Intellectual Property India Publishes Patent Application for Machine Learning-Based Spectroscopic Analytical System For Authentication, Composition Analysis And Degradation Assessment Of Pharmaceutical Products

MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641113911 A) filed by Dr. Duggirala Mahendra; Dr. Kolli Dhanujaya Rao; P Lakshmi Sri Sai Krishna; M Divya Sri Akshaya; Chirumamilla Tabitha; Dasari Vamsi Krishna; Mangam Vijaya Vardhan; Veerla Venkata Sai; Kollimarla Venkateswarlu; and Baki Mahesh Reddy on September 23, 2026, for Machine Learning-Based Spectroscopic Analytical System For Authentication, Composition Analysis And Degradation Assessment Of Pharmaceutical Products.

Inventors include Dr. Duggirala Mahendra; Dr. Kolli Dhanujaya Rao; P Lakshmi Sri Sai Krishna; M Divya Sri Akshaya; Chirumamilla Tabitha; Dasari Vamsi Krishna; Mangam Vijaya Vardhan; Veerla Venkata Sai; Kollimarla Venkateswarlu; and Baki Mahesh Reddy.

The application for the patent was published on September 25, 2026, under issue no. 39/2026.

Abstract: ABSTRACT MACHINE LEARNING-BASED SPECTROSCOPIC ANALYTICAL SYSTEM FOR AUTHENTICATION, COMPOSITION ANALYSIS AND DEGRADATION ASSESSMENT OF PHARMACEUTICAL PRODUCTS The present invention provides a machine learning-based spectroscopic analytical system (100) for analysis of pharmaceutical products. The system comprises a spectroscopic acquisition unit (106) configured to obtain spectral information from a pharmaceutical sample (102), a spectral data acquisition module (112), a spectral preprocessing module (116), a spectral fingerprint generation module (120), a spectral fingerprint database (124) storing reference spectral profiles (126), and a machine-learning analytical engine (130). Acquired spectral information is automatically preprocessed to generate a processed spectral dataset from which a sample spectral fingerprint (122) is derived. The machine-learning analytical engine analyzes the processed spectral information and/or sample spectral fingerprint relative to reference spectral information to generate one or more analytical outputs. The outputs may comprise pharmaceutical authentication, composition analysis, detection of unexpected components or adulterants, estimation of active pharmaceutical ingredient concentration and degradation assessment. The system thereby integrates physical spectroscopic measurement, spectral preprocessing, reference-profile analysis and machine-learning-assisted pharmaceutical characterization within a unified analytical architecture.

Disclaimer: Curated by HT Syndication.