1
|
Walker JA, Staab EM, Ridgway JP, Schmitt J, Franco MI, Hunter S, Motley D, Laiteerapong N. Patient Perspectives on Portal-Based Anxiety and Depression Screening in HIV Care: A Qualitative Study Using the Consolidated Framework for Implementation Research. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2024; 21:692. [PMID: 38928937 PMCID: PMC11203430 DOI: 10.3390/ijerph21060692] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/01/2024] [Revised: 05/13/2024] [Accepted: 05/24/2024] [Indexed: 06/28/2024]
Abstract
Electronic patient portals represent a promising means of integrating mental health assessments into HIV care where anxiety and depression are highly prevalent. Patient attitudes toward portal-based mental health screening within HIV clinics have not been well described. The aim of this formative qualitative study is to characterize the patient-perceived facilitators and barriers to portal-based anxiety and depression screening within HIV care in order to inform implementation strategies for mental health screening. Twelve adult HIV clinic patients participated in semi-structured interviews that were audio recorded and transcribed. The transcripts were coded using constructs from the Consolidated Framework for Implementation Research and analyzed thematically to identify the barriers to and facilitators of portal-based anxiety and depression screening. Facilitators included an absence of alternative screening methods, an approachable design, perceived adaptability, high compatibility with HIV care, the potential for linkage to treatment, an increased self-awareness of mental health conditions, the ability to bundle screening with clinic visits, and communicating an action plan for results. The barriers included difficulty navigating the patient portal system, a lack of technical support, stigmatization from the healthcare system, care team response times, and the novelty of using patient portals for communication. The patients in the HIV clinic viewed the use of a portal-based anxiety and depression screening tool as highly compatible with routine HIV care. Technical difficulties, follow-up concerns, and a fear of stigmatization were commonly perceived as barriers to portal use. The results of this study can be used to inform implementation strategies when designing or incorporating portal-based mental health screening into other HIV care settings.
Collapse
Affiliation(s)
- Jacob A. Walker
- Department of Medicine, University of Colorado School of Medicine, Aurora, CO 80045, USA
| | - Erin M. Staab
- Department of Medicine, University of Chicago, Chicago, IL 60637, USA (N.L.)
| | - Jessica P. Ridgway
- Department of Medicine, University of Chicago, Chicago, IL 60637, USA (N.L.)
| | - Jessica Schmitt
- Department of Medicine, University of Chicago, Chicago, IL 60637, USA (N.L.)
| | - Melissa I. Franco
- Department of Medicine, University of Chicago, Chicago, IL 60637, USA (N.L.)
| | - Scott Hunter
- Chicago Center for HIV Elimination, Department of Medicine, University of Chicago, Chicago, IL 60637, USA
- WCG Clinical Endpoint Solutions, Hamilton, NJ 08540, USA
| | - Darnell Motley
- Department of Medicine, University of Chicago, Chicago, IL 60637, USA (N.L.)
| | - Neda Laiteerapong
- Department of Medicine, University of Chicago, Chicago, IL 60637, USA (N.L.)
| |
Collapse
|
2
|
Arias de la Torre J, Ronaldson A, Vilagut G, Martínez-Alés G, Dregan A, Bakolis I, Valderas JM, Molina AJ, Martín V, Bellón JÁ, Alonso J. Implementation of community screening strategies for depression. Nat Med 2024; 30:930-932. [PMID: 38413728 DOI: 10.1038/s41591-024-02821-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/29/2024]
Affiliation(s)
- Jorge Arias de la Torre
- CIBER Epidemiology and Public Health (CIBERESP), Madrid, Spain.
- Institute of Biomedicine (IBIOMED), University of Leon, Leon, Spain.
- Care in Long Term Conditions Research Division, King's College London, London, UK.
| | - Amy Ronaldson
- Institute of Psychiatry, Psychology and Neuroscience (IoPPN), King's College London, London, UK
| | - Gemma Vilagut
- CIBER Epidemiology and Public Health (CIBERESP), Madrid, Spain
- Health Services Research Group, Hospital del Mar Medical Research Institute (IMIM), Barcelona, Spain
| | - Gonzalo Martínez-Alés
- CAUSALab, Harvard University T.H. Chan School of Public Health, Boston, MA, USA
- Mental Health Network Biomedical Research Center (CIBERSAM), Madrid, Spain
- Hospital La Paz Institute for Health Research (IdiPAZ), Madrid, Spain
| | - Alex Dregan
- Institute of Psychiatry, Psychology and Neuroscience (IoPPN), King's College London, London, UK
| | - Ioannis Bakolis
- Institute of Psychiatry, Psychology and Neuroscience (IoPPN), King's College London, London, UK
| | - Jose M Valderas
- Department of Medicine, National University of Singapore, Singapore, Singapore
- Department of Family Medicine, National University Health System, Singapore, Singapore
- Centre for Research in Health Systems Performance (CRiHSP) National University Health System, Singapore, Singapore
| | - Antonio J Molina
- CIBER Epidemiology and Public Health (CIBERESP), Madrid, Spain
- Institute of Biomedicine (IBIOMED), University of Leon, Leon, Spain
| | - Vicente Martín
- CIBER Epidemiology and Public Health (CIBERESP), Madrid, Spain
- Institute of Biomedicine (IBIOMED), University of Leon, Leon, Spain
| | - Juan Ángel Bellón
- Biomedical Research Institute of Málaga (IBIMA-Bionand platform), Malaga, Spain
- El Palo Health Centre, Andalusian Health Service (SAS), Malaga, Spain
- Department of Public Health and Psychiatry, University of Málaga (UMA), Malaga, Spain
| | - Jordi Alonso
- CIBER Epidemiology and Public Health (CIBERESP), Madrid, Spain
- Health Services Research Group, Hospital del Mar Medical Research Institute (IMIM), Barcelona, Spain
- Department of Medicine and Life Sciences, Pompeu Fabra University (UPF), Barcelona, Spain
| |
Collapse
|
3
|
Feng W, Wu H, Ma H, Tao Z, Xu M, Zhang X, Lu S, Wan C, Liu Y. Applying contrastive pre-training for depression and anxiety risk prediction in type 2 diabetes patients based on heterogeneous electronic health records: a primary healthcare case study. J Am Med Inform Assoc 2024; 31:445-455. [PMID: 38062850 PMCID: PMC10797279 DOI: 10.1093/jamia/ocad228] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 11/13/2023] [Accepted: 11/21/2023] [Indexed: 01/22/2024] Open
Abstract
OBJECTIVE Due to heterogeneity and limited medical data in primary healthcare services (PHS), assessing the psychological risk of type 2 diabetes mellitus (T2DM) patients in PHS is difficult. Using unsupervised contrastive pre-training, we proposed a deep learning framework named depression and anxiety prediction (DAP) to predict depression and anxiety in T2DM patients. MATERIALS AND METHODS The DAP model consists of two sub-models. Firstly, the pre-trained model of DAP used unlabeled discharge records of 85 085 T2DM patients from the First Affiliated Hospital of Nanjing Medical University for unsupervised contrastive learning on heterogeneous electronic health records (EHRs). Secondly, the fine-tuned model of DAP used case-control cohorts (17 491 patients) selected from 149 596 T2DM patients' EHRs in the Nanjing Health Information Platform (NHIP). The DAP model was validated in 1028 patients from PHS in NHIP. Evaluation included receiver operating characteristic area under the curve (ROC-AUC) and precision-recall area under the curve (PR-AUC), and decision curve analysis (DCA). RESULTS The pre-training step allowed the DAP model to converge at a faster rate. The fine-tuned DAP model significantly outperformed the baseline models (logistic regression, extreme gradient boosting, and random forest) with ROC-AUC of 0.91±0.028 and PR-AUC of 0.80±0.067 in 10-fold internal validation, and with ROC-AUC of 0.75 ± 0.045 and PR-AUC of 0.47 ± 0.081 in external validation. The DCA indicate the clinical potential of the DAP model. CONCLUSION The DAP model effectively predicted post-discharge depression and anxiety in T2DM patients from PHS, reducing data fragmentation and limitations. This study highlights the DAP model's potential for early detection and intervention in depression and anxiety, improving outcomes for diabetes patients.
Collapse
Affiliation(s)
- Wei Feng
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, 210009, China
| | - Honghan Wu
- Institute of Health Informatics, University College London, London, WC1E 6BT, United Kingdom
- The Alan Turing Institute, London, NW1 2DB, United Kingdom
| | - Hui Ma
- Department of Medical Psychology, Nanjing Brain Hospital affiliated with Nanjing Medical University, Nanjing, Jiangsu, 210024, China
| | - Zhenhuan Tao
- Department of Planning, Nanjing Health Information Center, Nanjing, Jiangsu, 210003, China
| | - Mengdie Xu
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, 210009, China
| | - Xin Zhang
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, 210009, China
- Department of Information, The First Affiliated Hospital, Nanjing Medical University, Nanjing, Jiangsu, 210029, China
| | - Shan Lu
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, 210009, China
- Department of Information, The First Affiliated Hospital, Nanjing Medical University, Nanjing, Jiangsu, 210029, China
| | - Cheng Wan
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, 210009, China
| | - Yun Liu
- Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, 210009, China
- Department of Information, The First Affiliated Hospital, Nanjing Medical University, Nanjing, Jiangsu, 210029, China
| |
Collapse
|
4
|
Zimmer D, Staab EM, Ridgway JP, Schmitt J, Franco M, Hunter SJ, Motley D, Laiteerapong N. Population-Level Portal-Based Anxiety and Depression Screening Perspectives in HIV Care Clinicians: Qualitative Study Using the Consolidated Framework for Implementation Research. JMIR Form Res 2024; 8:e48935. [PMID: 38206651 PMCID: PMC10811578 DOI: 10.2196/48935] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Revised: 11/07/2023] [Accepted: 11/22/2023] [Indexed: 01/12/2024] Open
Abstract
BACKGROUND Depression and anxiety are common among people with HIV and are associated with inadequate viral suppression, disease progression, and increased mortality. However, depression and anxiety are underdiagnosed and undertreated in people with HIV owing to inadequate visit time and personnel availability. Conducting population-level depression and anxiety screening via the patient portal is a promising intervention that has not been studied in HIV care settings. OBJECTIVE We aimed to explore facilitators of and barriers to implementing population-level portal-based depression and anxiety screening for people with HIV. METHODS We conducted semistructured hour-long qualitative interviews based on the Consolidated Framework for Implementation Research with clinicians at an HIV clinic. RESULTS A total of 10 clinicians participated in interviews. In total, 10 facilitators and 7 barriers were identified across 5 Consolidated Framework for Implementation Research domains. Facilitators included advantages of systematic screening outside clinic visits; the expectation that assessment frequency could be tailored to patient needs; evidence from the literature and previous experience in other settings; respect for patient privacy; empowering patients and facilitating communication about mental health; compatibility with clinic culture, workflows, and systems; staff beliefs about the importance of mental health screening and benefits for HIV care; engaging all clinic staff and leveraging their strengths; and clear planning and communication with staff. Barriers included difficulty in ensuring prompt response to suicidal ideation; patient access, experience, and comfort using the portal; limited availability of mental health services; variations in how providers use the electronic health record and communicate with patients; limited capacity to address mental health concerns during HIV visits; staff knowledge and self-efficacy regarding the management of mental health conditions; and the impersonal approach to a sensitive topic. CONCLUSIONS We proposed 13 strategies for implementing population-level portal-based screening for people with HIV. Before implementation, clinics can conduct local assessments of clinicians and clinic staff; engage clinicians and clinic staff with various roles and expertise to support the implementation; highlight advantages, relevance, and evidence for population-level portal-based mental health screening; make screening frequency adaptable based on patient history and symptoms; use user-centered design methods to refine results that are displayed and communicated in the electronic health record; make screening tools available for patients to use on demand in the portal; and create protocols for positive depression and anxiety screeners, including those indicating imminent risk. During implementation, clinics should communicate with clinicians and clinic staff and provide training on protocols; provide technical support and demonstrations for patients on how to use the portal; use multiple screening methods for broad reach; use patient-centered communication in portal messages; provide clinical decision support tools, training, and mentorship to help clinicians manage mental health concerns; and implement integrated behavioral health and increase mental health referral partnerships.
Collapse
Affiliation(s)
- Daniela Zimmer
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| | - Erin M Staab
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| | - Jessica P Ridgway
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| | - Jessica Schmitt
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| | - Melissa Franco
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| | - Scott J Hunter
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
- Western Institutional Review Board- Copernicus Group, Princeton, NJ, United States
| | - Darnell Motley
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| | - Neda Laiteerapong
- Section of General Internal Medicine, University of Chicago, Chicago, IL, United States
| |
Collapse
|
5
|
Federman AD, Becker J, Carnavali F, Rivera Mindt M, Cho D, Pandey G, Chan L, Curtis L, Wolf MS, Wisnivesky JP. Relationship Between Cognitive Impairment and Depression Among Middle Aged and Older Adults in Primary Care. Gerontol Geriatr Med 2024; 10:23337214231214217. [PMID: 38476882 PMCID: PMC10929046 DOI: 10.1177/23337214231214217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Revised: 10/23/2023] [Accepted: 10/27/2023] [Indexed: 03/14/2024] Open
Abstract
Objectives: To determine rates of previously undetected cognitive impairment among patients with depression in primary care. Methods: Patients ages 55 and older with no documented history of dementia or mild cognitive impairment were recruited from primary care practices in New York City, NY and Chicago, IL (n = 855). Cognitive function was assessed with the Montreal Cognitive Assessment (MoCA) and depression with the Patient Health Questionnaire-8. Results: The mean age was 66.8 (8.0) years, 45.3% were male, 32.7% Black, and 29.2% Latinx. Cognitive impairment increased with severity of depression: 22.9% in persons with mild depression, 27.4% in moderate depression and 41.8% in severe depression (p = .0002). Severe depression was significantly associated with cognitive impairment in multivariable analysis (standardized β = -.11, SE = 0.33, p < .0001). Discussion: Depression was strongly associated with previously undetected cognitive impairment. Primary care clinicians should consider screening, or expand their screening, for both conditions.
Collapse
Affiliation(s)
| | | | | | - Monica Rivera Mindt
- Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Fordham University, New York, NY, USA
| | - Dayeon Cho
- Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Gaurav Pandey
- Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Lili Chan
- Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | | | | | | |
Collapse
|
6
|
Miller A, Skoranski AK, Prior B, Fitzpatrick R, Morgan C, Hepschmidt P, Smith BA, Cella M, Brown McGlotten D, Pitt K, Polomano RC. An "Engage to Sustain" Intervention to Improve Process Performance Measures in Ambulatory Care. J Ambul Care Manage 2023; 46:284-297. [PMID: 37540113 DOI: 10.1097/jac.0000000000000474] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/05/2023]
Abstract
In ambulatory care, monitoring process performance measures (PPMs) is essential to meet regulatory requirements, establish targets for care, seek reimbursement, and evaluate patient care responsibilities. We implemented a comprehensive program, "Engage to Sustain," for licensed practical nurses (LPNs) and certified medical assistants (CMAs) to practice at the top of their licensure/certification. Screening rates for 4 key PPMs (depression screening, fall risk screening, and tobacco use screening and counseling) markedly increased following this intervention across 18 ambulatory departments with more than 2 million patient visits. These results suggest that shifting responsibilities for patient screening from physicians and advanced practitioners to LPNs and CMAs may improve screening rates.
Collapse
Affiliation(s)
- Angela Miller
- Penn Medicine Clinical Practices of the University of Pennsylvania, Philadelphia (Drs Miller and Fitzpatrick and Mss Prior and Pitt); Penn Medicine Medical Group, Penn Primary Care & Penn Specialty Practices, Philadelphia, Pennsylvania (Mr Skoranski); Corporate Information Services (Dr Brown McGlotten), Penn Medicine, Philadelphia, Pennsylvania (Mss Morgan and Hepschmidt); Hospital of the University of Pennsylvania, Philadelphia (Ms Smith); Primary Care and Penn Specialty Practices, Bala Cynwyd, Pennsylvania (Mr Cella); and University of Pennsylvania School of Nursing, Philadelphia (Dr Polomano)
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|
7
|
Staab EM, Franco MI, Zhu M, Wan W, Gibbons RD, Vinci LM, Beckman N, Yohanna D, Laiteerapong N. Population Health Management Approach to Depression Symptom Monitoring in Primary Care via Patient Portal: A Randomized Controlled Trial. Am J Med Qual 2023; 38:188-195. [PMID: 37314235 DOI: 10.1097/jmq.0000000000000126] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Depression is undertreated in primary care. Using patient portals to administer regular symptom assessments could facilitate more timely care. At an urban academic medical center outpatient clinic, patients with active portal accounts and depression on their problem list or a positive screen in the past year were randomized to assessment during triage at visits (usual care) versus usual care plus assessment via portal (population health care). Portal invitations were sent regardless of whether patients had scheduled appointments. More patients completed assessments in the population health care arm than usual care: 59% versus 18%, P < 0.001. Depression symptoms were more common among patients who completed their initial assessment via the portal versus in the clinic. In the population health care arm, 57% (N = 80/140) of patients with moderate-to-severe symptoms completed at least 1 follow-up assessment versus 37% (N = 13/35) in usual care. A portal-based population health approach could improve depression monitoring in primary care.
Collapse
Affiliation(s)
- Erin M Staab
- Department of Medicine, University of Chicago, Chicago, IL
| | | | - Mengqi Zhu
- Department of Medicine, University of Chicago, Chicago, IL
| | - Wen Wan
- Department of Medicine, University of Chicago, Chicago, IL
| | - Robert D Gibbons
- Department of Psychiatry and Behavioral Neuroscience, University of Chicago, Chicago, IL
- Department of Public Health Sciences, University of Chicago, Chicago, IL
| | - Lisa M Vinci
- Department of Medicine, University of Chicago, Chicago, IL
| | - Nancy Beckman
- Department of Psychiatry and Behavioral Neuroscience, University of Chicago, Chicago, IL
| | - Daniel Yohanna
- Department of Psychiatry and Behavioral Neuroscience, University of Chicago, Chicago, IL
| | | |
Collapse
|