1
|
Kennedy EE, Davoudi A, Hwang S, Freda PJ, Urbanowicz R, Bowles KH, Mowery DL. Identifying Barriers to Post-Acute Care Referral and Characterizing Negative Patient Preferences Among Hospitalized Older Adults Using Natural Language Processing. AMIA ... ANNUAL SYMPOSIUM PROCEEDINGS. AMIA SYMPOSIUM 2023; 2022:606-615. [PMID: 37128417 PMCID: PMC10148308] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 05/03/2023]
Abstract
Our objective was to detect common barriers to post-acute care (B2PAC) among hospitalized older adults using natural language processing (NLP) of clinical notes from patients discharged home when a clinical decision support system recommended post-acute care. We annotated B2PAC sentences from discharge planning notes and developed an NLP classifier to identify the highest-value B2PAC class (negative patient preferences). Thirteen machine learning models were compared with Amazon's AutoGluon deep learning model. The study included 594 acute care notes from 100 patient encounters (1156 sentences contained 11 B2PAC) in a large academic health system. The most frequent and modifiable B2PAC class was negative patient preferences (18.3%). The best supervised model was Extreme Gradient Boosting (F1: 0.859), but the deep learning model performed better (F1: 0.916). Alerting clinicians of negative patient preferences early in the hospitalization can prompt interventions such as patient education to ensure patients receive the right level of care and avoid negative outcomes.
Collapse
Affiliation(s)
- Erin E Kennedy
- University of Pennsylvania School of Nursing, NewCourtland Center for Transitions and Health, Philadelphia, PA
| | - Anahita Davoudi
- University of Pennsylvania, Institute for Biomedical Informatics, Philadelphia, PA
| | - Sy Hwang
- University of Pennsylvania, Institute for Biomedical Informatics, Philadelphia, PA
| | - Philip J Freda
- University of Pennsylvania, Institute for Biomedical Informatics, Philadelphia, PA
- Cedars-Sinai Medical Center, Department of Computational Biomedicine, Los Angeles, California
| | - Ryan Urbanowicz
- University of Pennsylvania, Institute for Biomedical Informatics, Philadelphia, PA
- Cedars-Sinai Medical Center, Department of Computational Biomedicine, Los Angeles, California
| | - Kathryn H Bowles
- University of Pennsylvania School of Nursing, NewCourtland Center for Transitions and Health, Philadelphia, PA
| | - Danielle L Mowery
- University of Pennsylvania, Institute for Biomedical Informatics, Philadelphia, PA
| |
Collapse
|
2
|
Chesney TR, Haas B, Coburn NG, Mahar AL, Zuk V, Zhao H, Hsu AT, Hallet J. Immediate and Long-Term Health Care Support Needs of Older Adults Undergoing Cancer Surgery: A Population-Based Analysis of Postoperative Homecare Utilization. Ann Surg Oncol 2020; 28:1298-1310. [PMID: 32789531 DOI: 10.1245/s10434-020-08992-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2020] [Accepted: 07/18/2020] [Indexed: 12/17/2022]
Abstract
BACKGROUND Functional outcomes are central to decision-making by older adults (OA), but long-term risks after cancer surgery have not been described beyond 1 year for this population. This study aimed to evaluate long-term health care support needs by examining homecare use after cancer surgery for OA. METHODS This population-based study investigated adults 70 years of age or older with a new cancer diagnosis between 2007 and 2017 who underwent resection. The outcomes were receipt and intensity of homecare from postoperative discharge to 5 years after surgery. Time-to-event analysis with competing events was used. RESULTS Among 82,037 patients, homecare use was highest (43.7% of eligible patients) in postoperative month 1. The need for homecare subsequently decreased to stabilize between year 1 (13.9%) and year 5 (12.6%). Of the patients not receiving preoperative homecare, 10.9% became long-term users at year 5 after surgery. Advancing age, female sex, frailty, high-intensity surgery, more recent period of surgery, and receipt of preoperative homecare were associated with increased hazards of postoperative homecare. Intensity of homecare went from 10.3 to 10.1 days per patient-month between month 1 and year 1, reaching 12 days per patient-month at year 5. The type of homecare services changed from predominantly nursing care in year 1 (51.9%) to increasing personal support services from year 2 (69.6%) to year 5 (77.5%). CONCLUSION Receipt of homecare increased long-term after cancer surgery for OA, peaking in the first 6 months and plateauing thereafter at a new baseline. One tenth of the patients without preoperative homecare became long-term homecare users postoperatively, indicating changing health care needs focused on personal support services from year 2 to year 5.
Collapse
Affiliation(s)
- Tyler R Chesney
- Department of Surgery, University of Toronto, Toronto, ON, Canada
| | - Barbara Haas
- Department of Surgery, University of Toronto, Toronto, ON, Canada.,Division of General Surgery, Sunnybrook Health Sciences Centre - Odette Cancer Centre, Toronto, ON, Canada.,Sunnybrook Research Institute, Toronto, ON, Canada.,ICES, Toronto, ON, Canada.,Interdepartmental Division of Critical Care Medicine, University of Toronto, Toronto, ON, Canada.,Department of Critical Care Medicine, Sunnybrook Health Sciences Centre, Toronto, ON, Canada
| | - Natalie G Coburn
- Department of Surgery, University of Toronto, Toronto, ON, Canada.,Division of General Surgery, Sunnybrook Health Sciences Centre - Odette Cancer Centre, Toronto, ON, Canada.,Sunnybrook Research Institute, Toronto, ON, Canada.,ICES, Toronto, ON, Canada
| | - Alyson L Mahar
- Department of Community Health Sciences, University of Manitoba, Winnipeg, MB, Canada
| | - Victoria Zuk
- Sunnybrook Research Institute, Toronto, ON, Canada
| | | | - Amy T Hsu
- Ottawa Hospital Research Institute, Ottawa, ON, Canada.,Bruyère Research Institute, Ottawa, ON, Canada
| | - Julie Hallet
- Department of Surgery, University of Toronto, Toronto, ON, Canada. .,Division of General Surgery, Sunnybrook Health Sciences Centre - Odette Cancer Centre, Toronto, ON, Canada. .,Sunnybrook Research Institute, Toronto, ON, Canada. .,ICES, Toronto, ON, Canada.
| | | |
Collapse
|
3
|
Kim S, Lee SC, Skinner CS, Brown CJ, Balentine CJ. A Surgeon's Guide to Treating Older Patients with Colorectal Cancer. CURRENT COLORECTAL CANCER REPORTS 2019; 15:1-7. [PMID: 31728133 PMCID: PMC6855304 DOI: 10.1007/s11888-019-00424-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
PURPOSE OF REVIEW Review strategies to improve outcomes of colorectal cancer treatment in older patients. RECENT FINDINGS Older colorectal patients face many barriers to recovery during their initial inpatient stay following surgery and after leaving the hospital. In addition to the risk of inpatient morbidity and mortality, older patients are more likely to require post-acute care services, to face nutritional deficits, and to experience complications of chemoradiation. SUMMARY In order to improve outcomes for older patients with colorectal cancer, it is important for surgeons to recognize their unique needs and to develop plans to address them. The involvement of a multidisciplinary team with geriatric experience can guide planning for surgery, the immediate postoperative recovery, and long-term survivorship.
Collapse
Affiliation(s)
- Sooyeon Kim
- Department of Surgery, University of Texas Southwestern Medical Center, Dallas, TX
| | - Simon C. Lee
- Department of Clinical Sciences, Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX
| | - Celette S. Skinner
- Department of Clinical Sciences, Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX
| | - Cynthia J. Brown
- Birmingham/Atlanta Veterans Affairs Geriatric Research, Education, and Clinical Care Center, Birmingham, AL; Division of Gerontology, Geriatrics, and Palliative Care, University of Alabama at Birmingham, Birmingham, AL
| | - Courtney J. Balentine
- Department of Surgery, University of Texas Southwestern Medical Center, Dallas, TX
- VA North Texas Health Care System, Dallas, TX
| |
Collapse
|
4
|
Megaritis C, Sakellari E, Psychogiou M, Tzenalis A, Krepia V, Charalambous G, Sapountzi-Krepia D. Exploring home care nurses' perceptions regarding their services in economic crisis: A qualitative approach. Nurs Forum 2018; 53:521-528. [PMID: 29968259 DOI: 10.1111/nuf.12281] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
This article explores the home care nurses' perceptions on the services they provide in Cyprus, which has been hit by a financial crisis. Semistructured interviews were conducted in Greek at the home care nurses' offices. Data were analyzed using qualitative content analysis. The participants' perceptions are described in terms of provision of home care nursing, administration of homecare nursing, job satisfaction, financial issues, and suggesting improvements. The financial crisis influences the home care services with regard to workload increase, staff shortage, and lack of resources. Home care nurses are well engaged in the provision of proper services in order to address the patients' needs. However, the financial crisis has set obstacles in the provision of care.
Collapse
Affiliation(s)
| | - Evanthia Sakellari
- Department of Public and Community Health, University of West Attica, Athens, Greece
| | - Maria Psychogiou
- Department of Nursing Science, University of Eastern Finland, Kuopio, Finland
| | | | - Vassiliki Krepia
- School of Human Movement and Quality of Life Sciences, Faculty of Nursing, University of Peloponnese, Sparta, Greece.,Sismanogleion Hospital of Attica, Marousi, Greece
| | | | | |
Collapse
|
5
|
Bowles KH, Ratcliffe SJ, Naylor MD, Holmes JH, Keim SK, Flores EJ. Nurse Generated EHR Data Supports Post-Acute Care Referral Decision Making: Development and Validation of a Two-step Algorithm. AMIA ... ANNUAL SYMPOSIUM PROCEEDINGS. AMIA SYMPOSIUM 2018; 2017:465-474. [PMID: 29854111 PMCID: PMC5977719] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Objective: Build and validate a clinical decision support (CDS) algorithm for discharge decisions regarding referral for post-acute care (PAC) and to what site of care. Materials and Methods: Case studies derived from EHR data were judged by 171 interdisciplinary experts and prediction models were generated. Results: A two-step algorithm emerged with area under the curve (AUC) in validation of 91.5% (yes/no refer) and AUC 89.7% (where to refer). Discussion: CDS for discharge planning (DP) decisions may remove subjectivity, and variation in decision-making. CDS could automate the assessment process and alert clinicians of high need patients earlier in the hospital stay. Conclusion: Our team successfully built and validated a two-step algorithm to support discharge referral decision-making from EHR data. Getting patients the care and support they need may decrease readmissions and other adverse events. Further work is underway to test the effects of the CDS on patient outcomes in two hospitals.
Collapse
Affiliation(s)
- Kathryn H Bowles
- University of Pennsylvania, Philadelphia, PA
- Visiting Nurse Service of New York
| | | | | | | | | | | |
Collapse
|
6
|
Geddie PI, Wochna Loerzel V, Norris AE. Family Caregiver Knowledge, Patient Illness Characteristics, and Unplanned Hospital Admissions in Older Adults With Cancer. Oncol Nurs Forum 2016; 43:453-63. [PMID: 27314188 DOI: 10.1188/16.onf.453-463] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
PURPOSE/OBJECTIVES To explore factors related to unplanned hospital admissions and determine if one or more factors are predictive of unplanned hospital admissions for older adults with cancer.
. DESIGN A prospective longitudinal design and a retrospective chart review.
. SETTING Adult oncology outpatient infusion centers and inpatient units at Orlando Regional Medical Center in Florida.
. SAMPLE A convenience sample of 129 dyads of older adults with cancer and their family caregivers.
. METHODS Family caregiver demographic and side effect knowledge data were collected prospectively during interviews with family caregivers using a newly developed tool, the Nurse Assessment of Family Caregiver Knowledge and Action Tool. Patient demographic and clinical data were obtained through a retrospective chart review. Descriptive statistics and logistic regression analyses were used to evaluate data and examine relationships among variables.
. MAIN RESEARCH VARIABLES Patient illness characteristics; impaired function; side effects, such as infection, fever, vomiting, and diarrhea; family caregiver knowledge; and unplanned hospital admissions.
. FINDINGS Unplanned hospital admissions were more likely to occur when older adults had impaired function and side effects, such as infection, fever, vomiting, and diarrhea. Impaired function and family caregiver knowledge did not moderate the effects of these side effects on unplanned hospital admissions.
. CONCLUSIONS Findings suggest that the presence of impaired function and side effects, such as infection, fever, vomiting, and diarrhea, predict unplanned hospital admissions in older adults with cancer during the active treatment phase. Side effects may or may not be related to chemotherapy and may be related to preexisting comorbidities.
. IMPLICATIONS FOR NURSING Nurses can conduct targeted assessments to identify older adults and their family caregivers who will need additional follow-up and support during the cancer treatment trajectory. Information gained from these assessments will assist nurses to provide practical and tailored strategies to reduce the risk for unplanned admissions.
Collapse
|
7
|
Jones CD, Wald HL, Boxer RS, Masoudi FA, Burke RE, Capp R, Coleman EA, Ginde AA. Characteristics Associated with Home Health Care Referrals at Hospital Discharge: Results from the 2012 National Inpatient Sample. Health Serv Res 2016; 52:879-894. [PMID: 27196526 DOI: 10.1111/1475-6773.12504] [Citation(s) in RCA: 37] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022] Open
Abstract
OBJECTIVE To assess patient- and hospital-level factors associated with home health care (HHC) referrals following nonelective U.S. patient hospitalizations in 2012. DATA SOURCE The 2012 National Inpatient Sample (NIS). STUDY DESIGN Retrospective, cross-sectional multivariable logistic regression modeling to assess patient- and hospital-level variables in patient discharges with versus without HHC referrals. DATA COLLECTION Analysis included 1,109,905 discharges in patients ≥65 years with Medicare. PRINCIPAL FINDINGS About 29.2 percent of discharges were referred to HHC, which were more likely with older age, female sex, urban location, low income, longer length of stay, higher severity of illness scores, diagnoses of heart failure or sepsis, and hospital location in New England (referent: Pacific). CONCLUSIONS As health policy changes influence postacute HHC, defining specific diagnoses and regional patterns associated with HHC is a first step to optimize postacute HHC services.
Collapse
Affiliation(s)
- Christine D Jones
- Hospital Medicine Section, Division of General Internal Medicine, University of Colorado Denver School of Medicine, Aurora, CO
| | - Heidi L Wald
- Hospital Medicine Section, Division of General Internal Medicine, Division of Health Care Policy and Research, University of Colorado Denver School of Medicine, Aurora, CO
| | - Rebecca S Boxer
- Division of Geriatric Medicine, University of Colorado Denver School of Medicine, VA Eastern Colorado Health Care System, Aurora, CO
| | - Frederick A Masoudi
- Division of Cardiology, University of Colorado Denver School of Medicine, Aurora, CO
| | - Robert E Burke
- Department of Medicine, VA Eastern Colorado Health Care System, Denver, CO.,Division of General Internal Medicine, University of Colorado Denver School of Medicine, Denver, CO
| | - Roberta Capp
- Department of Emergency Medicine, University of Colorado Denver School of Medicine, Aurora, CO
| | - Eric A Coleman
- Division of Health Care Policy and Research, University of Colorado Denver School of Medicine, Aurora, CO
| | - Adit A Ginde
- Department of Emergency Medicine, University of Colorado Denver School of Medicine, Aurora, CO
| |
Collapse
|
8
|
Length of home hospice care, family-perceived timing of referrals, perceived quality of care, and quality of death and dying in terminally ill cancer patients who died at home. Support Care Cancer 2014; 23:491-9. [PMID: 25142705 DOI: 10.1007/s00520-014-2397-7] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2014] [Accepted: 08/08/2014] [Indexed: 11/27/2022]
Abstract
PURPOSE This study aims to clarify the length of home hospice care, family-perceived timing of referrals, and their effects on the family-perceived quality of care and quality of death and dying of terminally ill cancer patients who died at home and identify the determinants of perceived late referrals. METHODS A multicenter questionnaire survey was conducted involving 1,052 family members of cancer patients who died at home supported by 15 home-based hospice services throughout Japan. RESULTS A total of 693 responses were analyzed (effective response rate, 66 %). Patients received home-based hospice care for a median of 35.0 days, and 8.0 % received home hospice care for less than 1 week. While 1.5 % of the families reported the timing of referrals as early, 42 % reported the timing as late or too late. The families of patients with a length of care of less than 4 weeks were more likely to regard the timing of referrals as late or too late. The patients of family members who regarded the timing of referrals as late or too late had a significantly lower perceived quality of care (effect size, 0.18; P = 0.039) and lower quality of death and dying (effect size, 0.15, P = 0.063). Independent determinants of higher likelihoods of perceived late referrals included: frequent visits to emergency departments, patient being unprepared for worsening condition, and patient having concerns about relationship with new doctor. Discharge nurse availability was independently associated with lower likelihoods of perceived late referrals. CONCLUSIONS A significant number of bereaved families regarded the timing of referrals to home hospices as late, and the perceived timing was associated with the family-perceived quality of care and quality of death and dying. Systematic strategies to overcome the barriers related to perceived late referrals are necessary.
Collapse
|
9
|
Fukui S, Fujita J, Tsujimura M, Sumikawa Y, Hayashi Y, Fukui N. Late referrals to home palliative care service affecting death at home in advanced cancer patients in Japan: a nationwide survey. Ann Oncol 2011; 22:2113-2120. [DOI: 10.1093/annonc/mdq719] [Citation(s) in RCA: 37] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
|
10
|
Predictors of home death of home palliative cancer care patients: a cross-sectional nationwide survey. Int J Nurs Stud 2011; 48:1393-400. [PMID: 21621775 DOI: 10.1016/j.ijnurstu.2011.05.001] [Citation(s) in RCA: 23] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2010] [Revised: 04/21/2011] [Accepted: 05/01/2011] [Indexed: 11/21/2022]
Abstract
OBJECTIVES To identify factors influencing the place of death among home palliative cancer care patients, focusing on the role of nurses in terms of pre- and post-discharge from hospital to home care settings. DESIGN, SETTINGS AND PARTICIPANTS A cross-sectional nationwide questionnaire survey was conducted at 1000 randomly selected homecare agencies in Japan. The questionnaires were completed by primary community nurses of home palliative patients just after their discharge. A total of 568 responses were analyzed (effective response rate, 69%). RESULTS Multivariate logistic regression analysis revealed the following independent factors of place of death among those patients: desire for home death at referral by both patient and family caregiver; caregiver relationship to patient as daughter or daughter-in-law; totally bedridden functional status of patient; patient not suffering from depression and/or anxiety at referral; patients and caregivers duly informed about the dying process/death in detail, as well as instructed by community nurses about pain management and how to treat/prevent bedsores in home care settings. CONCLUSIONS This study demonstrated the importance of both the hospital and community nurses' role in increasing the patients' chance of dying at home. Hospital nurses should support early transfer to home palliative care according to their assessment of the desire of patient/family caregiver for home death, the patients' clinical status, and caregivers' ability to provide patient care at home. Community nurses should inform patients/family caregiver in detail about the dying process/death just after discharge, relieve patient pain, treat/prevent bedsores, and instruct family caregivers on their symptom control.
Collapse
|