1
|
Bancks MP, Pilla SJ, Balasubramanyam A, Yeh HC, Johnson KC, Rigdon J, Wagenknecht LE, Espeland MA. Association of Lifestyle Intervention With Risk for Cardiovascular Events Differs by Level of Glycated Hemoglobin. J Clin Endocrinol Metab 2024; 109:e1012-e1019. [PMID: 37978826 PMCID: PMC10876384 DOI: 10.1210/clinem/dgad674] [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: 08/07/2023] [Revised: 10/30/2023] [Accepted: 11/15/2023] [Indexed: 11/19/2023]
Abstract
PURPOSE We reevaluated the Action for Health in Diabetes (Look AHEAD) intensive lifestyle intervention (ILI) to assess whether the effect of ILI on cardiovascular disease (CVD) prevention differed by baseline glycated hemoglobin (HbA1c). METHODS Look AHEAD randomized 5145 adults, aged 45 to 76 years with type 2 diabetes and overweight/obesity to ILI or a diabetes support and education (DSE) control group for a median of 9.6 years. ILI focused on achieving weight loss through decreased caloric intake and increased physical activity. We assessed the parent trial's primary composite CVD outcome. We evaluated additive and multiplicative heterogeneity of the intervention on CVD risk by baseline HbA1c. RESULTS Mean baseline HbA1c was 7.3% (SD 1.2) and ranged from 4.4% (quintile 1) to 14.5% (quintile 5). We observed additive and multiplicative heterogeneity of the association between ILI and CVD (all P < .001) by baseline HbA1c. Randomization to ILI was associated with lower CVD risk for HbA1c quintiles 1 [hazard ratio (HR): 0.68, 95% confidence interval (CI): 0.53, 0.88] and 2 (HR: 0.80, 95% CI: 0.66, 0.96) and associated with higher CVD risk for HbA1c quintile 5 (HR: 1.27, 95% CI: 1.02, 1.58), compared to DSE. CONCLUSION Among adults with type 2 diabetes and overweight/obesity, randomization to a lifestyle intervention was differentially associated with CVD risk by baseline HbA1c such that it was associated with lower risk at lower HbA1c levels and higher risk at higher HbA1c levels. There is a critical need to develop and tailor lifestyle interventions to be successful for individuals with type 2 diabetes and high HbA1c.
Collapse
Affiliation(s)
- Michael P Bancks
- Department of Epidemiology and Prevention, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA
| | - Scott J Pilla
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD 21205, USA
| | | | - Hsin-Chieh Yeh
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD 21205, USA
| | - Karen C Johnson
- Department of Preventive Medicine, University of Tennessee Health Science Center, Memphis, TN 38163, USA
| | - Joseph Rigdon
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA
| | - Lynne E Wagenknecht
- Department of Epidemiology and Prevention, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA
| | - Mark A Espeland
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA
- Department of Internal Medicine, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA
| |
Collapse
|
2
|
Master SR, Badrick TC, Bietenbeck A, Haymond S. Machine Learning in Laboratory Medicine: Recommendations of the IFCC Working Group. Clin Chem 2023:7186579. [PMID: 37252943 DOI: 10.1093/clinchem/hvad055] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Accepted: 04/12/2023] [Indexed: 06/01/2023]
Abstract
BACKGROUND Machine learning (ML) has been applied to an increasing number of predictive problems in laboratory medicine, and published work to date suggests that it has tremendous potential for clinical applications. However, a number of groups have noted the potential pitfalls associated with this work, particularly if certain details of the development and validation pipelines are not carefully controlled. METHODS To address these pitfalls and other specific challenges when applying machine learning in a laboratory medicine setting, a working group of the International Federation for Clinical Chemistry and Laboratory Medicine was convened to provide a guidance document for this domain. RESULTS This manuscript represents consensus recommendations for best practices from that committee, with the goal of improving the quality of developed and published ML models designed for use in clinical laboratories. CONCLUSIONS The committee believes that implementation of these best practices will improve the quality and reproducibility of machine learning utilized in laboratory medicine. SUMMARY We have provided our consensus assessment of a number of important practices that are required to ensure that valid, reproducible machine learning (ML) models can be applied to address operational and diagnostic questions in the clinical laboratory. These practices span all phases of model development, from problem formulation through predictive implementation. Although it is not possible to exhaustively discuss every potential pitfall in ML workflows, we believe that our current guidelines capture best practices for avoiding the most common and potentially dangerous errors in this important emerging field.
Collapse
Affiliation(s)
- Stephen R Master
- Department of Pathology and Laboratory Medicine, Children's Hospital of Philadelphia, Philadelphia, PA, United States
- Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Tony C Badrick
- Royal College of Pathologists of Australasia Quality Assurance Programs, Sydney, Australia
| | | | - Shannon Haymond
- Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, IL, United States
- Department of Pathology, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States
| |
Collapse
|
3
|
Serota DP, Rosenbloom L, Hervera B, Seo G, Feaster DJ, Metsch LR, Suarez E, Chueng TA, Hernandez S, Rodriguez AE, Tookes HE, Doblecki-Lewis S, Bartholomew TS. Integrated Infectious Disease and Substance Use Disorder Care for the Treatment of Injection Drug Use-Associated Infections: A Prospective Cohort Study With Historical Control. Open Forum Infect Dis 2023; 10:ofac688. [PMID: 36632415 PMCID: PMC9830545 DOI: 10.1093/ofid/ofac688] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2022] [Accepted: 12/19/2022] [Indexed: 12/24/2022] Open
Abstract
Background To address the infectious disease (ID) and substance use disorder (SUD) syndemic, we developed an integrated ID/SUD clinical team rooted in harm reduction at a county hospital in Miami, Florida. The Severe Injection-Related Infection (SIRI) team treats people who inject drugs (PWID) and provides medical care, SUD treatment, and patient navigation during hospitalization and after hospital discharge. We assessed the impact of the SIRI team on ID and SUD treatment and healthcare utilization outcomes. Methods We prospectively collected data on patients seen by the SIRI team. A diagnostic code algorithm confirmed by chart review was used to identify a historical control group of patients with SIRI hospitalizations in the year preceding implementation of the SIRI team. The primary outcome was death or readmission within 90 days post-hospital discharge. Secondary outcomes included initiation of medications for opioid use disorder (MOUD) and antibiotic course completion. Results There were 129 patients included in the study: 59 in the SIRI team intervention and 70 in the pre-SIRI team control group. SIRI team patients had a 45% risk reduction (aRR, 0.55 [95% confidence interval CI, .32-.95]; 24% vs 44%) of being readmitted in 90 days or dying compared to pre-SIRI historical controls. SIRI team patients were more likely to initiate MOUD in the hospital (93% vs 33%, P < .01), complete antibiotic treatment (90% vs 60%, P < .01), and less likely to have patient-directed discharge (17% vs 37%, P = .02). Conclusions An integrated ID/SUD team was associated with improvements in healthcare utilization, MOUD initiation, and antibiotic completion for PWID with infections.
Collapse
Affiliation(s)
- David P Serota
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Liza Rosenbloom
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Belén Hervera
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Grace Seo
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Daniel J Feaster
- Division of Biostatistics, Department of Public Health Sciences, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Lisa R Metsch
- Department of Sociomedical Sciences, Mailman School of Public Health, Columbia University, New York, New York, USA
| | - Edward Suarez
- Department of Psychiatry and Behavioral Sciences, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Teresa A Chueng
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Salma Hernandez
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Allan E Rodriguez
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Hansel E Tookes
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Susanne Doblecki-Lewis
- Division of Infectious Diseases, Department of Medicine, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Tyler S Bartholomew
- Division of Health Services Research and Policy, Department of Public Health Sciences, University of Miami Miller School of Medicine, Miami, Florida, USA
| |
Collapse
|
4
|
Ratanatharathorn A, Chibnik LB, Koenen KC, Weisskopf MG, Roberts AL. Association of maternal polygenic risk scores for mental illness with perinatal risk factors for offspring mental illness. Sci Adv 2022; 8:eabn3740. [PMID: 36516246 PMCID: PMC9750139 DOI: 10.1126/sciadv.abn3740] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 11/14/2022] [Indexed: 06/17/2023]
Abstract
We examined whether genetic risk for mental illness is associated with known perinatal risk factors for offspring mental illness to determine whether gene-environmental correlation might account for the associations of perinatal factors with mental illness. Among 8983 women with 19,733 pregnancies, we found that genetic risk for mental illness was associated with any smoking during pregnancy [attention-deficit hyperactivity disorder (ADHD) and overall genetic risk], breast-feeding for less than 1 month (ADHD, depression, and overall genetic risk), experience of intimate partner violence in the year before the birth (depression and overall genetic risk), and pregestational overweight or obesity (bipolar disorder). These results indicate that genetic risk may partly account for the association between perinatal conditions and mental illness in offspring.
Collapse
Affiliation(s)
- Andrew Ratanatharathorn
- Department of Epidemiology, Columbia University Mailman School of Public Health, New York, NY 10032, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
| | - Lori B. Chibnik
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
- Department of Neurology, Massachusetts General Hospital, Boston, MA 02114, USA
| | - Karestan C. Koenen
- Department of Epidemiology, Columbia University Mailman School of Public Health, New York, NY 10032, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
- Department of Social and Behavioral Sciences, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
- Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA
- Department of Psychiatry, Massachusetts General Hospital, Boston, MA 02114, USA
| | - Marc G. Weisskopf
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
- Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
| | - Andrea L. Roberts
- Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
| |
Collapse
|