The use of artificial neural networks for the selection of the most appropriate formulation and processing variables in order to ... View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2003-06

AUTHORS

Michael M. Leane, Iain Cumming, Owen I. Corrigan

ABSTRACT

The objective of this work was to apply artificial neural networks (ANNs) to examine the relative importance of various factors, both formulation and process, governing the in-vitro dissolution from enteric-coated sustained release (SR) minitablets. Input feature selection (IFS) algorithms were used in order to give an estimate of the relative importance of the various formulation and processing variables in determining minitablet dissolution rate. Both forward and backward stepwise algorithms were used as well as genetic algorithms. Networks were subsequently trained using the back propagation algorithm in order to check whether or not the IFS process had correctly located any unimportant inputs. IFS gave consistent rankings for the importance of the various formulation and processing variables in determining the release of drug from minitablets. Consistent ranking was achieved for both indices of the release process; ie, the time taken for release to commence through the enteric coat (Tlag) and that for the drug to diffuse through the SR matrix of the minitablet into the dissolution medium (T90-10). In the case of the Tlag phase, the main coating parameters, along with the original batch blend size and the blend time with lubricant, were found to have most influence. By contrast, with the T90-10 phase, the amounts of matrix forming polymer and direct compression filler were most important. In the subsequent training of the ANNs, removal of inputs regarded as less important led to improved network performance. ANNs were capable of ranking the relative importance of the various formulations and processing variables that influenced the release rate of the drug from minitablets. This could be done for all main stages of the release process. Subsequent training of the ANN verified that removal of less relevant inputs from the training process led to an improved performance from the ANN. More... »

PAGES

129-140

Identifiers

URI

http://scigraph.springernature.com/pub.10.1208/pt040226

DOI

http://dx.doi.org/10.1208/pt040226

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1018669844

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/12916908


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": "Chemistry, Pharmaceutical", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Computer Simulation", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Delayed-Action Preparations", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Models, Chemical", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks, Computer", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Software", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Tablets", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Elan Pharmaceutical Technologies, Trinity College, Biotechnology Building, Dublin 2, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.8217.c", 
          "name": [
            "Department of Pharmaceutics and Pharmaceutical Technology, School of Pharmacy, Trinity College, Dublin 2, Ireland", 
            "Elan Pharmaceutical Technologies, Trinity College, Biotechnology Building, Dublin 2, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Leane", 
        "givenName": "Michael M.", 
        "id": "sg:person.0606072440.77", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0606072440.77"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Elan Pharmaceutical Technologies, Trinity College, Biotechnology Building, Dublin 2, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.8217.c", 
          "name": [
            "Elan Pharmaceutical Technologies, Trinity College, Biotechnology Building, Dublin 2, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cumming", 
        "givenName": "Iain", 
        "id": "sg:person.0740437307.39", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0740437307.39"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Pharmaceutics and Pharmaceutical Technology, School of Pharmacy, Trinity College, Dublin 2, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.8217.c", 
          "name": [
            "Department of Pharmaceutics and Pharmaceutical Technology, School of Pharmacy, Trinity College, Dublin 2, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Corrigan", 
        "givenName": "Owen I.", 
        "id": "sg:person.01120462577.83", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01120462577.83"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1023/a:1018917128684", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028417432", 
          "https://doi.org/10.1023/a:1018917128684"
        ], 
        "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.10.1023/a:1018966222807", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042859520", 
          "https://doi.org/10.1023/a:1018966222807"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2003-06", 
    "datePublishedReg": "2003-06-01", 
    "description": "The objective of this work was to apply artificial neural networks (ANNs) to examine the relative importance of various factors, both formulation and process, governing the in-vitro dissolution from enteric-coated sustained release (SR) minitablets. Input feature selection (IFS) algorithms were used in order to give an estimate of the relative importance of the various formulation and processing variables in determining minitablet dissolution rate. Both forward and backward stepwise algorithms were used as well as genetic algorithms. Networks were subsequently trained using the back propagation algorithm in order to check whether or not the IFS process had correctly located any unimportant inputs. IFS gave consistent rankings for the importance of the various formulation and processing variables in determining the release of drug from minitablets. Consistent ranking was achieved for both indices of the release process; ie, the time taken for release to commence through the enteric coat (Tlag) and that for the drug to diffuse through the SR matrix of the minitablet into the dissolution medium (T90-10). In the case of the Tlag phase, the main coating parameters, along with the original batch blend size and the blend time with lubricant, were found to have most influence. By contrast, with the T90-10 phase, the amounts of matrix forming polymer and direct compression filler were most important. In the subsequent training of the ANNs, removal of inputs regarded as less important led to improved network performance. ANNs were capable of ranking the relative importance of the various formulations and processing variables that influenced the release rate of the drug from minitablets. This could be done for all main stages of the release process. Subsequent training of the ANN verified that removal of less relevant inputs from the training process led to an improved performance from the ANN.", 
    "genre": "article", 
    "id": "sg:pub.10.1208/pt040226", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1023420", 
        "issn": [
          "1530-9932"
        ], 
        "name": "AAPS PharmSciTech", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "4"
      }
    ], 
    "keywords": [
      "sustained release minitablets", 
      "processing variables", 
      "artificial neural network", 
      "coating parameters", 
      "release process", 
      "blend time", 
      "SR matrix", 
      "release rate", 
      "release of drugs", 
      "improved performance", 
      "dissolution rate", 
      "back-propagation algorithm", 
      "minitablets", 
      "neural network", 
      "enteric coat", 
      "dissolution medium", 
      "direct compression fillers", 
      "improved network performance", 
      "dissolution", 
      "filler", 
      "formulation", 
      "appropriate formulation", 
      "lubricant", 
      "performance", 
      "genetic algorithm", 
      "matrix", 
      "removal", 
      "process", 
      "amount of matrix", 
      "phase", 
      "unimportant inputs", 
      "input", 
      "network performance", 
      "algorithm", 
      "polymers", 
      "order", 
      "propagation algorithm", 
      "most influence", 
      "main stages", 
      "relevant inputs", 
      "network", 
      "parameters", 
      "removal of input", 
      "training process", 
      "influence", 
      "time", 
      "work", 
      "rate", 
      "size", 
      "relative importance", 
      "feature selection algorithm", 
      "selection algorithm", 
      "amount", 
      "consistent ranking", 
      "variables", 
      "coat", 
      "release", 
      "medium", 
      "use", 
      "commences", 
      "importance", 
      "objective", 
      "estimates", 
      "stage", 
      "selection", 
      "cases", 
      "factors", 
      "index", 
      "backward stepwise algorithm", 
      "ranking", 
      "IFS", 
      "contrast", 
      "stepwise algorithm", 
      "training", 
      "subsequent training", 
      "drugs"
    ], 
    "name": "The use of artificial neural networks for the selection of the most appropriate formulation and processing variables in order to predict the in vitro dissolution of sustained release minitablets", 
    "pagination": "129-140", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1018669844"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1208/pt040226"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "12916908"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1208/pt040226", 
      "https://app.dimensions.ai/details/publication/pub.1018669844"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-08-04T16:55", 
    "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_377.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1208/pt040226"
  }
]
 

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/pt040226'

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/pt040226'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1208/pt040226'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1208/pt040226'


 

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

196 TRIPLES      21 PREDICATES      113 URIs      102 LITERALS      15 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1208/pt040226 schema:about N1a8dd0ac620b4575ad36e47fd2397fd3
2 N2a4731de8af74ed79738ca0b49271744
3 N2fc9298bc62d4a6d92b7cf9ab652b714
4 N2ff74be3195d45d09fb773479fae0565
5 N8b8a9d7bedd6474994e10451c9bdeebf
6 Na055cdaa533145eb9c1a6bbcc6e82681
7 Nb84489e7da1249afa5f03aea3cb555cf
8 Ncbeeb03afc5a4235b862fa86d1d1d987
9 anzsrc-for:11
10 anzsrc-for:1115
11 schema:author Nee88e889f82b4e149068b81b42fd28d4
12 schema:citation sg:pub.10.1023/a:1015843527138
13 sg:pub.10.1023/a:1018917128684
14 sg:pub.10.1023/a:1018966222807
15 schema:datePublished 2003-06
16 schema:datePublishedReg 2003-06-01
17 schema:description The objective of this work was to apply artificial neural networks (ANNs) to examine the relative importance of various factors, both formulation and process, governing the in-vitro dissolution from enteric-coated sustained release (SR) minitablets. Input feature selection (IFS) algorithms were used in order to give an estimate of the relative importance of the various formulation and processing variables in determining minitablet dissolution rate. Both forward and backward stepwise algorithms were used as well as genetic algorithms. Networks were subsequently trained using the back propagation algorithm in order to check whether or not the IFS process had correctly located any unimportant inputs. IFS gave consistent rankings for the importance of the various formulation and processing variables in determining the release of drug from minitablets. Consistent ranking was achieved for both indices of the release process; ie, the time taken for release to commence through the enteric coat (Tlag) and that for the drug to diffuse through the SR matrix of the minitablet into the dissolution medium (T90-10). In the case of the Tlag phase, the main coating parameters, along with the original batch blend size and the blend time with lubricant, were found to have most influence. By contrast, with the T90-10 phase, the amounts of matrix forming polymer and direct compression filler were most important. In the subsequent training of the ANNs, removal of inputs regarded as less important led to improved network performance. ANNs were capable of ranking the relative importance of the various formulations and processing variables that influenced the release rate of the drug from minitablets. This could be done for all main stages of the release process. Subsequent training of the ANN verified that removal of less relevant inputs from the training process led to an improved performance from the ANN.
18 schema:genre article
19 schema:isAccessibleForFree true
20 schema:isPartOf N3bee99889cd84fb4a1939b8bf6fe1e63
21 N3e55f38eeaec4a70afadd37ef2b8a446
22 sg:journal.1023420
23 schema:keywords IFS
24 SR matrix
25 algorithm
26 amount
27 amount of matrix
28 appropriate formulation
29 artificial neural network
30 back-propagation algorithm
31 backward stepwise algorithm
32 blend time
33 cases
34 coat
35 coating parameters
36 commences
37 consistent ranking
38 contrast
39 direct compression fillers
40 dissolution
41 dissolution medium
42 dissolution rate
43 drugs
44 enteric coat
45 estimates
46 factors
47 feature selection algorithm
48 filler
49 formulation
50 genetic algorithm
51 importance
52 improved network performance
53 improved performance
54 index
55 influence
56 input
57 lubricant
58 main stages
59 matrix
60 medium
61 minitablets
62 most influence
63 network
64 network performance
65 neural network
66 objective
67 order
68 parameters
69 performance
70 phase
71 polymers
72 process
73 processing variables
74 propagation algorithm
75 ranking
76 rate
77 relative importance
78 release
79 release of drugs
80 release process
81 release rate
82 relevant inputs
83 removal
84 removal of input
85 selection
86 selection algorithm
87 size
88 stage
89 stepwise algorithm
90 subsequent training
91 sustained release minitablets
92 time
93 training
94 training process
95 unimportant inputs
96 use
97 variables
98 work
99 schema:name The use of artificial neural networks for the selection of the most appropriate formulation and processing variables in order to predict the in vitro dissolution of sustained release minitablets
100 schema:pagination 129-140
101 schema:productId N5db2e8f544be4fdfb95fe95ee1574fd3
102 Nd8ef18b55fe84b129f3e111044dfb549
103 Nebcbae86db2948128489986b99f8b13a
104 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018669844
105 https://doi.org/10.1208/pt040226
106 schema:sdDatePublished 2022-08-04T16:55
107 schema:sdLicense https://scigraph.springernature.com/explorer/license/
108 schema:sdPublisher N482a0ae220f84396a4281222e64cff2c
109 schema:url https://doi.org/10.1208/pt040226
110 sgo:license sg:explorer/license/
111 sgo:sdDataset articles
112 rdf:type schema:ScholarlyArticle
113 N1a8dd0ac620b4575ad36e47fd2397fd3 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
114 schema:name Neural Networks, Computer
115 rdf:type schema:DefinedTerm
116 N2a4731de8af74ed79738ca0b49271744 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
117 schema:name Software
118 rdf:type schema:DefinedTerm
119 N2fc9298bc62d4a6d92b7cf9ab652b714 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
120 schema:name Chemistry, Pharmaceutical
121 rdf:type schema:DefinedTerm
122 N2ff74be3195d45d09fb773479fae0565 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
123 schema:name Tablets
124 rdf:type schema:DefinedTerm
125 N3bee99889cd84fb4a1939b8bf6fe1e63 schema:issueNumber 2
126 rdf:type schema:PublicationIssue
127 N3e55f38eeaec4a70afadd37ef2b8a446 schema:volumeNumber 4
128 rdf:type schema:PublicationVolume
129 N482a0ae220f84396a4281222e64cff2c schema:name Springer Nature - SN SciGraph project
130 rdf:type schema:Organization
131 N5db2e8f544be4fdfb95fe95ee1574fd3 schema:name doi
132 schema:value 10.1208/pt040226
133 rdf:type schema:PropertyValue
134 N8b8a9d7bedd6474994e10451c9bdeebf schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
135 schema:name Models, Chemical
136 rdf:type schema:DefinedTerm
137 Na055cdaa533145eb9c1a6bbcc6e82681 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
138 schema:name Delayed-Action Preparations
139 rdf:type schema:DefinedTerm
140 Nb84489e7da1249afa5f03aea3cb555cf schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
141 schema:name Computer Simulation
142 rdf:type schema:DefinedTerm
143 Nc2da96b8c26348f39414aecf86b87fb6 rdf:first sg:person.0740437307.39
144 rdf:rest Nd1239992e37b45cab812e1939bffb203
145 Ncbeeb03afc5a4235b862fa86d1d1d987 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
146 schema:name Artificial Intelligence
147 rdf:type schema:DefinedTerm
148 Nd1239992e37b45cab812e1939bffb203 rdf:first sg:person.01120462577.83
149 rdf:rest rdf:nil
150 Nd8ef18b55fe84b129f3e111044dfb549 schema:name pubmed_id
151 schema:value 12916908
152 rdf:type schema:PropertyValue
153 Nebcbae86db2948128489986b99f8b13a schema:name dimensions_id
154 schema:value pub.1018669844
155 rdf:type schema:PropertyValue
156 Nee88e889f82b4e149068b81b42fd28d4 rdf:first sg:person.0606072440.77
157 rdf:rest Nc2da96b8c26348f39414aecf86b87fb6
158 anzsrc-for:11 schema:inDefinedTermSet anzsrc-for:
159 schema:name Medical and Health Sciences
160 rdf:type schema:DefinedTerm
161 anzsrc-for:1115 schema:inDefinedTermSet anzsrc-for:
162 schema:name Pharmacology and Pharmaceutical Sciences
163 rdf:type schema:DefinedTerm
164 sg:journal.1023420 schema:issn 1530-9932
165 schema:name AAPS PharmSciTech
166 schema:publisher Springer Nature
167 rdf:type schema:Periodical
168 sg:person.01120462577.83 schema:affiliation grid-institutes:grid.8217.c
169 schema:familyName Corrigan
170 schema:givenName Owen I.
171 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01120462577.83
172 rdf:type schema:Person
173 sg:person.0606072440.77 schema:affiliation grid-institutes:grid.8217.c
174 schema:familyName Leane
175 schema:givenName Michael M.
176 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0606072440.77
177 rdf:type schema:Person
178 sg:person.0740437307.39 schema:affiliation grid-institutes:grid.8217.c
179 schema:familyName Cumming
180 schema:givenName Iain
181 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0740437307.39
182 rdf:type schema:Person
183 sg:pub.10.1023/a:1015843527138 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002628904
184 https://doi.org/10.1023/a:1015843527138
185 rdf:type schema:CreativeWork
186 sg:pub.10.1023/a:1018917128684 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028417432
187 https://doi.org/10.1023/a:1018917128684
188 rdf:type schema:CreativeWork
189 sg:pub.10.1023/a:1018966222807 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042859520
190 https://doi.org/10.1023/a:1018966222807
191 rdf:type schema:CreativeWork
192 grid-institutes:grid.8217.c schema:alternateName Department of Pharmaceutics and Pharmaceutical Technology, School of Pharmacy, Trinity College, Dublin 2, Ireland
193 Elan Pharmaceutical Technologies, Trinity College, Biotechnology Building, Dublin 2, Ireland
194 schema:name Department of Pharmaceutics and Pharmaceutical Technology, School of Pharmacy, Trinity College, Dublin 2, Ireland
195 Elan Pharmaceutical Technologies, Trinity College, Biotechnology Building, Dublin 2, Ireland
196 rdf:type schema:Organization
 




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


...