1
|
Economou-Zavlanos NJ, Bessias S, Cary MP, Bedoya AD, Goldstein BA, Jelovsek JE, O’Brien CL, Walden N, Elmore M, Parrish AB, Elengold S, Lytle KS, Balu S, Lipkin ME, Shariff AI, Gao M, Leverenz D, Henao R, Ming DY, Gallagher DM, Pencina MJ, Poon EG. Translating ethical and quality principles for the effective, safe and fair development, deployment and use of artificial intelligence technologies in healthcare. J Am Med Inform Assoc 2024; 31:705-713. [PMID: 38031481 PMCID: PMC10873841 DOI: 10.1093/jamia/ocad221] [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] [Subscribe] [Scholar Register] [Received: 06/22/2023] [Revised: 10/06/2023] [Accepted: 11/03/2023] [Indexed: 12/01/2023] Open
Abstract
OBJECTIVE The complexity and rapid pace of development of algorithmic technologies pose challenges for their regulation and oversight in healthcare settings. We sought to improve our institution's approach to evaluation and governance of algorithmic technologies used in clinical care and operations by creating an Implementation Guide that standardizes evaluation criteria so that local oversight is performed in an objective fashion. MATERIALS AND METHODS Building on a framework that applies key ethical and quality principles (clinical value and safety, fairness and equity, usability and adoption, transparency and accountability, and regulatory compliance), we created concrete guidelines for evaluating algorithmic technologies at our institution. RESULTS An Implementation Guide articulates evaluation criteria used during review of algorithmic technologies and details what evidence supports the implementation of ethical and quality principles for trustworthy health AI. Application of the processes described in the Implementation Guide can lead to algorithms that are safer as well as more effective, fair, and equitable upon implementation, as illustrated through 4 examples of technologies at different phases of the algorithmic lifecycle that underwent evaluation at our academic medical center. DISCUSSION By providing clear descriptions/definitions of evaluation criteria and embedding them within standardized processes, we streamlined oversight processes and educated communities using and developing algorithmic technologies within our institution. CONCLUSIONS We developed a scalable, adaptable framework for translating principles into evaluation criteria and specific requirements that support trustworthy implementation of algorithmic technologies in patient care and healthcare operations.
Collapse
Affiliation(s)
| | - Sophia Bessias
- Duke AI Health, Duke University School of Medicine, Durham, NC 27705, United States
| | - Michael P Cary
- Duke AI Health, Duke University School of Medicine, Durham, NC 27705, United States
- Duke University School of Nursing, Durham, NC 27710, United States
| | - Armando D Bedoya
- Duke Health Technology Solutions, Duke University Health System, Durham, NC 27705, United States
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
| | - Benjamin A Goldstein
- Duke AI Health, Duke University School of Medicine, Durham, NC 27705, United States
- Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC 27705, United States
| | - John E Jelovsek
- Department of Obstetrics and Gynecology, Duke University School of Medicine, Durham, NC 27710, United States
| | - Cara L O’Brien
- Duke Health Technology Solutions, Duke University Health System, Durham, NC 27705, United States
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
| | - Nancy Walden
- Duke AI Health, Duke University School of Medicine, Durham, NC 27705, United States
| | - Matthew Elmore
- Duke AI Health, Duke University School of Medicine, Durham, NC 27705, United States
| | - Amanda B Parrish
- Office of Regulatory Affairs and Quality, Duke University School of Medicine, Durham, NC 27705, United States
| | - Scott Elengold
- Office of Counsel, Duke University, Durham, NC 27701, United States
| | - Kay S Lytle
- Duke University School of Nursing, Durham, NC 27710, United States
- Duke Health Technology Solutions, Duke University Health System, Durham, NC 27705, United States
| | - Suresh Balu
- Duke Institute for Health Innovation, Duke University, Durham, NC 27701, United States
| | - Michael E Lipkin
- Department of Urology, Duke University School of Medicine, Durham, NC 27710, United States
| | - Afreen Idris Shariff
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
- Duke Endocrine-Oncology Program, Duke University Health System, Durham, NC 27710, United States
| | - Michael Gao
- Duke Institute for Health Innovation, Duke University, Durham, NC 27701, United States
| | - David Leverenz
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
| | - Ricardo Henao
- Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC 27705, United States
- Department of Bioengineering, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia
| | - David Y Ming
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
- Duke Department of Pediatrics, Duke University Health System, Durham, NC 27705, United States
- Department of Population Health Sciences, Duke University School of Medicine, Durham, NC 27701, United States
| | - David M Gallagher
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
| | - Michael J Pencina
- Duke AI Health, Duke University School of Medicine, Durham, NC 27705, United States
- Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC 27705, United States
| | - Eric G Poon
- Duke Health Technology Solutions, Duke University Health System, Durham, NC 27705, United States
- Department of Medicine, Duke University School of Medicine, Durham, NC 27710, United States
- Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC 27705, United States
| |
Collapse
|
2
|
Shariff AI, Qamar A, Rivera JV, Mozingo LK, Thacker C, Rushing C, Jung S, Salama AK, D’Alessio DA. SAT-414 A Single Center Retrospective Analysis and Review of Endocrinopathies from Immune Checkpoint Inhibitors Between 2007 and 2017. J Endocr Soc 2020. [PMCID: PMC7209427 DOI: 10.1210/jendso/bvaa046.758] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
Immune checkpoint inhibitors (ICI) specifically target and dysregulate immune tolerance. As a result of this immune activation, immune related adverse events (irAEs) are common. These can include endocrinopathies like immune hypophysitis (IH), primary adrenal insufficiency (PAI), autoimmune thyroid disease, Graves disease and type 1 Diabetes Mellitus (T1DM)[1]. The aim of this retrospective review was to describe the prevalence, timing, and clinical characteristics of ICI-related endocrinopathies at our institution. Methods: A retrospective chart review was conducted for all patients between January 01, 2007 and February 01, 2017 who met predefined clinical, biochemical and imaging criteria for endocrinopathies including IH, T1DM, autoimmune thyroid disease, Graves disease and PAI. Results: Among 690 patients who received ICPI during the study period, 91 unique patients with complete data developed endocrinopathies, for an overall prevalence of 13%. The study included 50 (55%) men and 41 (45%) women with a median age of 64 years (range 20-96 years). Grade 2 endocrinopathies were reported more commonly (n=49, 54%); grade 3/4 events were rare (15%). Among the ICIs, Nivolumab was the most common ICI noted for study patients (n=51, 56%). Autoimmune thyroid disease was the most common irAE in our study (n= 63, 9.1% overall prevalence). We also report 25 cases of IH (3.6%), 2 cases of PAI (0.3%) and 1 case of Graves disease (0.1%). Most patients with autoimmune thyroid disease developed subclinical hypothyroidism (n=26, 3.8%) and overt hyperthyroidism (n=21, 3.0%). We note a high median TSH of 67.3 µIU/mL; range- 20.6-111.0 in overt hypothyroidism compared to subclinical hypothyroidism (14.0 µIU/mL; range- 5.6-100 µIU/mL). Overall, median time to developing any endocrinopathy after initiating ICI was 13.7 weeks; range- 0.7-351.5 weeks. Among the subjects who developed IH, the median TSH was 0.37 µIU/mL (0.01 - 62.39 µIU/mL) with a free T4 of 0.74 ng/dL (0.25-1.86 ng/dL) and the median cortisol was 0.80 µg/dL (0.25-24.5 µg/dL). Amongst the IH group, 17 patients developed isolated secondary adrenal insufficiency and 8 patients developed combination of other hormone deficiencies with secondary AI including 6 with secondary hypothyroidism, 1 patient with hypogonadotropic hypogonadism and 1 with hypothyroidism and hypogonadism in addition to secondary AI. Despite development of irAEs, ICI therapy was continued in 59 pts (65%) who developed an endocrine irAE. Conclusions: In summary, this is one of the largest single institution retrospective studies on ICI related endocrinopathies. The majority of endocrinopathies were low grade, and most patients continued ICI treatment. Reference: Barroso-Sousa, Romualdo. Incidence of Endocrine Dysfunction Following the Use of Different Immune Checkpoint Inhibitor Regimens: A Systematic Review and Meta-analysis. JAMA, Sept 2017
Collapse
|
3
|
Shariff AI, Syed S, Shelby RA, Force J, Clarke JM, D'Alessio D, Corsino L. Novel cancer therapies and their association with diabetes. J Mol Endocrinol 2019; 62:R187-R199. [PMID: 30532995 DOI: 10.1530/jme-18-0002] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [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: 10/01/2018] [Accepted: 10/25/2018] [Indexed: 12/29/2022]
Abstract
Over the last decade, there has been a shift in the focus of cancer therapy from conventional cytotoxic drugs to therapies more specifically directed to cancer cells. These novel therapies include immunotherapy, targeted therapy and precision medicine, each developed in great part with a goal of limiting collateral destruction of normal tissues, while enhancing tumor destruction. Although this approach is sound in theory, even new, specific therapies have some undesirable, 'off target effects', in great part due to molecular pathways shared by neoplastic and normal cells. One such undesirable effect is hyperglycemia, which results from either the loss of immune tolerance and autoimmune destruction of pancreatic β-cells or dysregulation of the insulin signaling pathway resulting in insulin resistance. These distinct pathogenic mechanisms lead to clinical presentations similar to type 1 (T1DM) and type 2 (T2DM) diabetes mellitus. Both types of diabetes have been reported in patients across clinical trials, and data on the mechanism(s) for developing hyperglycemia, prevalence, prognosis and effect on cancer mortality is still emerging. With the rapidly expanding list of clinical indications for new cancer therapies, it is essential to understand the impact of their adverse effects. In this review, we focus on hyperglycemia and diabetes related to cancer therapies, describe what is known about mechanism(s) leading to dysregulated glucose metabolism and provide a guide to management of complex oncology patients with a new diagnosis of diabetes.
Collapse
Affiliation(s)
- Afreen Idris Shariff
- Division of Endocrinology, Metabolism and Nutrition, Duke University School of Medicine, Durham, North Carolina, USA
| | - Sohail Syed
- Virginia Commonwealth University, Richmond, Virginia, USA
| | - Rebecca A Shelby
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, North Carolina, USA
| | - Jeremy Force
- Division of Medical Oncology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Jeffrey Melson Clarke
- Division of Medical Oncology, Duke University School of Medicine, Durham, North Carolina, USA
| | - David D'Alessio
- Division of Endocrinology, Metabolism and Nutrition, Duke University School of Medicine, Durham, North Carolina, USA
| | - Leonor Corsino
- Division of Endocrinology, Metabolism and Nutrition, Duke University School of Medicine, Durham, North Carolina, USA
| |
Collapse
|