient representatives can be involved in the development of a multi-criteria decision support tool to identify, evaluate and prioritize high value-added health technologies and interventions in order to enhancing clinical appropriateness The fact that accessibility aspects were more important for patient representatives calls for specific attention to these criteria when prioritizing health technologies or interventions. Furthermore, we need to ensure that the decisions made regarding the relevance of these technologies and interventions also reflect patients’ preferences.

An EPIC electronic decision support tool to identify percentage of patients with stage IV thoracic or gastrointestinal malignancy who would benefit from concurrent palliative care but do not currently receive it.

2017 ◽  
Vol 35 (8_suppl) ◽  
pp. 133-133
Author(s):  
Kerin B. Adelson ◽  
Amelia Anne Trant ◽  
Kim Framski ◽  
Mark Swidler ◽  
Nitu Kashyap
Keyword(s):  
Palliative Care ◽  
Decision Support ◽  
Care Service ◽  
Palliative Care Service ◽  
Stage Iv ◽  
Decision Support Tool ◽  
Care Utilization ◽  
Support Tool ◽  
Early Integration ◽  
Stage Iv Disease

133 Background: In 2016 ASCO updated its guideline for early integration of palliative care (PC) into standard oncologic care for all “inpatients and outpatients with advanced cancer.” PC has been shown to improve quality of life, align care at the end of life with patient preferences, and reduce health-care utilization. In preparation for the expansion of our palliative care service into ambulatory disease-based practices at Smilow Cancer Hospital at Yale-New Haven, we sought to create a decision support tool (DST) in the EPIC Electronic Health Record (EHR) that would identify patients for PC referral. Methods: This DST identifies patients with a GI or thoracic malignancy who have had an ICD-10 diagnosis of metastatic or stage IV disease, have not had a palliative care visit in the last 6 months, and are not enrolled in hospice. If the patient meets criteria, the DST will remind providers that “this patient meets ASCO and IOM criteria for concurrent palliative care with oncologic care ” and offers a one-click option to place the referral. To understand the volume of patients this DST would refer, we ran it silently in the EHR background from 7/15/16 through 9/1/16. We tracked how many patients were seen in the clinics, how many were eligible, and how many were referred to PC. Results: See table. Conclusions: Our silent BPA indicated that only 5% of patients eligible for a palliative care consult received it at baseline; this matches national data, which suggests that most patients who would benefit from PC do not receive it. This DST has the potential to dramatically improve PC referral rates and increase adherence with ASCO and IOM guidelines. We plan to move the DST into the live clinical EHR in 2017 after the integrated PC clinics are open. We anticipate that once our BPA is activated, we will see a dramatic increase in the number of eligible patients referred to palliative care. [Table: see text]

scholarly journals Evaluation of ML-Based Clinical Decision Support Tool to Replace an Existing Tool in an Academic Health System: Lessons Learned

2020 ◽  
Vol 10 (3) ◽  
pp. 104
Author(s):  
Myung Woo ◽  
Brooke Alhanti ◽  
Sam Lusk ◽  
Felicia Dunston ◽  
Stephen Blackwelder ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Clinical Care ◽  
Decision Support Tool ◽  
Clinical Decision ◽  
Learning Tools ◽  
Modest Improvement ◽  
Support Tool ◽  
Clinical Decision Support Tool

There is increasing application of machine learning tools to problems in healthcare, with an ultimate goal to improve patient safety and health outcomes. When applied appropriately, machine learning tools can augment clinical care provided to patients. However, even if a model has impressive performance characteristics, prospectively evaluating and effectively implementing models into clinical care remains difficult. The primary objective of this paper is to recount our experiences and challenges in comparing a novel machine learning-based clinical decision support tool to legacy, non-machine learning tools addressing potential safety events in the hospitals and to summarize the obstacles which prevented evaluation of clinical efficacy of tools prior to widespread institutional use. We collected and compared safety events data, specifically patient falls and pressure injuries, between the standard of care approach and machine learning (ML)-based clinical decision support (CDS). Our assessment was limited to performance of the model rather than the workflow due to challenges in directly comparing both approaches. We did note a modest improvement in falls with ML-based CDS; however, it was not possible to determine that overall improvement was due to model characteristics.

scholarly journals Opportunities and Barriers for Adoption of a Decision-Support Tool for Alzheimer’s Disease

2021 ◽  
Vol 2 (4) ◽  
pp. 1-19
Author(s):  
Maura Bellio ◽  
Dominic Furniss ◽  
Neil P. Oxtoby ◽  
Sara Garbarino ◽  
Nicholas C. Firth ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Decision Support ◽  
Design Research ◽  
Clinical Care ◽  
Decision Support Tool ◽  
Added Value ◽  
Structured Interviews ◽  
Support Tool ◽  
Combination Of Methods

Clinical decision-support tools (DSTs) represent a valuable resource in healthcare. However, lack of Human Factors considerations and early design research has often limited their successful adoption. To complement previous technically focused work, we studied adoption opportunities of a future DST built on a predictive model of Alzheimer’s Disease (AD) progression. Our aim is two-fold: exploring adoption opportunities for DSTs in AD clinical care, and testing a novel combination of methods to support this process. We focused on understanding current clinical needs and practices, and the potential for such a tool to be integrated into the setting, prior to its development. Our user-centred approach was based on field observations and semi-structured interviews, analysed through workflow analysis, user profiles, and a design-reality gap model. The first two are common practice, whilst the latter provided added value in highlighting specific adoption needs. We identified the likely early adopters of the tool as being both psychiatrists and neurologists based in research-oriented clinical settings. We defined ten key requirements for the translation and adoption of DSTs for AD around IT, user, and contextual factors. Future works can use and build on these requirements to stand a greater chance to get adopted in the clinical setting.

scholarly journals Effectiveness and scalability of an electronic patient-reported outcome measure and decision support tool for family-centred and participation-focused early intervention: PROSPECT hybrid type 1 trial protocol

BMJ Open ◽  
2022 ◽  
Vol 12 (1) ◽  
pp. e051582
Author(s):  
Vera Kaelin ◽  
Vivian Villegas ◽  
Yi-Fan Chen ◽  
Natalie Murphy ◽  
Elizabeth Papautsky ◽  
...  
Keyword(s):  
Decision Support ◽  
Early Intervention ◽  
Fixed Effects ◽  
Decision Support Tool ◽  
Patient Reported Outcome ◽  
Support Tool ◽  
Hybrid Type ◽  
Generalised Linear Mixed Model ◽  
Patient Reported

IntroductionEarly intervention (EI) endorses family-centred and participation-focused services, but there remain insufficient options for systematically enacting this service approach. The Young Children’s Participation and Environment Measure electronic patient-reported outcome (YC-PEM e-PRO) is an evidence-based measure for caregivers that enables family-centred services in EI. The Parent-Reported Outcomes for Strengthening Partnership within the Early Intervention Care Team (PROSPECT) is a community-based pragmatic trial examining the effectiveness of implementing the YC-PEM e-PRO measure and decision support tool as an option for use within routine EI care, on service quality and child outcomes (aim 1). Following trial completion, we will characterise stakeholder perspectives of facilitators and barriers to its implementation across multiple EI programmes (aim 2).Methods and analysisThis study employs a hybrid type 1 effectiveness-implementation study design. For aim 1, we aim to enrol 223 caregivers of children with or at risk for developmental disabilities or delays aged 0–3 years old that have accessed EI services for three or more months from one EI programme in the Denver Metro catchment of Colorado. Participants will be invited to enrol for 12 months, beginning at the time of their child’s annual evaluation of progress. Participants will be randomised using a cluster-randomised design at the EI service coordinator level. Both groups will complete baseline testing and follow-up assessment at 1, 6 and 12 months. A generalised linear mixed model will be fitted for each outcome of interest, with group, time and their interactions as primary fixed effects, and adjusting for child age and condition severity as secondary fixed effects. For aim 2, we will conduct focus groups with EI stakeholders (families in the intervention group, service coordinators and other service providers in the EI programme, and programme leadership) which will be analysed thematically to explain aim 1 results and identify supports and remaining barriers to its broader implementation in multiple EI programmes.Ethics and disseminationThis study has been approved by the institutional review boards at the University of Illinois at Chicago (2020-0555) and University of Colorado (20-2380). An active dissemination plan will ensure that findings have maximum reach for research and practice.Trial registration numberNCT04562038.

Sign in / Sign up

Export Citation Format

Share Document