ABSTRACT
This article reviews literature on the use of artificial intelligence (AI) for screening, diagnosis, monitoring and treatment of glaucoma. The first part of the review provides information how AI methods improve the effectiveness of glaucoma screening, presents the technologies using deep learning, including neural networks, for the analysis of big data obtained by methods of ocular imaging (fundus imaging, optical coherence tomography of the anterior and posterior eye segments, digital gonioscopy, ultrasound biomicroscopy, etc.), including a multimodal approach. The results found in the reviewed literature are contradictory, indicating that improvement of the AI models requires further research and a standardized approach. The use of neural networks for timely detection of glaucoma based on multimodal imaging will reduce the risk of blindness associated with glaucoma.
Subject(s)
Artificial Intelligence , Deep Learning , Glaucoma , Neural Networks, Computer , Humans , Glaucoma/diagnosis , Tomography, Optical Coherence/methods , Mass Screening/methods , Diagnostic Techniques, OphthalmologicalABSTRACT
This study presents the analysis of the natural long-term aging of both the intact tablets and the active pharmaceutical ingredient. No forced aging conditions were applied to the samples. It is shown that the near infrared spectroscopy of the intact tablets packed in plastic blisters, supported by chemometrics, is a reliable method for detection of even slight deviations of the medicine from its regular state. Independent components analysis helps to extract source signals from spectra of the composite object "a coated tablet sealed in polyvinylchloride blister". Further analysis of the near infrared and attenuated total reflectance infrared spectra of the pure substance confirmed that the aging process detected by the analysis of the intact tablets is directly related to the degradation of the active pharmaceutical ingredient.
Subject(s)
Data Analysis , Diclofenac , Chemometrics , Spectroscopy, Near-Infrared/methods , Tablets/chemistryABSTRACT
The aim of this study is to investigate the influence of hard capsule shells on the possibility of non-invasive monitoring and authentication of medicines presented in capsules dosage form. It is shown that the NIR measurements followed by the chemometric analysis, reflects all macro-components of the analyzed samples, which are the PVC blister, the capsule shell, and the capsule contents. The special variable selection procedure, based on the pure spectra of all components, makes it possible to develop a model that is insensitive to small variations of the capsule shell. The shrinkage of spectral region can greatly affect the results of the classification. Consequently, in case we are interested in the whole remedy, capsules with deviations in shell properties should be rejected as the substandard ones. If we are only interested in the quality of capsules' content, the developed model is effective and applicable in the routine testing. The final model helps to understand and demonstrate the reason for the rejection of substandard samples authentication. It also gives a practical signal to the manufacturer to pay attention to the quality of the capsule shells.
Subject(s)
Oxazolidinones , Capsules , IsoxazolesABSTRACT
The chemometric issues related to the application of non-targeted analysis for the detection of food frauds were analyzed employing discriminant analysis and a one-class classifier. The similarities and differences between the two methods were investigated. The results of classification are characterized by a set of indices called figures of merit. They comprehensively characterized the quality and reliability of classification. The principle is illustrated using an actual example of Oregano herbs adulteration. The informative region 9000-4000â¯cm-1 of near-Infrared spectroscopy is used as analytical means. The results of the application of each method for Oregano data collection are presented. It is shown that the discriminant method is only partially appropriate for solving the authentication problem. One class classifier is a powerful and devoted for non-targeted analysis. The step by step analysis introduced in the paper can also be successfully utilized in apply for revealing of forgeries of various food products.
Subject(s)
Food Analysis/methods , Food Contamination/analysis , Fraud , Origanum/chemistry , Discriminant Analysis , Food Analysis/statistics & numerical data , Food Contamination/statistics & numerical data , Least-Squares Analysis , Reproducibility of Results , Sensitivity and Specificity , Spectroscopy, Near-Infrared/methodsABSTRACT
A detailed step-by-step procedure for revealing counterfeit and substandard tablets is presented. Non-invasive NIR measurements are used for data collection. The entire complex multi-layer object as the "packaging -coating-core" system requires special treatment at all stages of model development and validation. The influence of each layer is studied. A procedure that covers data collection, construction of the model, as well as special internal and external validation is advocated here. A special set of objects called 'nearest of kin' (NoK) collection, which consists of generic medications nearest to the target objects, assists in reliable assessment of the model specificity. The whole procedure summarizes the results obtained for over a thousand different dosage forms of tablets. Two real-world examples of genuine and counterfeit medicines are considered. The first example presents uncoated tablets with high concentration of active ingredient and fairly simple set excipients. Its NoK collection consists of six different manufacturers. The second example presents coated tablets with low concentration of active ingredient and rather complex set of excipients. Its NoK collection is presented by seven different manufacturers.
Subject(s)
Cheminformatics , Counterfeit Drugs/analysis , Spectroscopy, Near-Infrared , Bisoprolol/analysis , Furosemide/analysis , Reference Standards , TabletsABSTRACT
The ultimate goal of the study is to present a method of authentication of hard-shell capsules of medicines packed in polyvinylchloride (PVC) blisters without damaging the primary packaging. This is done by collecting NIR spectra in a non-invasive mode and subsequent analysis of measurements by a one-class classification procedure. The first part of the study demonstrates that NIR spectra collected through a PVC blister and capsule shell do carry information about the medication itself. Firstly, this is done by visual inspection of spectra of the sample, its interfering layers and main pharmaceutical ingredients. Secondly, three regression models for quantification of active pharmaceutical ingredient (API) are built. The possibility of calibration and prediction of API through several nuisance layers using NIR spectroscopy is demonstrated. In order to solve the authentication problem the data driven soft Independent modeling of class analogies method is applied to the collected NIR spectra. The constructed model is validated using laboratory prepared mixtures. Afterwards, the model was applied to real counterfeited samples. Capsules of fluconazole are used for demonstration of the proposed approach."
ABSTRACT
The progress in instrumentation technology has led to miniaturization of NIR instruments. Fast systems that contain no moving parts were developed to be used in the field, warehouses, drugstores, etc. At the same time, in general these portable/handheld spectrometers have a lower spectral resolution and a narrower spectral region than stationary ones. Vendors of portable instruments supply their equipment with special software for spectra processing, which aims at simplifying the analyst's work to the highest degree possible. Often such software is not fully capable of solving complex problems. In application to a real-world problem of counterfeit drug detection we demonstrate that even impaired spectral data do carry information sufficient for drug authentication. The chemometrics aided approach helps to extract this information and thus to extend the applicability of miniaturized NIR instruments. MicroPhazir-RX NIR spectrometer is used as an example of a portable instrument. The data driven soft independent modeling of class analogy (DD-SIMCA) method is employed for data processing. A representative set of tablets of a calcium channel blocker from 6 different manufacturers is used to illustrate the proposed approach. It is shown that the DD-SIMCA approach yields a better result than the basic method provided by the instrument vendor.
Subject(s)
Counterfeit Drugs/analysis , Mobile Applications , Pharmaceutical Preparations/analysis , Pharmaceutical Preparations/standards , Spectroscopy, Near-Infrared/methods , Spectroscopy, Near-Infrared/instrumentation , Time FactorsABSTRACT
When combating counterfeits it is equally important to recognize fakes and to avoid misclassification of genuine samples. This study presents a general approach to the problem using a newly-developed method called Data Driven Soft Independent Modeling of Class Analogy. The possibility to collect representative data for both training and validation is of great importance in classification modeling. When fakes are not available, we propose to compose the test set using the legitimate drug's analogs, manufactured by various producers. These analogs should have the identical API and a similar composition of excipients. The approach shows satisfactory results both in revealing counterfeits and in accounting for the future variability of the target class drugs. The presented case studies demonstrate that theoretically predicted misclassification errors can be successfully employed for the science-based risk assessment in drug identification.
Subject(s)
Pharmaceutical Preparations/analysis , Pharmaceutical Preparations/chemistry , Counterfeit Drugs/analysis , Counterfeit Drugs/chemistry , Excipients/chemistry , Risk Assessment , Spectroscopy, Near-Infrared/methodsABSTRACT
The possibility of routine testing of pharmaceutical substances directly in warehouses is of great importance for manufactures, especially taking into account the demands of PAT. The application of NIR instruments with remote fiber optic probe makes these measurements simple and rapid. On the other hand carrying out measurements through closed polyethylene bags is a real challenge. To make the whole procedure reliable we propose the special trichotomy classification procedure. The approach is illustrated by a real-world example.