A Concept-Based Framework for Retrieving Evidence to Support Emergency Physician Decision Making at the Point of Care

AbstractTo support point-of-care decision making by presenting outcomes of past treatment choices for cohorts of similar patients based on observational data from electronic health records (EHRs), a machine-learning precision cohort treatment option (PCTO) workflow consisting of (1) data extraction, (2) similarity model training, (3) precision cohort identification, and (4) treatment options analysis was developed. The similarity model is used to dynamically create a cohort of similar patients, to inform clinical decisions about an individual patient. The workflow was implemented using EHR data from a large health care provider for three different highly prevalent chronic diseases: hypertension (HTN), type 2 diabetes mellitus (T2DM), and hyperlipidemia (HL). A retrospective analysis demonstrated that treatment options with better outcomes were available for a majority of cases (75%, 74%, 85% for HTN, T2DM, HL, respectively). The models for HTN and T2DM were deployed in a pilot study with primary care physicians using it during clinic visits. A novel data-analytic workflow was developed to create patient-similarity models that dynamically generate personalized treatment insights at the point-of-care. By leveraging both knowledge-driven treatment guidelines and data-driven EHR data, physicians can incorporate real-world evidence in their medical decision-making process when considering treatment options for individual patients.

Download Full-text

Physicians’ decreased tendency to choose palliative care for patients with advanced dementia between 1999 and 2015

BMC Palliative Care ◽

10.1186/s12904-021-00811-5 ◽

2021 ◽

Vol 20 (1) ◽

Author(s):

Saila Haapasalmi ◽

Reetta P. Piili ◽

Riina Metsänoja ◽

Pirkko-Liisa I. Kellokumpu-Lehtinen ◽

Juho T. Lehto

Keyword(s):

Decision Making ◽

Palliative Care ◽

Legal Protection ◽

Postal Survey ◽

Advanced Dementia ◽

Background Factors ◽

Physician Decision Making ◽

Care Approach ◽

Life Threatening ◽

The Impact

Abstract Background Physicians’ decision-making for seriously ill patients with advanced dementia is of high importance, especially as the prevalence of dementia is rising rapidly, and includes many challenging ethical, medical and juridical aspects. We assessed the change in this decision-making over 16 years (from 1999 to 2015) and several background factors influencing physicians’ decision. Methods A postal survey including a hypothetical patient-scenario representing a patient with an advanced dementia and a life-threatening gastrointestinal bleeding was sent to 1182 and 1258 Finnish physicians in 1999 and 2015, respectively. The target groups were general practitioners (GPs), surgeons, internists and oncologists. The respondents were asked to choose between several life-prolonging and palliative care approaches. The influence of physicians’ background factors and attitudes on their decision were assessed. Results The response rate was 56%. A palliative care approach was chosen by 57 and 50% of the physicians in 1999 and 2015, respectively (p = 0.01). This change was statistically significant among GPs (50 vs 40%, p = 0.018) and oncologists (77 vs 56%, p = 0.011). GPs chose a palliative care approach less often than other responders in both years (50 vs. 63% in 1999 and 40 vs. 56% in 2015, p < 0.001). In logistic regression analysis, responding in 2015 and being a GP remained explanatory factors for a lower tendency to choose palliative care. The impact of family’s benefit on the decision-making decreased, whereas the influence of the patient’s benefit and ethical values as well as the patient’s or physician’s legal protection increased from 1999 to 2015. Conclusions Physicians chose a palliative care approach for a patient with advanced dementia and life-threatening bleeding less often in 2015 than in 1999. Specialty, attitudes and other background factors influenced significantly physician decision-making. Education on the identification and palliative care of the patients with late-stage dementia are needed to make these decisions more consistent.

Download Full-text

1138. Script for Pediatrics: Creating a Smartphone Application to Improve Antimicrobial Prescribing

Open Forum Infectious Diseases ◽

10.1093/ofid/ofz360.1002 ◽

2019 ◽

Vol 6 (Supplement_2) ◽

pp. S405-S405

Author(s):

Sarah Primhak ◽

Natasha Pool ◽

Gayl Humphrey ◽

Lesley Voss ◽

Rachel H Webb ◽

...

Keyword(s):

Decision Making ◽

Antimicrobial Stewardship ◽

Point Of Care ◽

Smartphone Application ◽

Antibiotic Prescribing ◽

Oral Antibiotic ◽

Duration Of Treatment ◽

Antibiotic Allergy ◽

Alternative Agent ◽

The Impact

Abstract Background When considering antimicrobial stewardship (AMS) interventions, pediatrics is an important and often overlooked group. By 5 years of age, 97% of New Zealand (NZ) children have received antibiotics (median 8 antibiotic courses/child). Prescribing is complex due to age and weight-based adjustments, unpalatable oral preparations and inappropriate allergy labeling. Our tertiary Children’s Hospital has >250 web-based nationally utilized guidelines, 15% including antimicrobials. A point prevalence audit showed only 63% guideline adherence for inpatient antimicrobial prescriptions. We designed an accessible app to bring antibiotic prescribing and antibiotic allergy decision-making to prescribers at point of care. Methods Using local hospital and community guidelines, the national formulary and in consultation with subspecialist teams, 31 algorithms were developed. Each algorithm asked questions including diagnosis, age, antibiotic allergy history and known colonization with-resistant organisms. Results The smartphone app (Script) uses the algorithms to advise on appropriate antimicrobial, dose, route and duration of treatment. Advice regarding IV-oral switch parameters and oral antibiotic choice is provided. If allergy is suspected symptom-based decision-making enables the user to choose an alternative agent or encourages allergy de-labeling. Further AMS occurs in some algorithms when advice is given not to prescribe antimicrobials. Conclusion Script for Pediatrics launched in NZ in March 2019 with >1000 users in the first 6 weeks. The most frequently accessed guidelines are otitis media, pneumonia and meningitis. Smartphone applications with local relevance and the ability to update in real-time may prove important tools, by providing easily accessible and intuitive advice to help support antimicrobial stewardship activities. This intervention has been rapidly adopted by pediatric hospital prescribers. The impact on prescribing in concordance with guidelines, timely intravenous to oral antibiotic switch and allergy de-labeling will be assessed. Disclosures All authors: No reported disclosures.

Download Full-text