Generalization of a prototype intelligent hybrid system for hard gelatin capsule formulation development View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2005-09

AUTHORS

Wendy I. Wilson, Yun Peng, Larry L. Augsburger

ABSTRACT

The aim of this project was to expand a previously developed prototype expert network for use in the analysis of multiple biopharmaceutics classification system (BCS) class II drugs. The model drugs used were carbamazepine, chlorpropamide, diazepam, ibuprofen, ketoprofen, naproxen, and piroxicam. Recommended formulations were manufactured and tested for dissolution performance. A comprehensive training data set for the model drugs was developed and used to retrain the artificial neural network. The training and the system were validated based on the comparison of predicted and observed performance of the recommended formulations. The initial test of the system resulted in high error values, indicating poor prediction capabilities for drugs other than piroxicam. A new data set, containing 182 batches, was used for retraining. The percent of the test batches were used for cross-validation, resulting in models with R2≥70%. The comparison of observed performance to the predicted performance found that the system predicted succcessfully. The hybrid network was generally able to predict the amount of drug dissolved within 5% for the model drugs. Through validation, the system was proven to be capable of designing formulations that met specific drug performance criteria. By including parameters to address wettability and the intrinsic dissolution characteristics of the drugs, the hybrid system was shown to be suitable for analysis of multiple BCS class II drugs. More... »

PAGES

e449-e457

Identifiers

URI

http://scigraph.springernature.com/pub.10.1208/pt060356

DOI

http://dx.doi.org/10.1208/pt060356

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1034895274

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/16354004


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/11", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Medical and Health Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1115", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Pharmacology and Pharmaceutical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Artificial Intelligence", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Capsules", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Chemistry, Pharmaceutical", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Gelatin", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Reproducibility of Results", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Technology, Pharmaceutical", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Department of Pharmaceutical Sciences, University of Maryland-Baltimore, 21201, Baltimore, MD", 
          "id": "http://www.grid.ac/institutes/grid.411024.2", 
          "name": [
            "Department of Pharmaceutical Sciences, University of Maryland-Baltimore, 21201, Baltimore, MD"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wilson", 
        "givenName": "Wendy I.", 
        "id": "sg:person.01065516667.62", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01065516667.62"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, 21250, Maltiomre, MD", 
          "id": "http://www.grid.ac/institutes/grid.266673.0", 
          "name": [
            "Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, 21250, Maltiomre, MD"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Peng", 
        "givenName": "Yun", 
        "id": "sg:person.01136741416.72", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01136741416.72"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Pharmaceutical Sciences, University of Maryland-Baltimore, 21201, Baltimore, MD", 
          "id": "http://www.grid.ac/institutes/grid.411024.2", 
          "name": [
            "Department of Pharmaceutical Sciences, University of Maryland-Baltimore, 21201, Baltimore, MD"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Augsburger", 
        "givenName": "Larry L.", 
        "id": "sg:person.01153104621.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01153104621.46"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1023/a:1011986823850", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1007767460", 
          "https://doi.org/10.1023/a:1011986823850"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1016212804288", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037126380", 
          "https://doi.org/10.1023/a:1016212804288"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007578321803", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000308030", 
          "https://doi.org/10.1023/a:1007578321803"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1015843527138", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002628904", 
          "https://doi.org/10.1023/a:1015843527138"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1208/pt040226", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018669844", 
          "https://doi.org/10.1208/pt040226"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2005-09", 
    "datePublishedReg": "2005-09-01", 
    "description": "The aim of this project was to expand a previously developed prototype expert network for use in the analysis of multiple biopharmaceutics classification system (BCS) class II drugs. The model drugs used were carbamazepine, chlorpropamide, diazepam, ibuprofen, ketoprofen, naproxen, and piroxicam. Recommended formulations were manufactured and tested for dissolution performance. A comprehensive training data set for the model drugs was developed and used to retrain the artificial neural network. The training and the system were validated based on the comparison of predicted and observed performance of the recommended formulations. The initial test of the system resulted in high error values, indicating poor prediction capabilities for drugs other than piroxicam. A new data set, containing 182 batches, was used for retraining. The percent of the test batches were used for cross-validation, resulting in models with R2\u226570%. The comparison of observed performance to the predicted performance found that the system predicted succcessfully. The hybrid network was generally able to predict the amount of drug dissolved within 5% for the model drugs. Through validation, the system was proven to be capable of designing formulations that met specific drug performance criteria. By including parameters to address wettability and the intrinsic dissolution characteristics of the drugs, the hybrid system was shown to be suitable for analysis of multiple BCS class II drugs.", 
    "genre": "article", 
    "id": "sg:pub.10.1208/pt060356", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1023420", 
        "issn": [
          "1530-9932"
        ], 
        "name": "AAPS PharmSciTech", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "6"
      }
    ], 
    "keywords": [
      "intelligent hybrid system", 
      "comprehensive training data", 
      "artificial neural network", 
      "poor prediction capability", 
      "training data", 
      "neural network", 
      "expert networks", 
      "hybrid network", 
      "highest error value", 
      "hybrid system", 
      "new data set", 
      "data sets", 
      "network", 
      "prediction capability", 
      "observed performance", 
      "error values", 
      "performance criteria", 
      "performance", 
      "system", 
      "capability", 
      "test batches", 
      "set", 
      "project", 
      "training", 
      "initial test", 
      "validation", 
      "generalization", 
      "model", 
      "data", 
      "batch", 
      "formulation", 
      "use", 
      "comparison", 
      "amount", 
      "analysis", 
      "development", 
      "parameters", 
      "criteria", 
      "characteristics", 
      "values", 
      "aim", 
      "test", 
      "percent", 
      "formulation development", 
      "model drug", 
      "BCS class II drug", 
      "dissolution performance", 
      "class II drug", 
      "dissolution characteristics", 
      "Biopharmaceutics Classification System class II drug", 
      "wettability", 
      "amount of drug", 
      "drugs", 
      "ibuprofen", 
      "ketoprofen", 
      "naproxen", 
      "carbamazepine", 
      "piroxicam", 
      "chlorpropamide", 
      "diazepam"
    ], 
    "name": "Generalization of a prototype intelligent hybrid system for hard gelatin capsule formulation development", 
    "pagination": "e449-e457", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1034895274"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1208/pt060356"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "16354004"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1208/pt060356", 
      "https://app.dimensions.ai/details/publication/pub.1034895274"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-08-04T16:56", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220804/entities/gbq_results/article/article_411.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1208/pt060356"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1208/pt060356'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1208/pt060356'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1208/pt060356'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1208/pt060356'


 

This table displays all metadata directly associated to this object as RDF triples.

181 TRIPLES      21 PREDICATES      97 URIs      84 LITERALS      13 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1208/pt060356 schema:about N115e87497fe249d282c8669a1a694e7e
2 N5236454cc63c41ad9f2d5cea3127f09f
3 N5f346d1208584f5aa1bd28739418e2ac
4 N6302e6c1c18c4b528aa4c6b7d7de5c97
5 Ndce08e0008594f2593c88fbba6dfeaa0
6 Nf41b814697e548118afdf64f69fa839f
7 anzsrc-for:11
8 anzsrc-for:1115
9 schema:author Nd43223b23dbe43db8e97f509ebbf84ec
10 schema:citation sg:pub.10.1023/a:1007578321803
11 sg:pub.10.1023/a:1011986823850
12 sg:pub.10.1023/a:1015843527138
13 sg:pub.10.1023/a:1016212804288
14 sg:pub.10.1208/pt040226
15 schema:datePublished 2005-09
16 schema:datePublishedReg 2005-09-01
17 schema:description The aim of this project was to expand a previously developed prototype expert network for use in the analysis of multiple biopharmaceutics classification system (BCS) class II drugs. The model drugs used were carbamazepine, chlorpropamide, diazepam, ibuprofen, ketoprofen, naproxen, and piroxicam. Recommended formulations were manufactured and tested for dissolution performance. A comprehensive training data set for the model drugs was developed and used to retrain the artificial neural network. The training and the system were validated based on the comparison of predicted and observed performance of the recommended formulations. The initial test of the system resulted in high error values, indicating poor prediction capabilities for drugs other than piroxicam. A new data set, containing 182 batches, was used for retraining. The percent of the test batches were used for cross-validation, resulting in models with R2≥70%. The comparison of observed performance to the predicted performance found that the system predicted succcessfully. The hybrid network was generally able to predict the amount of drug dissolved within 5% for the model drugs. Through validation, the system was proven to be capable of designing formulations that met specific drug performance criteria. By including parameters to address wettability and the intrinsic dissolution characteristics of the drugs, the hybrid system was shown to be suitable for analysis of multiple BCS class II drugs.
18 schema:genre article
19 schema:isAccessibleForFree true
20 schema:isPartOf N07b0914ed41b4b06a3aa1c9f27e54053
21 N6ccd064ec0b44b579670c4c04d7d2b2e
22 sg:journal.1023420
23 schema:keywords BCS class II drug
24 Biopharmaceutics Classification System class II drug
25 aim
26 amount
27 amount of drug
28 analysis
29 artificial neural network
30 batch
31 capability
32 carbamazepine
33 characteristics
34 chlorpropamide
35 class II drug
36 comparison
37 comprehensive training data
38 criteria
39 data
40 data sets
41 development
42 diazepam
43 dissolution characteristics
44 dissolution performance
45 drugs
46 error values
47 expert networks
48 formulation
49 formulation development
50 generalization
51 highest error value
52 hybrid network
53 hybrid system
54 ibuprofen
55 initial test
56 intelligent hybrid system
57 ketoprofen
58 model
59 model drug
60 naproxen
61 network
62 neural network
63 new data set
64 observed performance
65 parameters
66 percent
67 performance
68 performance criteria
69 piroxicam
70 poor prediction capability
71 prediction capability
72 project
73 set
74 system
75 test
76 test batches
77 training
78 training data
79 use
80 validation
81 values
82 wettability
83 schema:name Generalization of a prototype intelligent hybrid system for hard gelatin capsule formulation development
84 schema:pagination e449-e457
85 schema:productId N2ba81d25363b4265949c01f40f38495b
86 N6c826a424ea84fcba1125a433089bc09
87 Nacbcbac91d594240a66cb9691d44fbc7
88 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034895274
89 https://doi.org/10.1208/pt060356
90 schema:sdDatePublished 2022-08-04T16:56
91 schema:sdLicense https://scigraph.springernature.com/explorer/license/
92 schema:sdPublisher N93eca6a2dd7f40d68490af7ea0c0d346
93 schema:url https://doi.org/10.1208/pt060356
94 sgo:license sg:explorer/license/
95 sgo:sdDataset articles
96 rdf:type schema:ScholarlyArticle
97 N07b0914ed41b4b06a3aa1c9f27e54053 schema:volumeNumber 6
98 rdf:type schema:PublicationVolume
99 N115e87497fe249d282c8669a1a694e7e schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
100 schema:name Reproducibility of Results
101 rdf:type schema:DefinedTerm
102 N25fb590a91bc4e9ea1b7e374124f0eb8 rdf:first sg:person.01136741416.72
103 rdf:rest Nc0bb2528d41b46e89b444370d1c9f054
104 N2ba81d25363b4265949c01f40f38495b schema:name dimensions_id
105 schema:value pub.1034895274
106 rdf:type schema:PropertyValue
107 N5236454cc63c41ad9f2d5cea3127f09f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
108 schema:name Technology, Pharmaceutical
109 rdf:type schema:DefinedTerm
110 N5f346d1208584f5aa1bd28739418e2ac schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
111 schema:name Gelatin
112 rdf:type schema:DefinedTerm
113 N6302e6c1c18c4b528aa4c6b7d7de5c97 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
114 schema:name Artificial Intelligence
115 rdf:type schema:DefinedTerm
116 N6c826a424ea84fcba1125a433089bc09 schema:name doi
117 schema:value 10.1208/pt060356
118 rdf:type schema:PropertyValue
119 N6ccd064ec0b44b579670c4c04d7d2b2e schema:issueNumber 3
120 rdf:type schema:PublicationIssue
121 N93eca6a2dd7f40d68490af7ea0c0d346 schema:name Springer Nature - SN SciGraph project
122 rdf:type schema:Organization
123 Nacbcbac91d594240a66cb9691d44fbc7 schema:name pubmed_id
124 schema:value 16354004
125 rdf:type schema:PropertyValue
126 Nc0bb2528d41b46e89b444370d1c9f054 rdf:first sg:person.01153104621.46
127 rdf:rest rdf:nil
128 Nd43223b23dbe43db8e97f509ebbf84ec rdf:first sg:person.01065516667.62
129 rdf:rest N25fb590a91bc4e9ea1b7e374124f0eb8
130 Ndce08e0008594f2593c88fbba6dfeaa0 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
131 schema:name Capsules
132 rdf:type schema:DefinedTerm
133 Nf41b814697e548118afdf64f69fa839f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
134 schema:name Chemistry, Pharmaceutical
135 rdf:type schema:DefinedTerm
136 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
137 schema:name Medical and Health Sciences
138 rdf:type schema:DefinedTerm
139 anzsrc-for:1115 schema:inDefinedTermSet anzsrc-for:
140 schema:name Pharmacology and Pharmaceutical Sciences
141 rdf:type schema:DefinedTerm
142 sg:journal.1023420 schema:issn 1530-9932
143 schema:name AAPS PharmSciTech
144 schema:publisher Springer Nature
145 rdf:type schema:Periodical
146 sg:person.01065516667.62 schema:affiliation grid-institutes:grid.411024.2
147 schema:familyName Wilson
148 schema:givenName Wendy I.
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01065516667.62
150 rdf:type schema:Person
151 sg:person.01136741416.72 schema:affiliation grid-institutes:grid.266673.0
152 schema:familyName Peng
153 schema:givenName Yun
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01136741416.72
155 rdf:type schema:Person
156 sg:person.01153104621.46 schema:affiliation grid-institutes:grid.411024.2
157 schema:familyName Augsburger
158 schema:givenName Larry L.
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01153104621.46
160 rdf:type schema:Person
161 sg:pub.10.1023/a:1007578321803 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000308030
162 https://doi.org/10.1023/a:1007578321803
163 rdf:type schema:CreativeWork
164 sg:pub.10.1023/a:1011986823850 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007767460
165 https://doi.org/10.1023/a:1011986823850
166 rdf:type schema:CreativeWork
167 sg:pub.10.1023/a:1015843527138 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002628904
168 https://doi.org/10.1023/a:1015843527138
169 rdf:type schema:CreativeWork
170 sg:pub.10.1023/a:1016212804288 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037126380
171 https://doi.org/10.1023/a:1016212804288
172 rdf:type schema:CreativeWork
173 sg:pub.10.1208/pt040226 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018669844
174 https://doi.org/10.1208/pt040226
175 rdf:type schema:CreativeWork
176 grid-institutes:grid.266673.0 schema:alternateName Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, 21250, Maltiomre, MD
177 schema:name Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, 21250, Maltiomre, MD
178 rdf:type schema:Organization
179 grid-institutes:grid.411024.2 schema:alternateName Department of Pharmaceutical Sciences, University of Maryland-Baltimore, 21201, Baltimore, MD
180 schema:name Department of Pharmaceutical Sciences, University of Maryland-Baltimore, 21201, Baltimore, MD
181 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...