Leave a message

Artificial intelligence (AI)/ML in Packaging innovations for Drug Discovery

Review Article | DOI: https://doi.org/10.31579/2690-8808/232

Artificial intelligence (AI)/ML in Packaging innovations for Drug Discovery

  • Anupam Chanda

B. Sc (Math), MS in Packaging and Polymer Science Technologist, Bioxytran Inc, MA, Boston, USA.

*Corresponding Author: Anupam Chanda, B. Sc (Math), MS in Packaging and Polymer Science Technologist, Bioxytran Inc, MA, Boston, USA.

Citation: Anupam Chanda, (2024), Artificial intelligence (AI)/ML in Packaging innovations for Drug Discovery, J, Clinical Case Reports and Studies, 5(10); DOI:10.31579/2690-8808/232

Copyright: ©, 2024, Anupam Chanda. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Received: 16 November 2024 | Accepted: 22 November 2024 | Published: 29 November 2024

Keywords: oral; injectables; solids; semi-solid doses form products

Abstract

Artificial intelligence (AI) is a technology that enables computers and machines to simulate human learning, comprehension, problem solving, decision making, creativity and autonomy. AI software can perform a variety of tasks, including:Content generation, Data analysis, Prediction, Process automation, Decision-making, Learning, and Problem-solving. ML/AI can help vision system experts to identify and sort false ejects from large image data sets for oral, Injectables, solids, semi-solid Doses form products “ONLINE INSPECTION”.

Introduction

Following software are mostly using in AI&ML:

  1. Python- Softwareintegration with AI/ML:
    • Python is widely used in AI due to its simplicity, versatility.
    • Rich selection of libraries for machine learningand data analysis.
    • It allowsdevelopers to createintelligent systems that can learn from data, recognize patterns, and makedecisions.
  2. OpenCV- Softwareintegration with AI/ML
    • Possibilities in computer vision applications.
    • Enhanced object detection to sophisticated image recognition.
  3. Keras -software Applications in AI/ML
    • Facilitates tasks like image classification, object detection, and video analysis througheasy-to-implement convolutional neural networks (CNNs).
    • Ideal for applications from medical imagingdiagnostics to automated manufacturing quality control.
  4. TensorFlow -Softwareintegration in AI/ML
  • Natural languageprocessing
  • Computer vision
  • Object detection
  • Exact recognition

Steps to follow:

  • Data collection from Existing Visioninspection machine
  • ML/AI can help visionsystem experts to identify and sort false ejects from
  • large image data sets.
  • ML/AI can facilitate a streaming analytics platformfor the automated
  • vision inspection process. This streaming analytics platform will support
  • the visionsystem experts with rapid identification and remediation of both
  • true and false ejectsfrom the upstream drug product unit operations.
  • Vision inspection team collaborate with the data scienceteam to developa
  • prototype convolutional neural network (CNN)to test the ability of AI/ML models to identify true versus false ejects.
  • After the eject- and acceptable-image sets had been assembled, the team collaborate with data scienceteam to developa deep learning model that could classify the images using Python, OpenCV, Keras, and TensorFlow.

AI ensuresPrecision in Vial & PFS Inspection

  • Maintaining rigorousquality control standardswhen mass-producing vials of liquid medicine can be challenging.
  • Vials can be subjectto contaminants,or cross-contamination can occur during manufacturing. These “defects” cannot be tolerated.
  • Detecting these issues is nearly impossible for the human eye, especially when vials are produced at a high rate.

Deep Learningand Edge Learningin Pharmaceutical Inspection AI's revolutionary potential lies in deep learningand Edge learning.

Deep learning

  • This technology predict patterns and perform judgment-based applications.
  • Deploys artificial intelligence (AI) algorithms to teach robotsand machines to do what comes naturally to humans: learning by example.
  • Advanced manufacturing practices for qualityinspection and task automation.
  • Deep learning technology transfers the logical burden from an application developer, who develops and scripts a rules-based algorithm, to an engineer training the system. In this way, deep learningmakes machine visioneasier to work with, while expanding the limits of accurate inspection.

Edge learning

  • Deploying AI models directlyon the production line equipment.
  • provides real-time data analysis and decision-making.
  • significantly reducinginspection time.
  • enhancing overallefficiency.

Silicone Oil Induced Effectsin Pharmaceutical GlassVials

Manual Inspection

Visual inspection Display Panel:

Particle inspection in liquid product


 

Advantages to use ai for online inspection for injectables:

  • Most of the casesthis has been observed in manual inspection, it is not possible to find out and eject very small silicon oil drops and silica flex and such kind of products are not ejected from the packing line. AI/ML can solve these problemsonline within fractionof seconds.
  • Very smallback particles, glass particles, rubberstopper loose parts AI can identify and ejected those vials/PFS from packing line.

AI and ML for Solid doses Form

Emptypocket and Black dots in Tablets

Colorshade difference & Broken Tablets

Advantages to use AI for online inspection for solid Doses:

  • In high speed blister packing line, empty pockets, black dots, broken tablets, dented capsules, open caps, out of rangecoloured tablets not possible to identify 100% online. AI/ML can solve such problems and avoid market complaints.

Label and Lot Code Verification with OCR and OCV

Advantages to use AI/ML for Batch coding Inspection

  • Missing of words in text, scratchon text, improperbatch coding, 2D data matrix is not proper, colour share of label and carton are not proper such kind of defective packaging materials are not possible to eject from the packing line. AI/MLcan do this activities perfectly and avoid market complaints.

AI applications in Microgravity Environments in Packaging Design

Singlebubble in the syringe can spoil the Eye

Cardiacproblem on space station

 

High Radiation in Microgravity

Gold Foil Coated Vial & PFS to preventhigh Radiation

BubbleFree Injection Syringein Space a Big Challenge

References

a