Holistic Approach for Artificial Intelligence Implementation in Pharmaceutical Products Lifecycle: A Meta-Analysis
Source abstract
Abstract
Recent developments in Digital Medicine approaches concern pharmaceutical product optimization. Artificial Intelligence (AI) has multiple applications for pharmaceutical products’ lifecycle, increasing development speed, quality of the products, and efficiency of the therapy. Here, we systematically review the overall approach for AI implementation in pharmaceutical products’ lifecycle. The published studies in PubMed and IEEE Xplore were searched from inception to March 2022. The papers were screened for relevant outcomes, publication types, and data sufficiency, and a total of 73 (1.2%) out of 6131 studies were retrieved after the selection. We extracted the data according to the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement. All Artificial Intelligence systems could be divided into multiple overlapping categories by implementation. For the 177 projects found, the most popular areas of AI implementation are clinical trials and pre-clinical tests (34%). In second place are novel small molecule design systems, with 33% of the total. The third most popular scope for AI implementation is target identification for novel medicines. More than 25% of the systems provide this functionality. It is interesting that most of the systems specialize in only one area (102 systems—57%). None of the systems provide functionality for full coverage of the lifecycle and function in all categories of the tasks. This meta-analysis demonstrated that Artificial Intelligence solutions in pharmaceutical products’ lifecycle could find numerous implementations, and none of the available market solutions covers them all.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Computational Drug Discovery Methods · Innovative Microfluidic and Catalytic Techniques Innovation · Biosimilars and Bioanalytical Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Digital Health Institute, I.M. Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University), 119991 Moscow, Russia
Agrarian and Technological Institute, Peoples’ Friendship University of Russia, 117198 Moscow, Russia
Funding
RUDN University Scientific Projects Grant System
References (88)
Show source-provided references
1. Estimation of clinical trial success rates and related parameters10.1093/biostatistics/kxx069 ↗
2. The role of product life cycle in medical technology innovation
3. Machine learning applications in drug development
4. Advancing Drug Discovery via Artificial Intelligence10.1016/j.tips.2019.06.004 ↗
5. Artificial intelligence and big data facilitated targeted drug discovery10.1136/svn-2019-000290 ↗
6. Bohr, H. (2020). Drug discovery and molecular modeling using artificial intelligence. Artif. Intell. Healthc., 61–83.10.1016/B978-0-12-818438-7.00003-4 ↗
7. Artificial intelligence (AI) in healthcare and biomedical research: Why a strong computational/AI bioethics framework is required?10.4103/ijo.IJO_1292_18 ↗
8. Image-based Classification of Tumor Type and Growth Rate using Machine Learning: A preclinical study10.1038/s41598-019-48738-5 ↗
9. Real-World Evidence—What Is It and What Can It Tell Us?10.1056/NEJMsb1609216 ↗
10. Artificial Intelligence for Clinical Trial Design10.1016/j.tips.2019.05.005 ↗
11. Applications of artificial intelligence in drug development using real-world data10.1016/j.drudis.2020.12.013 ↗
12. Real-World Evidence, Causal Inference, and Machine Learning10.1016/j.jval.2019.03.001 ↗
13. Medicines Agency (2022, August 01). HMA-EMA Joint Big Data Taskforce Phase II Report: “Evolving Data-Driven Regulation” 1, Available online: https://www.ema.europa.eu/en/documents/other/hma-ema-joint-big-data-taskforce-phase-ii-report-evolving-data-driven-regulation_en.pdf.
14. Guidelines for clinical trial protocols for interventions involving artificial intelligence: The SPIRIT-AI extension10.1038/s41591-020-1037-7 ↗
15. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: The CONSORT-AI extension10.1038/s41591-020-1034-x ↗
16. Artificial neural networks applied to quality-by-design: From formulation development to clinical outcome10.1016/j.ejpb.2020.05.012 ↗
17. Integrating Artificial and Human Intelligence into Tablet Production Process10.1208/s12249-014-0174-z ↗
18. The First Approved Gene Therapy Product for Cancer Ad-p53(Gendicine): 12 Years in the Clinic10.1089/hum.2017.218 ↗
19. Predicting the Future—Big Data, Machine Learning, and Clinical Medicine10.1056/NEJMp1606181 ↗
20. Arsalan, T., Koshechkin, K., and Lebedev, G. (2020). Scientific Approaches to the Digitalization of Drugs Assortment Monitoring Using Artificial Neural Networks. Smart Innov. Syst. Technol., 391–401.10.1007/978-981-15-5925-9_33 ↗
21. (2022, August 01). Report|Drug Shortages: Root Causes and Potential Solutions|FDA [Electronic Resource], Available online: https://www.fda.gov/drugs/drug-shortages/report-drug-shortages-root-causes-and-potential-solutions.
22. Artificial Intelligence and Personalized Medicine10.1007/978-3-030-16391-4_11 ↗
23. Technology of Supporting Medical Decision-Making Using Evidence-Based Medicine and Artificial Intelligence10.1016/j.procs.2020.09.195 ↗
24. Ferrari, D., Milic, J., Tonelli, R., Ghinelli, F., Meschiari, M., Volpi, S., Matteo, F., Giacomo, F., Vittorio, I., and Dina, Y. (2020). Machine learning in predicting respiratory failure in patients with COVID-19 pneumonia—Challenges, strengths, and opportunities in a global health emergency. PLoS ONE, 15.10.1371/journal.pone.0239172 ↗
25. An Easy-to-Use Machine Learning Model to Predict the Prognosis of Patients with COVID-19: Retrospective Cohort Study10.2196/24225 ↗
26. Artificial Intelligence for Drug Toxicity and Safety10.1016/j.tips.2019.07.005 ↗
27. Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing10.1002/cpt.1255 ↗
28. Artificial Intelligence within Pharmacovigilance: A Means to Identify Cognitive Services and the Framework for Their Validation10.1007/s40290-019-00269-0 ↗
29. Preferred reporting items for systematic review and meta-analysis protocols (PRISMA-P) 2015: Elaboration and explanation10.1136/bmj.g7647 ↗
30. Sievert, C., and Shirley, K. (2014). LDAvis: A Method for Visualizing and Interpreting Topics, Association for Computational Linguistics.10.3115/v1/W14-3110 ↗
31. Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data10.1021/acs.molpharmaceut.6b00248 ↗
32. (2022, August 01). Vyasa Analytics Introduces Synapse, A Novel “Smart Table” Software Application Powered by Deep Learning AI Technologies. Available online: https://www.prweb.com/releases/vyasa_analytics_introduces_synapse_a_novel_smart_table_software_application_powered_by_deep_learning_ai_technologies/prweb16677978.htm.
33. (2022, August 01). AI-Powered Healthcare. Available online: https://xbird.io/.
34. (2022, August 01). Xconomy: Gene Network Sciences Using Supercomputing to Match Patients with a Drug That Works—Page 2 of 2. Available online: https://xconomy.com/boston/2010/04/27/gene-network-sciences-using-supercomputing-to-match-patients-with-a-drug-that-works/2/.
35. (2022, August 01). Using AI to Accelerate Drug Discovery. Available online: https://www.nature.com/articles/d42473-020-00354-y.
36. (2022, August 01). Standigm and SK Chemicals Repurpose FDA-approved Drug into Rheumatoid Arthritis Candidate and Apply for Patent through Their Open Innovation Partnership, Business Wire. Available online: https://www.businesswire.com/news/home/20210107005121/en/Standigm-and-SK-Chemicals-Repurpose-FDA-approved-Drug-into-Rheumatoid-Arthritis-Candidate-and-Apply-for-Patent-through-their-Open-Innovation-Partnership.
37. (2022, August 01). Unlearn—Home. Available online: https://www.unlearn.ai.
38. (2022, August 01). Deep Lens BioPharma and CROs. Available online: https://www.deeplens.ai/deep-lens-healthcare-biopharma-cro.
39. PotentialNet for molecular property prediction10.1021/acscentsci.8b00507 ↗
40. (2022, August 01). Product Pipeline: BioXcel Therapeutics, Inc. (BTAI). Available online: https://www.bioxceltherapeutics.com/our-pipeline/.
41. (2022, August 01). InterVenn Biosciences|Clinical Glycoproteomics + Artificial Intelligence. Available online: https://intervenn.com.
42. (2022, August 01). Transforming Patient Safety—Medaware. Available online: https://www.medaware.com.
43. Data Management in a Regulatory Context10.3389/fmed.2017.00114 ↗
44. (2022, August 01). Turn Patient Insights into Actionirody. Available online: https://irody.com.
45. (2022, August 01). Savana—Transform the Free Text of Your Clinical Records into Big Data. Available online: https://www.savanamed.com.
46. (2022, August 01). LabGenius. Available online: https://labgeni.us.
47. (2022, August 01). InsightRX—Precision Dosing Done Right. Available online: https://www.insight-rx.com.
48. (2022, August 01). Novartis CEO Who Wanted to Bring Tech into Pharma Now Explains Why It’s So Hard. Available online: https://www.forbes.com/sites/davidshaywitz/2019/01/16/novartis-ceo-who-wanted-to-bring-tech-into-pharma-now-explains-why-its-so-hard/.
49. (2022, August 01). Drug Discovery with an AI-Augmented Platform—Cyclica. Available online: https://www.cyclicarx.com.
50. (2022, August 01). Artificial Intelligence Startup Healx Gets $10 Million to Find Cures for Rare Diseases—Healthcare Weekly. Available online: https://healthcareweekly.com/healx-artificial-intelligence-pharma.
51. (2022, August 01). IBM Watson Health|AI Healthcare Solutions|IBM. Available online: https://www.ibm.com/watson-health.
52. Carvalho, J.P., and Curto, S. (2022, August 01). Fuzzy Preprocessing of Medical Text Annotations of Intensive Care Units Patients. Available online: https://www.inesc-id.pt/publications/10251/pdf.
53. (2022, August 01). LingPipe Home. Available online: http://www.alias-i.com/lingpipe/.
54. (2022, August 01). The Stanford Natural Language Processing Group. Available online: https://nlp.stanford.edu/software/lex-parser.shtml.
55. GLR parsing with multiple grammars for natural language queries10.1145/568954.568956 ↗
56. De Marneffe, M.-C., Maccartney, B., and Manning, C.D. (2022, August 01). Generating Typed Dependency Parses from Phrase Structure Parses. Available online: https://www.researchgate.net/publication/200044364_Generating_Typed_Dependency_Parses_from_Phrase_Structure_Parses.
57. Zhang, X., and Lecun, Y. (2022, August 01). Text Understanding from Scratch. Available online: https://arxiv.org/abs/1502.01710.
58. Wang, P., Qian, Y., Soong, F.K., He, L., and Zhao, H. (2022, August 01). Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network. Available online: https://arxiv.org/abs/1510.06168.
59. ChEMU 2020: Natural Language Processing Methods Are Effective for Information Extraction from Chemical Patents10.3389/frma.2021.654438 ↗
60. A natural language processing approach based on embedding deep learning from heterogeneous compounds for quantitative structure–activity relationship modeling10.1111/cbdd.13742 ↗
61. Tarasov, S.D. (2022, August 01). Natural Language Generation, Paraphrasing and Summarization of User Reviews with Recurrent Neural Networks. Available online: http://www.dialog-21.ru/digests/dialog2015/materials/pdf/TarasovDS2.pdf.
62. (2022, August 01). Google AI Blog: Open Sourcing BERT: State-of-the-Art Pre-training for Natural Language Processing. Available online: https://ai.googleblog.com/2018/11/open-sourcing-bert-state-of-art-pre.html.
63. (2022, August 01). Better Language Models and Their Implications. Available online: https://openai.com/blog/better-language-models/.
64. Nambiar, A., Heflin, M., Liu, S., Maslov, S., Hopkins, M., and Ritz, A. (2020, January 21–24). Transforming the Language of Life: Transformer Neural Networks for Protein Prediction Tasks. Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020, New York, NY, USA.10.1145/3388440.3412467 ↗
65. (2022, August 01). bioRxiv Preprints Can Now be Submitted Directly to Leading Research Journals. Available online: https://phys.org/news/2016-01-biorxiv-preprints-submitted-journals.html.
66. A comparison of machine learning techniques for detection of drug target articles10.1016/j.jbi.2010.07.010 ↗
67. Bohr, A., and Memarzadeh, K. (2020). The rise of artificial intelligence in healthcare applications. Artificial Intelligence in Healthcare, Academic Press.10.1016/B978-0-12-818438-7.00002-2 ↗
68. Spectrum of deep learning algorithms in drug discovery10.1111/cbdd.13674 ↗
69. BioBERT: A pre-trained biomedical language representation model for biomedical text mining10.1093/bioinformatics/btz682 ↗
70. Artificial intelligence, drug repurposing and peer review10.1038/s41587-020-0686-x ↗
71. Artificial intelligence in COVID-19 drug repurposing10.1016/S2589-7500(20)30192-8 ↗
72. (2022, August 01). AI Driven Repositioning and Repurposing Summit 2021. Available online: https://pharmaphorum.com/events/ai-driven-repositioning-and-repurposing-summit-2021/.
73. Application of Artificial Intelligence in COVID-19 drug repurposing10.1016/j.dsx.2020.06.068 ↗
74. (2022, August 01). Deep Learning Takes on synthetic Biology. Available online: https://wyss.harvard.edu/news/deep-learning-takes-on-synthetic-biology/.
75. A machine learning Automated Recommendation Tool for synthetic biology
76. Artificial intelligence and machine learning in clinical development: A translational perspective10.1038/s41746-019-0148-3 ↗
77. (2022, August 01). Overview|The Conference Forum. Available online: https://theconferenceforum.org/conferences/webinar-open-ai-gpt3/overview/.
78. (2022, August 01). State-Of-The-Art Image Classification Algorithm: FixEfficientNet-L2|by Hucker Marius|Towards Data Science. Available online: https://towardsdatascience.com/state-of-the-art-image-classification-algorithm-fixefficientnet-l2-98b93deeb04c.
79. (2022, August 01). Cellular Image Classification for Drug Discovery|by Huseyn Gasimov|Intelec AI|Medium. Available online: https://medium.com/intelec-ai/cellular-image-classification-for-drug-discovery-4ef55741151c.
80. Lebedev, G., Fartushniy, E., Shaderkin, I., Klimenko, H., Kozhin, P., Koshechkin, K., Ryabkov, I., Tarasov, V., Morozov, E., and Fomina, I. (2020). Creation of a Medical Decision Support System Using Evidence-Based Medicine. Int. Conf. Intell. Decis. Technol., 413–427.10.1007/978-981-15-5925-9_35 ↗
81. Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine10.1093/database/baaa010 ↗
82. (2022, August 01). Artificial Intelligence to Eradicate Prescription Errors. Available online: https://www.whatnextglobal.com/post/artificial-intelligence-to-eradicate-prescription-errors.
83. Harika Anupama, A.G., Srilekha, G., and Uma Priya, G. (2022, August 01). Review on Artificial Intelligence (AI) in Drug Dispensing and Drug Ac-countability. Available online: https://globalresearchonline.net/journalcontents/v61-2/07.pdf.
84. (2022, August 01). Real-World Applications of Artificial Intelligence to Improve Medication Management Across the Care Continuum—Electronic Health Reporter. Available online: https://electronichealthreporter.com/real-world-applications-of-artificial-intelligence-to-improve-medication-management-across-the-care-continuum/.
85. (2022, August 01). Artificial Intelligence and the Opioid Epidemic—Applications for Relapse Treatment, Abuse Prevention, and More|Emerj. Available online: https://emerj.com/ai-sector-overviews/artificial-intelligence-opioid-epidemic/.
86. (2022, August 01). Malaria Outbreak Prediction Model Using Machine Learning. Available online: https://pdf4pro.com/amp/view/malaria-outbreak-prediction-model-using-machine-learning-474cb5.html.
87. Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 1—Overview of Knowledge Discovery Techniques in Artificial Intelligence10.3389/fphar.2020.01028 ↗
88. A renaissance of neural networks in drug discovery10.1080/17460441.2016.1201262 ↗