Early Detection of Opioid Over-Procurement: A Semisupervised Machine Learning Approach

References

• Abelson J, Williams A, Ba Tran A, Kornfeild M (2019) At height of crisis, Walgreens handled nearly one in five of the most addictive opioids. Washington Post (November 7), https://www.washingtonpost.com/investigations/2019/11/07/height-crisis-walgreens-handled-nearly-one-five-most-addictive-opioids/?arc404=true.Google Scholar
• Alpert A, Evans WN, Lieber EM, Powell D (2022) Origins of the opioid crisis and its enduring impacts. Quart. J. Econom. 137(2):1139–1179.Crossref, Google Scholar
• Aral KD, Güvenir HA, Sabuncuoğlu I, Akar AR (2012) A prescription fraud detection model. Comput. Methods Programs Biomedicine 106(1):37–46.Crossref, Google Scholar
• Bertsimas D, Li M (2020) Fast exact matrix completion: A unifying optimization framework. J. Machine Learn. Res. 21(231):1–43.Google Scholar
• Bertsimas D, Cory-Wright R, Lo S, Pauphilet J (2023) Optimal low-rank matrix completion: Semidefinite relaxations and eigenvector disjunctions. Preprint, submitted May 20, https://arxiv.org/abs/2305.12292v1.Google Scholar
• Bharat C, Hickman M, Barbieri S, Degenhardt L (2021) Big data and predictive modelling for the opioid crisis: Existing research and future potential. Lancet Digital Health 3(6):E397–E407.Crossref, Google Scholar
• Bolton RJ, Hand DJ (2002) Statistical fraud detection: A review. Statist. Sci. 17(3):235–255.Crossref, Google Scholar
• Candes EJ, Plan Y (2010) Matrix completion with noise. Proc. IEEE 98(6):925–936.Crossref, Google Scholar
• Case A, Deaton A (2020) Deaths of Despair and the Future of Capitalism (Princeton University Press, Princeton, NJ).Google Scholar
• CDC (2021) Drug overdose deaths data. Centers for Disease Control and Prevention. Accessed July 31, 2025, https://www.cdc.gov/nchs/nvss/vsrr/drug-overdose-data.htm.Google Scholar
• Che Z, St Sauver J, Liu H, Liu Y (2018) Deep learning solutions for classifying patients on opioid use. AMIA Annual Sympos. Proc. 2017:525–534.Google Scholar
• Dong X, Deng J, Hou W, Rashidian S, Rosenthal RN, Saltz M, Saltz JH, Wang F (2021) Predicting opioid overdose risk of patients with opioid prescriptions using electronic health records based on temporal deep learning. J. Biomedical Informatics 116:103725.Crossref, Google Scholar
• Dong X, Rashidian S, Wang Y, Hajagos J, Zhao X, Rosenthal RN, Kong J, Saltz M, Saltz J, Wang F (2020) Machine learning based opioid overdose prediction using electronic health records. AMIA Annual Sympos. Proc. 2019:389–398.Google Scholar
• Dufour R, Mardekian J, Pasquale MK, Schaaf D, Andrews GA, Patel NC (2014) Understanding predictors of opioid abuse: Predictive model development and validation. Pharmacy Times (October 20), https://www.pharmacytimes.com/view/understanding-predictors-of-opioid-abuse-predictive-model-development-and-validation.Google Scholar
• Ellis DI, Muhamadali H, Haughey SA, Elliott CT, Goodacre R (2015) Point-and-shoot: Rapid quantitative detection methods for on-site food fraud analysis—Moving out of the laboratory and into the food supply chain. Anal. Methods 7(22):9401–9414.Crossref, Google Scholar
• Ellis RJ, Wang Z, Genes N, Ma’ayan A (2019) Predicting opioid dependence from electronic health records with machine learning. BioData Mining 12:3.Crossref, Google Scholar
• Enyinda CI, Mbah CHN, Ogbuehi A (2010) An empirical analysis of risk mitigation in the pharmaceutical industry supply chain: A developing-country perspective. Thunderbird Internat. Bus. Rev. 52(1):45–54.Crossref, Google Scholar
• Farias VF, Li AA (2019) Learning preferences with side information. Management Sci. 65(7):3131–3149.Link, Google Scholar
• Grimani A, Gavine A, Moncur W (2020) An evidence synthesis of strategies, enablers and barriers for keeping secrets online regarding the procurement and supply of illicit drugs. Internat. J. Drug Policy 75:102621.Crossref, Google Scholar
• Han DH, Lee S, Seo DC (2020) Using machine learning to predict opioid misuse among U.S. adolescents. Preventive Medicine 130:105886.Crossref, Google Scholar
• Hastings JS, Howison M, Inman SE (2020) Predicting high-risk opioid prescriptions before they are given. Proc. Natl. Acad. Sci. USA 117(4):1917–1923.Crossref, Google Scholar
• Hylan TR, Von Korff M, Saunders K, Masters E, Palmer RE, Carrell D, Cronkite D, Mardekian J, Gross D (2015) Automated prediction of risk for problem opioid use in a primary care setting. J. Pain. 16(4):380–387.Crossref, Google Scholar
• Jaberidoost M, Nikfar S, Abdollahiasl A, Dinarvand R (2013) Pharmaceutical supply chain risks: A systematic review. DARU J. Pharmaceutical Sci. 21(1):69.Crossref, Google Scholar
• Jónasson JO, Kaw N, Sinha D, Trichakis N, Chen A, Conte J, Restaino A, Volpe S (2021) Preventing opioid overdose: From prediction to operationalization. SSRN Scholarly Paper ID 3842424, Social Science Research Network, Rochester, NY.Google Scholar
• Joudaki H, Rashidian A, Minaei-Bidgoli B, Mahmoodi M, Geraili B, Nasiri M, Arab M (2014) Using data mining to detect health care fraud and abuse: A review of literature. Global J. Health Sci. 7(1):194–202.Crossref, Google Scholar
• Kenan K, Mack K, Paulozzi L (2012) Trends in prescriptions for oxycodone and other commonly used opioids in the United States, 2000-2010. Open Medicine 6:e41–e47.Google Scholar
• Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30–37.Crossref, Google Scholar
• Kraus C, Valverde R (2014) A data warehouse design for the detection or fraud in the supply chain by using the Benford’s Law. Amer. J. Appl. Sci. 11(9):1507–1518.Crossref, Google Scholar
• Li J, Huang KY, Jin J, Shi J (2008) A survey on statistical methods for health care fraud detection. Health Care Management Sci. 11(3):275–287.Crossref, Google Scholar
• Li J, Xu Q, Shah N, Mackey TK (2019) A machine learning approach for the detection and characterization of illicit drug dealers on Instagram: Model evaluation study. J. Medical Internet Res. 21(6):e13803.Crossref, Google Scholar
• Liu Q, Vasarhelyi M (2013) Healthcare fraud detection: A survey and a clustering model incorporating geo-location information. Presented 29th World Continuous Auditing Report. Sympos. (29WCARS) (Brisbane, Australia).Google Scholar
• Lo-Ciganic WH, Donohue JM, Hulsey EG, Barnes S, Li Y, Kuza CC, Yang Q, et al. (2021) Integrating human services and criminal justice data with claims data to predict risk of opioid overdose among Medicaid beneficiaries: A machine-learning approach. PLoS One 16(3):e0248360.Crossref, Google Scholar
• Lo-Ciganic WH, Huang JL, Zhang HH, Weiss JC, Wu Y, Kwoh CK, Donohue JM, et al. (2019) Evaluation of machine-learning algorithms for predicting opioid overdose risk among Medicare beneficiaries with opioid prescriptions. JAMA Network Open 2(3):e190968.Crossref, Google Scholar
• Mackey T, Kalyanam J, Klugman J, Kuzmenko E, Gupta R (2018) Solution to detect, classify, and report illicit online marketing and sales of controlled substances via Twitter: Using machine learning and web forensics to combat digital opioid access. J. Medical Internet Res. 20(4):e10029.Crossref, Google Scholar
• Mehta N, Pandit A (2018) Concurrence of big data analytics and healthcare: A systematic review. Internat. J. Medical Informatics 114:57–65.Crossref, Google Scholar
• Menachemi N, Collum TH (2011) Benefits and drawbacks of electronic health record systems. Risk Management Healthcare Policy 4:47–55.Crossref, Google Scholar
• National Institute on Drug Abuse (2015) Prescription opioid use is a risk factor for heroin use. Accessed July 31, 2025, http://nida.nih.gov/publications/research-reports/prescription-opioids-heroin/prescription-opioid-use-risk-factor-heroin-use.Google Scholar
• National Institute on Drug Abuse (2021) The opioid epidemic: By the numbers. Accessed July 31, 2025, https://www.drugabuse.gov/drug-topics/opioids/opioid-overdose-crisis#by-the-numbers.Google Scholar
• Ngiam KY, Khor IW (2019) Big data and machine learning algorithms for health-care delivery. Lancet Oncology 20(5):e262–e273.Crossref, Google Scholar
• North Carolina Department of Justice (2020) Attorney General Josh Stein announces $1.6 billion global settlement with opioid manufacturer. Accessed July 31, 2025, https://ncdoj.gov/attorney-general-josh-stein-announces-1-6-billion-global-settlement-with-opioid-manufacturer/.Google Scholar
• Phua C, Lee V, Smith K, Gayler R (2010) A comprehensive survey of data mining-based fraud detection research. Preprint, submitted September 30, https://arxiv.org/abs/1009.6119.Google Scholar
• Prieto JT, Scott K, McEwen D, Podewils LJ, Al-Tayyib A, Robinson J, Edwards D, Foldy S, Shlay JC, Davidson AJ (2020) The detection of opioid misuse and heroin use from paramedic response documentation: Machine learning for improved surveillance. J. Medical Internet Res. 22(1):e15645.Crossref, Google Scholar
• Quinones S (2015) Dreamland: The True Tale of America’s Opiate Epidemic (Bloomsbury Publishing USA, New York).Google Scholar
• Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, Liu PJ, et al. (2018) Scalable and accurate deep learning with electronic health records. NPI Digital Medicine 1:18.Crossref, Google Scholar
• Scholl L, Seth P, Kariisa M, Wilson N, Baldwin G (2018) Drug and opioid-involved overdose deaths—United States, 2013 to 2017. Morbidity Mortality Weekly Rep. 67:1419–1427.Google Scholar
• Shi A, Seetharaman S, Sardella A, Wall M, Abeyakaran C (2024) Tackling the US opioid crisis: Data-driven detection of suspicious retail buyers. Preprint, summitted February 8, https://doi.org/10.21203/rs.3.rs-3645248/v1.Google Scholar
• The Washington Post (2020) DEA database: Where the pain pills went. Washington Post (January 17), https://www.washingtonpost.com/graphics/2019/investigations/dea-pain-pill-database/.Google Scholar
• Topol EJ (2019) High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine 25(1):44–56.Crossref, Google Scholar
• U.S. Department of Justice (2013) Walgreens agrees to pay a record settlement of $80 million for civil penalties under the Controlled Substances Act. Accessed July 31, 2025, https://www.justice.gov/usao-sdfl/pr/walgreens-agrees-pay-record-settlement-80-million-civil-penalties-under-controlled.Google Scholar
• U.S. Department of Justice District Court for the Northern District of Ohio (2020) In re: National prescription opiate litigation (MDL No. 2804). Accessed July 31, 2025, https://www.ohnd.uscourts.gov/mdl-2804.Google Scholar
• U.S. District Court (2020) National prescription opiate litigation (MDL No. 2804). Accessed July 31, 2025, https://www.ohnd.uscourts.gov/mdl-2804.Google Scholar
• U.S. District Court (2021) City of Huntington v. Amerisourcebergen Drug Corp., Civil Action no. 3:17-01362.Google Scholar
• U.S. Government Accountability Office (2020) Drug control: Actions needed to ensure usefulness of data on suspicious opioid orders (Report No. GAO-20-118). Accessed July 31, 2025, https://www.gao.gov/products/gao-20-118.Google Scholar
• U.S. House of Representatives Committee on Energy and Commerce (2018) Hearing on “Combating the Opioid Crisis: Oversight of Distributors’ Role in the Supply Chain.” Accessed July 31, 2025, https://www.congress.gov/115/meeting/house/108260/documents/HHRG-115-IF02-20180508-SD002.pdf.Google Scholar
• van Capelleveen G, Poel M, Mueller RM, Thornton D, van Hillegersberg J (2016) Outlier detection in healthcare fraud: A case study in the Medicaid dental domain. Internat. J. Accounting Inform. Systems 21:18–31.Google Scholar
• van Ruth SM, Luning PA, Silvis ICJ, Yang Y, Huisman W (2018) Differences in fraud vulnerability in various food supply chains and their tiers. Food Control 84:375–381.Crossref, Google Scholar
• Wang M, Jie F (2020) Managing supply chain uncertainty and risk in the pharmaceutical industry. Health Services Management Res. 33(3):156–164.Crossref, Google Scholar
• Wang Y, Hajli N (2017) Exploring the path to big data analytics success in healthcare. J. Bus. Res. 70:287–299.Crossref, Google Scholar
• Wang Y, Kung L, Wang WYC, Cegielski CG (2018) An integrated big data analytics-enabled transformation model: Application to health care. Inform. Management 55(1):64–79.Crossref, Google Scholar
• Zafari B, Ekin T (2019) Topic modelling for medical prescription fraud and abuse detection. J. Roy. Statist. Soc. Ser. C Appl. Statist. 68(3):751–769.Crossref, Google Scholar
• Zhang G, Ou SX, Huang YH, Wang CR (2015) Semi-supervised learning methods for large scale healthcare data analysis. Internat. J. Comput. Healthcare 2(2):98–110.Crossref, Google Scholar
• Zhu X, Goldberg AB (2009) Introduction to semi-supervised learning. Synthesis Lectures Artificial Intelligence Machine Learn. 3(1):1–130.Crossref, Google Scholar
• Zhu S, Wang Y, Wu Y (2011) Health care fraud detection using nonnegative matrix factorization. Proc. 6th Internat. Conf. Comput. Sci. Education (ICCSE) (IEEE, Piscataway, NJ), 499–503.Google Scholar