Development of Predictive Statistical Model for Gaining Valuable Insights in Pharmaceutical Product Recalls.
artificial intelligence
drug quality control
machine learning
multivariate analysis
pharmaceutical recalls
predictive modeling
Journal
AAPS PharmSciTech
ISSN: 1530-9932
Titre abrégé: AAPS PharmSciTech
Pays: United States
ID NLM: 100960111
Informations de publication
Date de publication:
23 Oct 2024
23 Oct 2024
Historique:
received:
05
03
2024
accepted:
07
10
2024
medline:
24
10
2024
pubmed:
24
10
2024
entrez:
23
10
2024
Statut:
epublish
Résumé
The rapid progress in artificial intelligence (AI) has revolutionized problem-solving across various domains. The global challenge of pharmaceutical product recalls imposes the development of effective tools to control and reduce shortage of pharmaceutical products and help avoid such recalls. This study employs AI, specifically machine learning (MI), to analyze critical factors influencing formulation, manufacturing, and formulation complexity which could offer promising avenue for optimizing drug development processes. Utilizing FDAZilla and SafeRX tools, an open database model was constructed, and predictive statistical models were developed using Multivariate Analysis and the Least Absolute Shrinkage and Selection Operator (LASSO) Approach. The study focuses on key descriptors such as delivery route, dosage form, dose, BCS classification, solid-state and physicochemical properties, release type, half-life, and manufacturing complexity. Through statistical analysis, a data simplification process identifies critical descriptors, assigning risk numbers and computing a cumulative risk number to assess product complexity and recall likelihood. Partial Least Square Regression and the LASSO approach established quantitative relationships between key descriptors and cumulative risk numbers. Results have identified key descriptors; BCS Class I, dose number, release profile, and drug half-life influencing product recall risk. The LASSO model further confirms these identified descriptors with 71% accuracy. In conclusion, the study presents a holistic AI and machine learning approach for evaluating and forecasting pharmaceutical product recalls, underscoring the importance of descriptors, formulation complexity, and manufacturing processes in mitigating risks associated with product quality.
Identifiants
pubmed: 39443361
doi: 10.1208/s12249-024-02970-z
pii: 10.1208/s12249-024-02970-z
doi:
Substances chimiques
Pharmaceutical Preparations
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
255Informations de copyright
© 2024. The Author(s), under exclusive licence to American Association of Pharmaceutical Scientists.
Références
Huggins CJPT. Drug recalls are more widespread than previously thought. Pharm Today. 2019;25(3):4.
doi: 10.1016/j.ptdy.2019.02.030
Wang B, Gagne JJ, Choudhry NK. The epidemiology of drug recalls in the United States. Arch Intern Med. 2012;172(14):1110–1.
doi: 10.1001/archinternmed.2012.2013
Sultan T, Rozin EH, Dave VS, Cetinkaya C. Non-destructive detection of disintegrant levels in compressed oral solid dosage forms. Int J Pharma. 2023;642:123171.
doi: 10.1016/j.ijpharm.2023.123171
Shah R, Ball GP, Netessine S. Plant operations and product recalls in the automotive industry: an empirical investigation. Manag Sci. 2017;63(8):2439–59.
doi: 10.1287/mnsc.2016.2456
Hall K, Stewart T, Chang J, Freeman MK. Characteristics of FDA drug recalls: a 30-month analysis. Am J Health Syst Pharm. 2016;73(4):235–40.
pubmed: 26843501
doi: 10.2146/ajhp150277
McMahon AW, Pratt RG, Hammad TA, Kozlowski S, Zhou E, Lu S, Kulick CG, Mallick T, Dal Pan G. Description of hypersensitivity adverse events following administration of heparin that was potentially contaminated with oversulfated chondroitin sulfate in early 2008. Pharmacoepidemiol Drug Saf. 2010;19(9):921–33.
pubmed: 20661880
doi: 10.1002/pds.1991
Lawrence XY, Woodcock J. FDA pharmaceutical quality oversight. Int J Pharm. 2015;491(1–2):2–7.
Anand G, Gray J, Siemsen E. Decay, shock, and renewal: operational routines and process entropy in the pharmaceutical industry. Organ Sci. 2012;23(6):1700–16.
doi: 10.1287/orsc.1110.0709
Ball G, Siemsen E, Shah R. Do plant inspections predict future quality? The role of investigator experience. Manage SO. 2017;19(4):534–50.
Brown AL, Camerer CF, Lovallo D. Estimating structural models of equilibrium and cognitive hierarchy thinking in the field: the case of withheld movie critic reviews. Manag Sci. 2013;59(3):733–47.
doi: 10.1287/mnsc.1120.1563
Feinstein J. The safety regulation of US nuclear power plants: violations, inspections, and abnormal occurrences. J Polit Econ. 1989;97(1):115–54.
doi: 10.1086/261595
Zimmerman MB. Learning effects and the commercialization of new energy technologies: the case of nuclear power. Bell J Econ. 1982;13(2):297–310.
doi: 10.2307/3003455
Gray JV, Anand G, Roth AV. The influence of ISO 9000 certification on process compliance. Prod Oper Manag. 2015;24(3):369–82.
doi: 10.1111/poms.12252
Steven AB, Dong Y, Corsi T. Global sourcing and quality recalls: an empirical study of outsourcing-supplier concentration-product recalls linkages. J Oper Manag. 2014;32(5):241–53.
doi: 10.1016/j.jom.2014.04.003
Ball GP, Shah R, Wowak KD. Product competition, managerial discretion, and manufacturing recalls in the US pharmaceutical industry. J Oper Manag. 2018;58:59–72.
doi: 10.1016/j.jom.2018.04.003
Gray JV, Leiblein MJ, Roth AV. Quality risk in offshore manufacturing: evidence from pharmaceutical industry. Qual Control Appl Stat. 2013;58(1):73–4.
Macher JT, Mayo JW, Nickerson JA. Regulator heterogeneity and endogenous efforts to close the information asymmetry gap. J Law Econ. 2011;54(1):25–54.
doi: 10.1086/658484
Friedli T, Koehler S, Buess P, Basu P, Calnan N. J. F. r. S. G. U. o. S. G., FDA quality metrics research. 2017.
Sousa R, Voss CA. Quality management re-visited: a reflective review and agenda for future research. J Oper Manag. 2002;20(1):91–109.
doi: 10.1016/S0272-6963(01)00088-2
Federico P, Heimerl F, Koch S, Miksch SJ. A survey on visual approaches for analyzing scientific literature and patents. IEEE Trans Vis Comput Graph. 2016;23(9):2179–98.
pubmed: 27654646
doi: 10.1109/TVCG.2016.2610422
Gayvert KM, Madhukar NS, Elemento O. A data-driven approach to predicting successes and failures of clinical trials. Cell Chem Biol. 2016;23(10):1294–301.
pubmed: 27642066
pmcid: 5074862
doi: 10.1016/j.chembiol.2016.07.023
Kumar V, Faheem M, Lee KW. A decade of machine learning-based predictive models for human pharmacokinetics: advances and challenges. Drug Discov Today. 2022;27(2):529–37.
pubmed: 34592448
doi: 10.1016/j.drudis.2021.09.013
Palmer DS, O’Boyle NM, Glen RC, Mitchell JB. Random forest models to predict aqueous solubility. J Chem Inf Model. 2007;47(1):150–8.
pubmed: 17238260
doi: 10.1021/ci060164k
Yamashita F, Fujita A, Sasa Y, Higuchi Y, Tsuda M, Hashida M. An evolutionary search algorithm for covariate models in population pharmacokinetic analysis. J Pharm Sci. 2017;106(9):2407–11.
pubmed: 28450239
doi: 10.1016/j.xphs.2017.04.029
Korolev D, Balakin KV, Nikolsky Y, Kirillov E, Ivanenkov YA, Savchuk NP, Ivashchenko AA, Nikolskaya T. Modeling of human cytochrome P450-mediated drug metabolism using unsupervised machine learning approach. J Med Chem. 2003;46(17):3631–43.
pubmed: 12904067
doi: 10.1021/jm030102a
Bies RR, Muldoon MF, Pollock BG, Manuck S, Smith G, Sale ME. A genetic algorithm-based, hybrid machine learning approach to model selection. J Pharmacokinet Pharmacodyn. 2006;33(2):195.
pubmed: 16565924
doi: 10.1007/s10928-006-9004-6
Parvatikar PP, Patil S, Khaparkhuntikar K, Patil S, Singh PK, Sahana R, Kulkarni RV, Raghu AV. Artificial intelligence: machine learning approach for screening large database and drug discovery. Antivir Res. 2023;220:105740.
pubmed: 37935248
doi: 10.1016/j.antiviral.2023.105740
US Food and Drug Administration. Artificial intelligence and machine learning in software as a medical device. Silver Spring, MD, USA: US Food & Drug Administration; 2021.
Vatansever S, Schlessinger A, Wacker D, Kaniskan HÜ, Jin J, Zhou MM, Zhang B. Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: state-of-the-arts and future directions. Med Res Rev. 2021;41(3):1427–73.
pubmed: 33295676
doi: 10.1002/med.21764
Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G, Li B, Madabhushi A, Shah P, Spitzer M, Zhao S. Applications of machine learning in drug discovery and development. Nat Rev Drug Discov. 2019;18(6):463–77.
pubmed: 30976107
pmcid: 6552674
doi: 10.1038/s41573-019-0024-5
Tibshirani R. Regression shrinkage and selection via the lasso. J Royal Stat Soc Series B: Stat Methodol. 1996;58(1):267–88.
doi: 10.1111/j.2517-6161.1996.tb02080.x
Kosugi A, Leong KH, Tsuji H, Hayashi Y, Kumada S, Okada K, Onuki Y. Characterization of powder-and tablet properties of different direct compaction grades of mannitol using a Kohonen self-organizing map and a lasso regression model. J Pharm Sci. 2020;109(8):2585–93.
pubmed: 32473211
doi: 10.1016/j.xphs.2020.05.010
Haware RV, Tho I, Bauer-Brandl A. Multivariate analysis of relationships between material properties, process parameters and tablet tensile strength for α-lactose monohydrates. Eur J Pharm Biopharm. 2009;73(3):424–31.
pubmed: 19698784
doi: 10.1016/j.ejpb.2009.08.005
Kerstiens EA, Byrn SR, Clase KL. The identification of quality risk factors for non-biological complex drugs and epilepsy drugs using statistical analysis of formulation-based recalls in the USA. AAPS PharmSciTech. 2022;23:1–9.
doi: 10.1208/s12249-021-02165-w
Buschmann H, Handler N, Holzgrabe U. The quality of drugs and drug products–always guaranteed? J Pharm Biomed Anal. 2023;239:115880.
pubmed: 38103416
doi: 10.1016/j.jpba.2023.115880
Kaur N, Suryanarayanan R. Levothyroxine sodium pentahydrate tablets–formulation considerations. J Pharm Sci. 2021;110(12):3743–56.
pubmed: 34384799
doi: 10.1016/j.xphs.2021.08.006
Prioritizing CG. Risk-based method for prioritizing CGMP inspections of pharmaceutical manufacturing sites—A pilot risk ranking model. 2004.
Wechsler J. FDA seeks risk-based inspection programme: the US Food and Drug Administration's new policies aim to make GMP inspections more efficient, and targeted at more risky products and situations. Pharm Technol Eur. 2003;15(11):18+.
Sousa A, Serra J, Estevens C, Costa R, Ribeiro AJ. A quality by design approach in oral extended release drug delivery systems: where we are and where we are going? J Pharm Investig. 2023;53(2):269–306.
Jovanovska VP. Development and formulation optimisation of modified release dosage form using quality by design–QbD aproach. 2018.
Din FV, Valanciute A, Houde VP, Zibrova D, Green KA, Sakamoto K, Alessi DR, Dunlop MG. Aspirin inhibits mTOR signaling, activates AMP-activated protein kinase, and induces autophagy in colorectal cancer cells. Gastroenterol. 2012;142(7):1504–15.
doi: 10.1053/j.gastro.2012.02.050
Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33(1):1.
pubmed: 20808728
pmcid: 2929880
doi: 10.18637/jss.v033.i01
Amidon GL, Lennernäs H, Shah VP, Crison JR. A theoretical basis for a biopharmaceutic drug classification: the correlation of in vitro drug product dissolution and in vivo bioavailability. Pharm Res. 1995;12:413–20.
pubmed: 7617530
doi: 10.1023/A:1016212804288
Martens H, Martens M. Modified Jack-knife estimation of parameter uncertainty in bilinear modelling by partial least squares regression (PLSR). Food Qual Prefer. 2000;11(1–2):5–16.
doi: 10.1016/S0950-3293(99)00039-7
Feufel MA, Rauwolf G, Meier FC, Karapinar-Çarkit F, Heibges M. Heuristics for designing user‐centric drug products: lessons learned from human factors and Ergonomics. Br J Clin Pharmacol. 2020;86(10):1989–99.
pubmed: 31663157
pmcid: 7495287
doi: 10.1111/bcp.14134
Engudomnukul S, Prombanpong S, Somboonwiwat T. A heuristic approach to capacity assignment in pharmaceutical manufacturing production line. Appl Mech Mater. 2014;548:1928–33.
doi: 10.4028/www.scientific.net/AMM.548-549.1928
Lindenberg M, Kopp S, Dressman JB. Classification of orally administered drugs on the World Health Organization Model list of Essential Medicines according to the biopharmaceutics classification system. Eur J Pharm Biopharm. 2004;58(2):265–78.
pubmed: 15296954
doi: 10.1016/j.ejpb.2004.03.001
Rönkkö M, McIntosh CN, Antonakis J, Edwards JR. Partial least squares path modeling: time for some serious second thoughts. J Oper Manag. 2016;1(47):9–27.
doi: 10.1016/j.jom.2016.05.002
Ferreira AP, Tobyn M. Multivariate analysis in the pharmaceutical industry: enabling process understanding and improvement in the PAT and QbD era. Pharm Dev Technol. 2015;20(5):513–27.
pubmed: 24641280
doi: 10.3109/10837450.2014.898656
Haware RV, Kancharla JP, Udupa AK, Staton S, Gupta MR, Al-Achi A, Stagner WC. Physico-mechanical properties of coprocessed excipient MicroceLac® 100 by DM 3 approach. Pharm Res. 2015;32:3618–35.
pubmed: 26055403
doi: 10.1007/s11095-015-1721-3
Dave VS, Popielarczyk M, Boyce H, Al-Achi A, Ike-Amaechi E, Hoag SW, Haware RV. Lubricant-sensitivity assessment of SPRESS® B820 by near-infrared spectroscopy: a comparison of multivariate methods. J Pharm Sci. 2017;106(2):537–45.
pubmed: 27832838
doi: 10.1016/j.xphs.2016.09.018
Zhao P, Yu B. On model selection consistency of Lasso. J Mach Learn Res. 2006;1(7):2541–63.
Haware RV, Dave VS, Kakarala B, Delaney S, Staton S, Munson E, Gupta MR, Stagner WC. Vegetable-derived magnesium stearate functionality evaluation by DM3 approach. Eur J Pharm Sci. 2016;30(89):115–24.
doi: 10.1016/j.ejps.2016.04.019