1
|
Miranda O, Fan P, Qi X, Wang H, Brannock MD, Kosten T, Ryan ND, Kirisci L, Wang L. Prediction of adverse events risk in patients with comorbid post-traumatic stress disorder and alcohol use disorder using electronic medical records by deep learning models. Drug Alcohol Depend 2024; 255:111066. [PMID: 38217979 PMCID: PMC10853953 DOI: 10.1016/j.drugalcdep.2023.111066] [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: 11/02/2023] [Revised: 12/15/2023] [Accepted: 12/15/2023] [Indexed: 01/15/2024]
Abstract
BACKGROUND Identifying co-occurring mental disorders and elevated risk is vital for optimization of healthcare processes. In this study, we will use DeepBiomarker2, an updated version of our deep learning model to predict the adverse events among patients with comorbid post-traumatic stress disorder (PTSD) and alcohol use disorder (AUD), a high-risk population. METHODS We analyzed electronic medical records of 5565 patients from University of Pittsburgh Medical Center to predict adverse events (opioid use disorder, suicide related events, depression, and death) within 3 months at any encounter after the diagnosis of PTSD+AUD by using DeepBiomarker2. We integrated multimodal information including: lab tests, medications, co-morbidities, individual and neighborhood level social determinants of health (SDoH), psychotherapy and veteran data. RESULTS DeepBiomarker2 achieved an area under the receiver operator curve (AUROC) of 0.94 on the prediction of adverse events among those PTSD+AUD patients. Medications such as vilazodone, dronabinol, tenofovir, suvorexant, modafinil, and lamivudine showed potential for risk reduction. SDoH parameters such as cognitive behavioral therapy and trauma focused psychotherapy lowered risk while active veteran status, income segregation, limited access to parks and greenery, low Gini index, limited English-speaking capacity, and younger patients increased risk. CONCLUSIONS Our improved version of DeepBiomarker2 demonstrated its capability of predicting multiple adverse event risk with high accuracy and identifying potential risk and beneficial factors.
Collapse
Affiliation(s)
- Oshin Miranda
- Computational Chemical Genomics Screening Center, Department of Pharmaceutical Sciences/School of Pharmacy, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Peihao Fan
- Computational Chemical Genomics Screening Center, Department of Pharmaceutical Sciences/School of Pharmacy, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Xiguang Qi
- Computational Chemical Genomics Screening Center, Department of Pharmaceutical Sciences/School of Pharmacy, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Haohan Wang
- School of Information Sciences at the University of Illinois Urbana-Champaign, Champaign, IL 61820, USA
| | | | - Thomas Kosten
- Menninger Department of Psychiatry, Baylor College of Medicine, Houston, TX 77030, USA
| | - Neal David Ryan
- Department of Psychiatry, School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
| | - Levent Kirisci
- University of Pittsburgh School of Pharmacy, Pittsburgh, PA 15213, USA
| | - LiRong Wang
- Computational Chemical Genomics Screening Center, Department of Pharmaceutical Sciences/School of Pharmacy, University of Pittsburgh, Pittsburgh, PA 15213, USA.
| |
Collapse
|
2
|
Miranda O, Fan P, Qi X, Wang H, Brannock MD, Kosten T, Ryan ND, Kirisci L, Wang L. Prediction of Adverse Events Risk in Patients with Comorbid Post- Traumatic Stress Disorder and Alcohol Use Disorder Using Electronic Medical Records by Deep Learning Models. Res Sq 2023:rs.3.rs-3299369. [PMID: 37790550 PMCID: PMC10543461 DOI: 10.21203/rs.3.rs-3299369/v1] [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] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/05/2023]
Abstract
Background Prediction of high-risk events in mental disorder patients is crucial. In our previous study, we developed a deep learning model: DeepBiomarker by using electronic medical records (EMR) to predict suicide related event (SRE) risk in post-traumatic stress disorder (PTSD) patients. Methods We applied DeepBiomarker2 through data integration of multimodal information: lab test, medication, co-morbidities, and social determinants of health. We analyzed EMRs of 5,565 patients from University of Pittsburgh Medical Center with a diagnosis of PTSD and alcohol use disorder (AUD) on risk of developing an adverse event (opioid use disorder, SREs, depression and death). Results DeepBiomarker2 predicted whether a PTSD + AUD patient will have a diagnosis of any adverse events (SREs, opioid use disorder, depression, death) within 3 months with area under the receiver operator curve (AUROC) of 0.94. We found piroxicam, vilazodone, dronabinol, tenofovir, suvorexant, empagliflozin, famciclovir, veramyst, amantadine, sulfasalazine, and lamivudine to have potential to reduce risk. Conclusions DeepBiomarker2 can predict multiple adverse event risk with high accuracy and identify potential risk and beneficial factors. Our results offer suggestions for personalized interventions in a variety of clinical and diverse populations.
Collapse
|
3
|
Herodes M, Le N, Anderson LJ, Migula D, Miranda G, Paulsen L, Garcia JM. Metabolic and quality of life effects of growth hormone replacement in patients with TBI and AGHD: A pilot study. Growth Horm IGF Res 2023; 71:101544. [PMID: 37295336 PMCID: PMC10527000 DOI: 10.1016/j.ghir.2023.101544] [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: 04/11/2023] [Revised: 05/25/2023] [Accepted: 05/27/2023] [Indexed: 06/12/2023]
Abstract
OBJECTIVE Traumatic brain injury (TBI), a common cause of adult growth hormone deficiency (AGHD), affects 20% of Veterans returning from Iraq and Afghanistan (OEF/OIF/OND). Growth hormone replacement therapy (GHRT) improves quality of life (QoL) in AGHD but remains unexplored in this population. This pilot, observational study investigates the feasibility and efficacy of GHRT in AGHD following TBI. DESIGN In this 6-month study of combat Veterans with AGHD and TBI starting GHRT (N = 7), feasibility (completion rate and rhGH adherence) and efficacy (improvements in self-reported QoL) of GHRT were measured (primary outcomes). Secondary outcomes included body composition, physical and cognitive function, psychological and somatic symptoms, physical activity, IGF-1 levels and safety parameters. It was hypothesized that participants would adhere to GHRT and that QoL would significantly improve after six months. RESULTS Five subjects (71%) completed all study visits. All patients administered daily rhGH injections, 6 (86%) of whom consistently administered the clinically-prescribed dose. While QoL demonstrated numeric improvement, this change did not reach statistical significance (p = 0.17). Significant improvements were observed in total lean mass (p = 0.02), latissimus dorsi strength (p = 0.05), verbal learning (Trial 1, p = 0.02; Trial 5, p = 0.03), attention (p = 0.02), short-term memory (p = 0.04), and post-traumatic stress disorder (PTSD) symptoms (p = 0.03). Body weight (p = 0.02) and total fat mass (p = 0.03) increased significantly. CONCLUSION GHRT is a feasible and well-tolerated intervention for U.S. Veterans with TBI-related AGHD. It improved key areas impacted by AGHD and symptoms of PTSD. Larger, placebo-controlled studies testing the efficacy and safety of this intervention in this population are warranted.
Collapse
Affiliation(s)
- Megan Herodes
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA; Division of Gerontology and Geriatric Medicine, University of Washington School of Medicine, Seattle, WA, USA
| | - Nancy Le
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA
| | - Lindsey J Anderson
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA
| | - Dorota Migula
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA
| | - Gary Miranda
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA; Division of Gerontology and Geriatric Medicine, University of Washington School of Medicine, Seattle, WA, USA
| | - Lauren Paulsen
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA
| | - Jose M Garcia
- Geriatric Research, Education and Clinical Center, Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA; Division of Gerontology and Geriatric Medicine, University of Washington School of Medicine, Seattle, WA, USA.
| |
Collapse
|
4
|
Halverson TF, Calhoun PS, Elbogen EB, Andover MS, Beckham JC, Pugh MJ, Kimbrel NA. Nonsuicidal self-injury among veterans is associated with psychosocial impairment, suicidal thoughts and behaviors, and underutilization of mental health services. Death Stud 2023; 48:238-249. [PMID: 37235533 PMCID: PMC10676439 DOI: 10.1080/07481187.2023.2216169] [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] [Subscribe] [Scholar Register] [Indexed: 05/28/2023]
Abstract
Nonsuicidal self-injury (NSSI) is a robust predictor of suicide attempts. However, understanding of NSSI and associated treatment utilization among Veterans is limited. Although impairment may be assumed, few studies examine the association between NSSI and psychosocial functioning, a core component of the rehabilitation framework of mental health. In a national survey of Veterans, current NSSI (n = 88) was associated with higher rates of suicidal thoughts and behaviors and more severe psychosocial impairment after adjusting for demographics and probable diagnoses of posttraumatic stress disorder, major depressive disorder, and alcohol use disorder, compared to Veterans without NSSI (n = 979). Only half of Veterans with NSSI were engaged with mental health services, with few appointments attended, suggesting that these Veterans are not receiving treatment interventions. Results underscore the adverse outcomes associated with NSSI. Underutilization of mental health services highlights the importance of screening for NSSI among Veterans to improve psychosocial outcomes.
Collapse
Affiliation(s)
- Tate F Halverson
- Durham Veterans Affairs Health Care System, Durham, NC, USA
- VA Mid-Atlantic Mental Illness Research, Education, and Clinical Center, Durham, North Carolina, USA
| | - Patrick S Calhoun
- Durham Veterans Affairs Health Care System, Durham, NC, USA
- VA Mid-Atlantic Mental Illness Research, Education, and Clinical Center, Durham, North Carolina, USA
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, USA
- VA Health Services Research and Development Center of Innovation to Accelerate Discovery and Practice Transformation, Durham, North Carolina, USA
| | - Eric B Elbogen
- VA Mid-Atlantic Mental Illness Research, Education, and Clinical Center, Durham, North Carolina, USA
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, USA
- VA National Center on Homelessness Among Veterans, Tampa, Florida, USA
| | | | - Jean C Beckham
- Durham Veterans Affairs Health Care System, Durham, NC, USA
- VA Mid-Atlantic Mental Illness Research, Education, and Clinical Center, Durham, North Carolina, USA
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, USA
- VA Health Services Research and Development Center of Innovation to Accelerate Discovery and Practice Transformation, Durham, North Carolina, USA
| | - Mary Jo Pugh
- VA Salt Lake City Healthcare System, Salt Lake City, Utah, USA
- Department of Medicine, School of Medicine, University of Utah, Salt Lake City, Utah, USA
| | - Nathan A Kimbrel
- Durham Veterans Affairs Health Care System, Durham, NC, USA
- VA Mid-Atlantic Mental Illness Research, Education, and Clinical Center, Durham, North Carolina, USA
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, USA
- VA Health Services Research and Development Center of Innovation to Accelerate Discovery and Practice Transformation, Durham, North Carolina, USA
| |
Collapse
|
5
|
Chalker SA, Pozun CT, Ehret BC. Functional impairment, internalized stigma, and well-being: Considerations for recovery-oriented suicide prevention for U.S. Veterans with serious mental illness. Pract Innov (Wash D C) 2023; 2023. [PMID: 37900980 PMCID: PMC10601383 DOI: 10.1037/pri0000213] [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] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/31/2023]
Abstract
Veterans Health Administration's (VHA) Psychosocial Rehabilitation and Recovery Centers (PRRCs) provide recovery-oriented care to Veterans with serious mental illness (SMI). As part of program evaluation, PRRC providers regularly assess recovery-oriented outcomes. Given the high rates of suicidal thoughts and behaviors among Veterans with SMI, understanding such outcomes in relation to suicide risk is crucial. Among Veterans entering a PRRC (N=4,731), the present study aimed to a) report suicidal ideation frequency in the past two weeks across demographics and psychiatric diagnoses, b) explore rates of current functional impairment, internalized stigma, and well-being, and c) examine differences in suicidal ideation frequency and functional impairment, internalized stigma, and well-being. Measurements before treatment were utilized. Younger (ρ=-.08, p<.001), married (z=-5.23, p<.001) Veterans, those not identifying as Black or African American (z=-4.80, p<.001), not diagnosed with schizophrenia (z=-6.97, <.001), diagnosed with depressive disorders (z=-8.79, <.001), anxiety disorders (z=-5.01, <.001), posttraumatic stress disorder (z=-7.69, <.001), or personality disorders (z=-7.12, <.001) were significantly more likely to endorse suicidal ideation. Veterans in this cohort had higher than average functional impairment (M=18.05, SD=9.85), mild internalized stigma (M=2.36, SD=0.51), and lower than average well-being (M=18.96, SD=3.93). The more often a Veteran reported thinking about suicide in the past two weeks, the more likely the Veteran viewed themselves to be more functionally impaired (p<.001), reported higher levels of internalized stigma (p<.001), and reported lower levels of well-being (p<.001). Findings and limitations, particularly the suicidal ideation frequency measurement, are discussed to contextualize suggestions to integrate recovery-oriented practices and suicide prevention care.
Collapse
Affiliation(s)
- Samantha A Chalker
- Veterans Affairs San Diego Healthcare System, San Diego, California, USA
- University of California, San Diego, Department of Psychiatry, San Diego, California, USA
| | - Cara T Pozun
- Veterans Affairs San Diego Healthcare System, San Diego, California, USA
| | - Blaire C Ehret
- Veterans Affairs San Diego Healthcare System, San Diego, California, USA
- University of California, San Diego, Department of Psychiatry, San Diego, California, USA
| |
Collapse
|
6
|
Haydabrus A, Santana-Santana M, Lazarenko Y, Giménez-Llort L. Current War in Ukraine: Lessons from the Impact of War on Combatants' Mental Health during the Last Decade. Int J Environ Res Public Health 2022; 19:10536. [PMID: 36078250 PMCID: PMC9518138 DOI: 10.3390/ijerph191710536] [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] [Figures] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Revised: 08/02/2022] [Accepted: 08/22/2022] [Indexed: 06/15/2023]
Abstract
Ukrainian Military Hospital retrospective analysis during a decade of conflicts (3995 records) unveils specific mental health ICD-10-CM distribution per rank and the long-lasting impact of active conflict or trench warfare. Most hospitalizations in all years of observation were among soldiers. Anxiety-related disorders have been present since 'peacetime', mainly among professional soldiers and high ranks, pointing to the need for rank-tailored psychological training in skills to reduce the anxiety burden. High frequency of psychoactive substance use emerged with acute conflicts and in nonprofessional soldiers during wartime. This dictates the need to strengthen the selection of military personnel, considering the tendency to addiction. Military operations multiply the hospitalizations in psychiatric hospitals. The data warn about a 'need for free beds effect', which is worse for soldiers. This is relevant to estimating and planning the need for hospital resources for the current situation where the general population has been recruited for defense. In the current war, tightening the rules of sobriety in units and up to a ban on the sale of alcoholic beverages in areas where hostilities are taking place is recommended. The specific impact on nonprofessional soldiers is relevant to the current war, with the general population of Ukraine recruited for defense and combat.
Collapse
Affiliation(s)
- Andriy Haydabrus
- Department of Neurology, Psychiatry, Narcology and Medical Psychology, School of Medicine, V.N. Karazin Kharkiv National University, 61022 Kharkiv, Ukraine
| | - Mikel Santana-Santana
- Department of Psychiatry and Forensic Medicine, School of Medicine, Universitat Autònoma de Barcelona, 08193 Barcelona, Spain
- Institut de Neurociències, Universitat Autònoma de Barcelona, 08193 Barcelona, Spain
| | - Yuriy Lazarenko
- Military Medical Clinical Center of the Northern Region, 61000 Kharkiv, Ukraine
| | - Lydia Giménez-Llort
- Department of Psychiatry and Forensic Medicine, School of Medicine, Universitat Autònoma de Barcelona, 08193 Barcelona, Spain
- Institut de Neurociències, Universitat Autònoma de Barcelona, 08193 Barcelona, Spain
| |
Collapse
|