Academic Journal
Προβολή σε EDS

Machine Learning-Enabled Image Analysis of Complex Chemical Mixtures: Synthetic Urine Droplets as a Test System.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Machine Learning-Enabled Image Analysis of Complex Chemical Mixtures: Synthetic Urine Droplets as a Test System.
Συγγραφείς: S V A; Florida State University, Department of Chemistry and Biochemistry, Tallahassee, Florida 32306-4390, United States., Dangi BB; Florida Agricultural and Mechanical University, Department of Chemistry, Tallahassee, Florida 32307, United States., Steinbock O; Florida State University, Department of Chemistry and Biochemistry, Tallahassee, Florida 32306-4390, United States.
Πηγή: Analytical chemistry [Anal Chem] 2026 Jul 14; Vol. 98 (27), pp. 20563-20571. Date of Electronic Publication: 2026 Jul 03.
Τύπος έκδοσης: Journal Article; Research Support, Non-U.S. Gov't
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: American Chemical Society Country of Publication: United States NLM ID: 0370536 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1520-6882 (Electronic) Linking ISSN: 00032700 NLM ISO Abbreviation: Anal Chem Subsets: MEDLINE
Imprint Name(s): Original Publication: Washington, American Chemical Society.
Ιατρικοί όροι (MeSH): Complex Mixtures*/analysis , Urine*/chemistry , Machine Learning* , Image Processing, Computer-Assisted*, Urea/urine ; Urea/analysis ; Sodium Chloride/urine ; Sodium Chloride/analysis ; Potassium Chloride/urine ; Potassium Chloride/analysis ; Creatinine/urine ; Glucose/analysis ; Hydrogen-Ion Concentration ; Humans
Περίληψη: Dried droplet deposits encode compositional information through evaporation-driven self-organization, offering a potential low-cost sensing modality for chemical analyses. Here, we evaluate the feasibility of inferring solute concentrations and pH from photographic images of dried synthetic urine stains by using automated experimentation and machine learning. A robotic droplet imager (RODI) combined with Latin hypercube sampling was employed to efficiently explore compositional space and generate standardized data sets comprising 70,000 images across two experimental systems: a two-component urea-NaCl model and seven-component synthetic urine mixtures spanning physiologically relevant ranges for urea, NaCl, KCl, creatinine, glucose, a combined salt group, and pH. Each image was reduced to 47 descriptors, capturing spatial morphology and texture. Random Forest regression yielded useful predictive performance for NaCl in the two-component system and identified pH as the most robustly inferred parameter in the complex mixture. However, continuous prediction of individual solute concentrations in the seven-component system remained limited, possibly due to the sparsity of training points across the high-dimensional compositional space. These findings delineate both the current capabilities and information-theoretic constraints of image-based compositional inference for complex chemical mixtures.
Substance Nomenclature: 8W8T17847W (Urea)
451W47IQ8X (Sodium Chloride)
660YQ98I10 (Potassium Chloride)
AYI8EX34EU (Creatinine)
IY9XDZ35W2 (Glucose)
0 (Complex Mixtures)
Entry Date(s): Date Created: 20260703 Date Completed: 20260714 Latest Revision: 20260721
Update Code: 20260722
DOI: 10.1021/acs.analchem.6c02602
PMID: 42396863
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=15206882&ISBN=&volume=98&issue=27&date=20260714&spage=20563&pages=20563-20571&title=Analytical chemistry&atitle=Machine%20Learning-Enabled%20Image%20Analysis%20of%20Complex%20Chemical%20Mixtures%3A%20Synthetic%20Urine%20Droplets%20as%20a%20Test%20System.&aulast=S%20V%20A&id=DOI:10.1021/acs.analchem.6c02602
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42396863
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Machine Learning-Enabled Image Analysis of Complex Chemical Mixtures: Synthetic Urine Droplets as a Test System.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22S+V+A%22">S V A</searchLink>; Florida State University, Department of Chemistry and Biochemistry, Tallahassee, Florida 32306-4390, United States.<br /><searchLink fieldCode="AU" term="%22Dangi+BB%22">Dangi BB</searchLink>; Florida Agricultural and Mechanical University, Department of Chemistry, Tallahassee, Florida 32307, United States.<br /><searchLink fieldCode="AU" term="%22Steinbock+O%22">Steinbock O</searchLink>; Florida State University, Department of Chemistry and Biochemistry, Tallahassee, Florida 32306-4390, United States.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%220370536%22">Analytical chemistry</searchLink> [Anal Chem] 2026 Jul 14; Vol. 98 (27), pp. 20563-20571. <i>Date of Electronic Publication: </i>2026 Jul 03.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article; Research Support, Non-U.S. Gov't
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22American+Chemical+Society%22">American Chemical Society </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>0370536 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1520-6882 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2200032700%22">00032700 </searchLink><i>NLM ISO Abbreviation: </i>Anal Chem <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: Washington, American Chemical Society.
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Complex+Mixtures%22">Complex Mixtures*</searchLink>/<searchLink fieldCode="MM" term="%22Complex+Mixtures+analysis%22">analysis</searchLink> <br /><searchLink fieldCode="MM" term="%22Urine%22">Urine*</searchLink>/<searchLink fieldCode="MM" term="%22Urine+chemistry%22">chemistry</searchLink> <br /><searchLink fieldCode="MM" term="%22Machine+Learning%22">Machine Learning*</searchLink> <br /><searchLink fieldCode="MM" term="%22Image+Processing%2C+Computer-Assisted%22">Image Processing, Computer-Assisted*</searchLink><br /><searchLink fieldCode="MH" term="%22Urea%22">Urea</searchLink>/<searchLink fieldCode="MH" term="%22Urea+urine%22">urine</searchLink> ; <searchLink fieldCode="MH" term="%22Urea%22">Urea</searchLink>/<searchLink fieldCode="MH" term="%22Urea+analysis%22">analysis</searchLink> ; <searchLink fieldCode="MH" term="%22Sodium+Chloride%22">Sodium Chloride</searchLink>/<searchLink fieldCode="MH" term="%22Sodium+Chloride+urine%22">urine</searchLink> ; <searchLink fieldCode="MH" term="%22Sodium+Chloride%22">Sodium Chloride</searchLink>/<searchLink fieldCode="MH" term="%22Sodium+Chloride+analysis%22">analysis</searchLink> ; <searchLink fieldCode="MH" term="%22Potassium+Chloride%22">Potassium Chloride</searchLink>/<searchLink fieldCode="MH" term="%22Potassium+Chloride+urine%22">urine</searchLink> ; <searchLink fieldCode="MH" term="%22Potassium+Chloride%22">Potassium Chloride</searchLink>/<searchLink fieldCode="MH" term="%22Potassium+Chloride+analysis%22">analysis</searchLink> ; <searchLink fieldCode="MH" term="%22Creatinine%22">Creatinine</searchLink>/<searchLink fieldCode="MH" term="%22Creatinine+urine%22">urine</searchLink> ; <searchLink fieldCode="MH" term="%22Glucose%22">Glucose</searchLink>/<searchLink fieldCode="MH" term="%22Glucose+analysis%22">analysis</searchLink> ; <searchLink fieldCode="MH" term="%22Hydrogen-Ion+Concentration%22">Hydrogen-Ion Concentration</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Dried droplet deposits encode compositional information through evaporation-driven self-organization, offering a potential low-cost sensing modality for chemical analyses. Here, we evaluate the feasibility of inferring solute concentrations and pH from photographic images of dried synthetic urine stains by using automated experimentation and machine learning. A robotic droplet imager (RODI) combined with Latin hypercube sampling was employed to efficiently explore compositional space and generate standardized data sets comprising 70,000 images across two experimental systems: a two-component urea-NaCl model and seven-component synthetic urine mixtures spanning physiologically relevant ranges for urea, NaCl, KCl, creatinine, glucose, a combined salt group, and pH. Each image was reduced to 47 descriptors, capturing spatial morphology and texture. Random Forest regression yielded useful predictive performance for NaCl in the two-component system and identified pH as the most robustly inferred parameter in the complex mixture. However, continuous prediction of individual solute concentrations in the seven-component system remained limited, possibly due to the sparsity of training points across the high-dimensional compositional space. These findings delineate both the current capabilities and information-theoretic constraints of image-based compositional inference for complex chemical mixtures.
– Name: NumberCAS
  Label: Substance Nomenclature
  Group: ID
  Data: 8W8T17847W (Urea)<br />451W47IQ8X (Sodium Chloride)<br />660YQ98I10 (Potassium Chloride)<br />AYI8EX34EU (Creatinine)<br />IY9XDZ35W2 (Glucose)<br />0 (Complex Mixtures)
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260703 <i>Date Completed: </i>20260714 <i>Latest Revision: </i>20260721
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260722
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1021/acs.analchem.6c02602
– Name: AN
  Label: PMID
  Group: ID
  Data: 42396863
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42396863
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1021/acs.analchem.6c02602
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 20563
    Subjects:
      – SubjectFull: Urea urine
        Type: general
      – SubjectFull: Urea analysis
        Type: general
      – SubjectFull: Sodium Chloride urine
        Type: general
      – SubjectFull: Sodium Chloride analysis
        Type: general
      – SubjectFull: Potassium Chloride urine
        Type: general
      – SubjectFull: Potassium Chloride analysis
        Type: general
      – SubjectFull: Creatinine urine
        Type: general
      – SubjectFull: Glucose analysis
        Type: general
      – SubjectFull: Hydrogen-Ion Concentration
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Complex Mixtures analysis
        Type: general
      – SubjectFull: Urine chemistry
        Type: general
      – SubjectFull: Machine Learning
        Type: general
      – SubjectFull: Image Processing, Computer-Assisted
        Type: general
    Titles:
      – TitleFull: Machine Learning-Enabled Image Analysis of Complex Chemical Mixtures: Synthetic Urine Droplets as a Test System.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: S V A
      – PersonEntity:
          Name:
            NameFull: Dangi BB
      – PersonEntity:
          Name:
            NameFull: Steinbock O
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 14
              M: 07
              Text: 2026 Jul 14
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1520-6882
          Numbering:
            – Type: volume
              Value: 98
            – Type: issue
              Value: 27
          Titles:
            – TitleFull: Analytical chemistry
              Type: main
ResultId 1