1
|
Browne J, Wu WC, Jiang L, Singh M, Bozzay ML, Kunicki ZJ, Bayer TA, De Vito AN, Primack JM, McGeary JE, Kelso CM, Rudolph JL. Lower odds of successful community discharge after medical hospitalization for Veterans with schizophrenia: A retrospective cohort study of national data. J Psychiatr Res 2024; 173:58-63. [PMID: 38489871 DOI: 10.1016/j.jpsychires.2024.03.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Revised: 02/23/2024] [Accepted: 03/04/2024] [Indexed: 03/17/2024]
Abstract
Medical comorbidity, particularly cardiovascular diseases, contributes to high rates of hospital admission and early mortality in people with schizophrenia. The 30 days following hospital discharge represents a critical period for mitigating adverse outcomes. This study examined the odds of successful community discharge among Veterans with schizophrenia compared to those with major affective disorders and those without serious mental illness (SMI) after a heart failure hospital admission. Data for Veterans hospitalized for heart failure were obtained from the Veterans Health Administration (VHA) and Centers for Medicare & Medicaid Services between 2011 and 2019. Psychiatric diagnoses and medical comorbidities were assessed in the year prior to hospitalization. Successful community discharge was defined as remaining in the community without hospital readmission, death, or hospice for 30 days after hospital discharge. Logistic regression analyses adjusting for relevant factors were used to examine whether individuals with a schizophrenia diagnosis showed lower odds of successful community discharge versus both comparison groups. Out of 309,750 total Veterans in the sample, 7377 (2.4%) had schizophrenia or schizoaffective disorder and 32,472 (10.5%) had major affective disorders (bipolar disorder or recurrent major depressive disorder). Results from adjusted logistic regression analyses demonstrated significantly lower odds of successful community discharge for Veterans with schizophrenia compared to the non-SMI (Odds Ratio [OR]: 0.63; 95% Confidence Interval [CI]: 0.60, 0.66) and major affective disorders (OR: 0.65, 95%; CI: 0.62, 0.69) groups. Intervention efforts should target the transition from hospital to home in the subgroup of Veterans with schizophrenia.
Collapse
Affiliation(s)
- Julia Browne
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA.
| | - Wen-Chih Wu
- Medical Service, VA Providence Healthcare System, Providence, RI, USA
| | - Lan Jiang
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA
| | - Mriganka Singh
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA
| | - Melanie L Bozzay
- Wexner Medical Center, The Ohio State University, Columbus, OH, USA
| | - Zachary J Kunicki
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA
| | - Thomas A Bayer
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Division of Geriatrics and Palliative Medicine, Alpert Medical School of Brown University, Providence, RI, USA
| | - Alyssa N De Vito
- Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA; Memory and Aging Program, Butler Hospital, Providence, RI, USA
| | - Jennifer M Primack
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA
| | - John E McGeary
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA
| | - Catherine M Kelso
- Veterans Health Administration, Office of Patient Care Services, Geriatrics and Extended Care, Washington DC, USA
| | - James L Rudolph
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Health Services, Policy & Practice, Brown University, Providence, RI, USA
| |
Collapse
|
2
|
Dai P, Shi Y, Lu D, Zhou Y, Luo J, He Z, Chen Z, Zou B, Tang H, Huang Z, Liao S. Classification of recurrent major depressive disorder using a residual denoising autoencoder framework: Insights from large-scale multisite fMRI data. Comput Methods Programs Biomed 2024; 247:108114. [PMID: 38447315 DOI: 10.1016/j.cmpb.2024.108114] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Revised: 02/14/2024] [Accepted: 03/01/2024] [Indexed: 03/08/2024]
Abstract
BACKGROUND AND OBJECTIVE Recurrent major depressive disorder (rMDD) has a high recurrence rate, and symptoms often worsen with each episode. Classifying rMDD using functional magnetic resonance imaging (fMRI) can enhance understanding of brain activity and aid diagnosis and treatment of this disorder. METHODS We developed a Residual Denoising Autoencoder (Res-DAE) framework for the classification of rMDD. The functional connectivity (FC) was extracted from fMRI data as features. The framework addresses site heterogeneity by employing the Combat method to harmonize feature distribution differences. A feature selection method based on Fisher scores was used to reduce redundant information in the features. A data augmentation strategy using a Synthetic Minority Over-sampling Technique algorithm based on Extended Frobenius Norm measure was incorporated to increase the sample size. Furthermore, a residual module was integrated into the autoencoder network to preserve important features and improve the classification accuracy. RESULTS We tested our framework on a large-scale, multisite fMRI dataset, which includes 189 rMDD patients and 427 healthy controls. The Res-DAE achieved an average accuracy of 75.1 % (sensitivity = 69 %, specificity = 77.8 %) in cross-validation, thereby outperforming comparison methods. In a larger dataset that also includes first-episode depression (comprising 832 MDD patients and 779 healthy controls), the accuracy reached 70 %. CONCLUSIONS We proposed a deep learning framework that can effectively classify rMDD and 33 identify the altered FC associated with rMDD. Our study may reveal changes in brain function 34 associated with rMDD and provide assistance for the diagnosis and treatment of rMDD.
Collapse
Affiliation(s)
- Peishan Dai
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China.
| | - Yun Shi
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Da Lu
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Ying Zhou
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Jialin Luo
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Zhuang He
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Zailiang Chen
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Beiji Zou
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| | - Hui Tang
- Department of Psychiatry, and National Clinical Research Center for Mental Disorders, The Second Xiangya Hospital of Central South University, Changsha, Hunan 410083, China
| | - Zhongchao Huang
- Department of Biomedical Engineering, School of Basic Medical Science, Central South University, Changsha, Hunan 410083, China
| | - Shenghui Liao
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China
| |
Collapse
|
3
|
Browne J, Rudolph JL, Jiang L, Bayer TA, Kunicki ZJ, De Vito AN, Bozzay ML, McGeary JE, Kelso CM, Wu WC. Serious mental illness is associated with elevated risk of hospital readmission in veterans with heart failure. J Psychosom Res 2024; 178:111604. [PMID: 38309130 DOI: 10.1016/j.jpsychores.2024.111604] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Revised: 01/23/2024] [Accepted: 01/29/2024] [Indexed: 02/05/2024]
Abstract
OBJECTIVE Adults with serious mental illness (SMI) have high rates of cardiovascular disease, particularly heart failure, which contribute to premature mortality. The aims were to examine 90- and 365-day all-cause medical or surgical hospital readmission in Veterans with SMI discharged from a heart failure hospitalization. The exploratory aim was to evaluate 180-day post-discharge engagement in cardiac rehabilitation, an effective intervention for heart failure. METHODS This study used administrative data from the Veterans Health Administration (VHA) and Centers for Medicare & Medicaid Services between 2011 and 2019. SMI status and medical comorbidity were assessed in the year prior to hospitalization. Cox proportional hazards models (competing risk of death) were used to evaluate the relationship between SMI status and outcomes. Models were adjusted for VHA hospital site, demographics, and medical characteristics. RESULTS The sample comprised 189,767 Veterans of which 23,671 (12.5%) had SMI. Compared to those without SMI, Veterans with SMI had significantly higher readmission rates at 90 (16.1% vs. 13.9%) and 365 (42.6% vs. 37.1%) days. After adjustment, risk of readmission remained significant (90 days: HR: 1.07, 95% CI: 1.03, 1.11; 365 days: HR: 1.10, 95% CI: 1.07, 1.12). SMI status was not significantly associated with 180-day cardiac rehabilitation engagement (HR: 0.98, 95% CI: 0.91, 1.07). CONCLUSIONS Veterans with SMI and heart failure have higher 90- and 365-day hospital readmission rates even after adjustment. There were no differences in cardiac rehabilitation engagement based on SMI status. Future work should consider a broader range of post-discharge interventions to understand contributors to readmission.
Collapse
Affiliation(s)
- Julia Browne
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA.
| | - James L Rudolph
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Health Services, Policy & Practice, Brown University, Providence, RI, USA
| | - Lan Jiang
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA
| | - Thomas A Bayer
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA
| | - Zachary J Kunicki
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA
| | - Alyssa N De Vito
- Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA; Memory and Aging Program, Butler Hospital, Providence, RI, USA
| | - Melanie L Bozzay
- Wexner Medical Center, The Ohio State University, Columbus, OH, USA
| | - John E McGeary
- Center of Innovation in Long Term Services and Supports, VA Providence Healthcare System, Providence, RI, USA; Department of Psychiatry and Human Behavior, Alpert Medical School of Brown University, Providence, RI, USA
| | - Catherine M Kelso
- Veterans Health Administration, Office of Patient Care Services, Geriatrics and Extended Care, Washington DC, USA
| | - Wen-Chih Wu
- Medical Service, VA Providence Healthcare System, Providence, RI, USA
| |
Collapse
|
4
|
Dai P, Lu D, Shi Y, Zhou Y, Xiong T, Zhou X, Chen Z, Zou B, Tang H, Huang Z, Liao S. Classification of recurrent major depressive disorder using a new time series feature extraction method through multisite rs-fMRI data. J Affect Disord 2023; 339:511-519. [PMID: 37467800 DOI: 10.1016/j.jad.2023.07.077] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 06/23/2023] [Accepted: 07/14/2023] [Indexed: 07/21/2023]
Abstract
BACKGROUND Major depressive disorder (MDD) has a high rate of recurrence. Identifying patients with recurrent MDD is advantageous in adopting prevention strategies to reduce the disabling effects of depression. METHOD We propose a novel feature extraction method that includes dynamic temporal information, and inputs the extracted features into a graph convolutional network (GCN) to achieve classification of recurrent MDD. We extract the average time series using an atlas from resting-state functional magnetic resonance imaging (fMRI) data. Pearson correlation was calculated between brain region sequences at each time point, representing the functional connectivity at each time point. The connectivity is used as the adjacency matrix and the brain region sequences as node features for a GCN model to classify recurrent MDD. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to analyze the contribution of different brain regions to the model. Brain regions making greater contribution to classification were considered to be the regions with altered brain function in recurrent MDD. RESULT We achieved a classification accuracy of 75.8 % for recurrent MDD on the multi-site dataset, the Rest-meta-MDD. The brain regions closely related to recurrent MDD have been identified. LIMITATION The pre-processing stage may affect the final classification performance and harmonizing site differences may improve the classification performance. CONCLUSION The experimental results demonstrate that the proposed method can effectively classify recurrent MDD and extract dynamic changes of brain activity patterns in recurrent depression.
Collapse
Affiliation(s)
- Peishan Dai
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China.
| | - Da Lu
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Yun Shi
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Ying Zhou
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Tong Xiong
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Xiaoyan Zhou
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Zailiang Chen
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Beiji Zou
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China
| | - Hui Tang
- Department of Psychiatry, and National Clinical Research Center for Mental Disorders, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China
| | - Zhongchao Huang
- Department of Biomedical Engineering, School of Basic Medical Science, Central South University, Changsha, Hunan, China
| | - Shenghui Liao
- School of Computer Science and Engineering, Central South University, Changsha, Hunan, China.
| |
Collapse
|
5
|
Fond G, Baumstarck K, Auquier P, Fernandes S, Pauly V, Bernard C, Orleans V, Llorca PM, Lançon C, Salas S, Boyer L. Recurrent major depressive disorder's impact on end-of-life care of cancer: A nationwide study. J Affect Disord 2020; 263:326-335. [PMID: 31969262 DOI: 10.1016/j.jad.2019.12.003] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/20/2019] [Revised: 11/28/2019] [Accepted: 12/04/2019] [Indexed: 12/23/2022]
Abstract
OBJECTIVE We still don't know if recurrent major depressive disorder (RMDD) may impact the quality of the end-of-life (EOL) cancer care in France. To tackle this knowledge gap, we explored EOL care in RMDD subjects who died from cancer compared to subjects without psychiatric disorder in a 4-year nationwide cohort study. DESIGN Nationwide cohort study. SETTING National hospital database, France. PARTICIPANTS All patients aged ≥15 years who died from cancer in hospital: 4070 RMDD subjects and 222,477 controls, 2013-2016, France. MAIN OUTCOME MEASURES Palliative care in the last 31 days of life and high-intensity EOL care including chemotherapy in the last 14 days of life, artificial nutrition, tracheal intubation, mechanical ventilation, gastrostomy, cardiopulmonary resuscitation, dialysis, transfusion, surgery, endoscopy, imaging, intensive care unit and emergency department admission in the last 31 days of life. Multivariate generalized mixed models with log-normal distribution was used to compare RMDD subjects and controls. RESULTS Compared to the controls, the RMDD subjects died 3 years younger, had more comorbidities, more thoracic cancers, less metastases and longer time from cancer diagnosis to death. After matching and adjustment, subjects with RMDD were found to receive more palliative care and less high-intensity EOL care, had fewer iterative admissions to acute care unit, and died less often in the intensive care unit and emergency department. CONCLUSIONS RMDD subjects were more likely to receive palliative care associated with less high-intensity EOL care. Yet the interpretation may be discussed, resulting from either patients'/families' wishes or difficulties for providers in offering personalized care to RMDD.
Collapse
Affiliation(s)
- Guillaume Fond
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France; Department of Medical Information, APHM, Marseille, France; Department of Epidemiology and Health Economics, APHM, Marseille, France.
| | - Karine Baumstarck
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France
| | - Pascal Auquier
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France; Department of Epidemiology and Health Economics, APHM, Marseille, France
| | - Sara Fernandes
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France
| | - Vanessa Pauly
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France; Department of Medical Information, APHM, Marseille, France
| | - Cecile Bernard
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France
| | | | | | - Christophe Lançon
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France; Department of Psychiatry, APHM, Marseille, France
| | | | - Laurent Boyer
- Aix-Marseille Univ., CEReSS - Health Service Research and Quality of Life Center, Marseille, France; Department of Medical Information, APHM, Marseille, France; Department of Epidemiology and Health Economics, APHM, Marseille, France
| |
Collapse
|
6
|
Abstract
Major depressive disorder (MDD) is a leading cause of disability worldwide. After the first episode, patients with remitted MDD have a 60% chance of experiencing a second episode. Consideration of therapy continuation should be viewed in terms of the balance between the adverse effects of medication and the need to prevent a possible relapse. Relapse during the early stages of MDD could be prevented more efficiently by conducting individual risk assessments and providing justification for continuing therapy. Our previous work established the neuroimaging markers of relapse by comparing patients with recurrent major depressive disorder (rMDD) in depressive and remitted states. However, it is not known which of these markers are trait markers that present before initial relapse and, consequently, predict disease course. Here, we first describe how inflammation can be translated to subtype-specific clinical features and suggest how this could be used to facilitate clinical diagnosis and treatment. Next, we address the central and peripheral functional state of the immune system in patients with MDD. In addition, we emphasize the important link between the number of depressive episodes and rMDD and use neuroimaging to propose a model for the latter. Last, we address how inflammation can affect brain circuits, providing a possible mechanism for rMDD. Our review suggests a link between inflammatory processes and brain region/circuits in rMDD.
Collapse
Affiliation(s)
- Chun-Hong Liu
- Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing Institute of Traditional Chinese Medicine, Beijing Key Laboratory of Acupuncture Neuromodulation, Beijing, 100010, China
| | - Guang-Zhong Zhang
- Dermatological Department, Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing, 100010, China
| | - Bin Li
- Acupuncture and Moxibustion Department, Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing, 100010, China
| | - Meng Li
- Clinical Affective Neuroimaging Laboratory (CANLAB), Otto-von-Guericke-University Magdeburg, Magdeburg, 39120, Germany
| | - Marie Woelfer
- Clinical Affective Neuroimaging Laboratory (CANLAB), Otto-von-Guericke-University Magdeburg, Magdeburg, 39120, Germany.,Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ, 07102, USA
| | - Martin Walter
- Clinical Affective Neuroimaging Laboratory (CANLAB), Otto-von-Guericke-University Magdeburg, Magdeburg, 39120, Germany.,Department of Psychiatry and Psychotherapy, University of Tuebingen, Tubeingen, 72074, Germany.,Leibniz Institute for Neurobiology, Magdeburg, 39118, Germany
| | - Lihong Wang
- Department of Psychiatry, University of Connecticut Health Center, Farmington, CT, 06030, USA.
| |
Collapse
|