Artificial neural networks: A study in clinical psychopharmacology

Ernestina Politi, Carlo Balduzzi, Riccardo Bussi, Laura Bellodi

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Controlled trials in clinical psychopharmacology may fail to provide reliable information about the benefit of treatment when the patient is viewed in a real-life setting rather than as part of a well-defined sampling procedure. A viewpoint, rooted in systems theory, is proposed based on the identification of complex relationships among such dimensions as clinician's reasoning, drug properties, and patient's condition. Artificial Neural Network (ANN) technology provides efficient tools for data analysis within a systems-oriented approach. This study proposes a way to predict the outcome of psychopharmacological treatment. Analysis was conducted on retrospective data from clinical records of psychiatric patients treated with moclobemide. Twelve pharmacological, diagnostic, and topological variables were identified as the decisional items considered by six clinicians: age at onset, sex, previous treatment, duration and dose of moclobemide treatment, other drugs, psychiatric diagnosis and other clinical features. Data were binarily coded and transformed into observed frequencies in the sampling space; treatment outcome was binarily scored as the model's target. A Back-Propagation ANN based on the Delta rule with logistic transfer function was used. ANN correctly classified all cases of successful treatment (n=51, 100%) but only half of the unsuccessful cases (n=14, 52%). Patterns of response and areas of uncertainty were analyzed in a topological approach. Copyright (C) 1999 Elsevier Science Ireland Ltd.

Original languageEnglish
Pages (from-to)203-215
Number of pages13
JournalPsychiatry Research
Volume87
Issue number2-3
DOIs
Publication statusPublished - Oct 11 1999

Fingerprint

Psychopharmacology
Moclobemide
Systems Theory
Controlled Clinical Trials
Therapeutics
Systems Analysis
Age of Onset
Mental Disorders
Pharmaceutical Preparations
Uncertainty
Psychiatry
Pharmacology
Technology
Clinical Studies

Keywords

  • Affective disorder
  • Anxiety disorder
  • Moclobemide
  • Statistics
  • Systems theory
  • Treatment outcome

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry
  • Psychology(all)

Cite this

Artificial neural networks : A study in clinical psychopharmacology. / Politi, Ernestina; Balduzzi, Carlo; Bussi, Riccardo; Bellodi, Laura.

In: Psychiatry Research, Vol. 87, No. 2-3, 11.10.1999, p. 203-215.

Research output: Contribution to journalArticle

Politi, E, Balduzzi, C, Bussi, R & Bellodi, L 1999, 'Artificial neural networks: A study in clinical psychopharmacology', Psychiatry Research, vol. 87, no. 2-3, pp. 203-215. https://doi.org/10.1016/S0165-1781(99)00049-9
Politi, Ernestina ; Balduzzi, Carlo ; Bussi, Riccardo ; Bellodi, Laura. / Artificial neural networks : A study in clinical psychopharmacology. In: Psychiatry Research. 1999 ; Vol. 87, No. 2-3. pp. 203-215.
@article{39a08487782448ec8391848b8facaf14,
title = "Artificial neural networks: A study in clinical psychopharmacology",
abstract = "Controlled trials in clinical psychopharmacology may fail to provide reliable information about the benefit of treatment when the patient is viewed in a real-life setting rather than as part of a well-defined sampling procedure. A viewpoint, rooted in systems theory, is proposed based on the identification of complex relationships among such dimensions as clinician's reasoning, drug properties, and patient's condition. Artificial Neural Network (ANN) technology provides efficient tools for data analysis within a systems-oriented approach. This study proposes a way to predict the outcome of psychopharmacological treatment. Analysis was conducted on retrospective data from clinical records of psychiatric patients treated with moclobemide. Twelve pharmacological, diagnostic, and topological variables were identified as the decisional items considered by six clinicians: age at onset, sex, previous treatment, duration and dose of moclobemide treatment, other drugs, psychiatric diagnosis and other clinical features. Data were binarily coded and transformed into observed frequencies in the sampling space; treatment outcome was binarily scored as the model's target. A Back-Propagation ANN based on the Delta rule with logistic transfer function was used. ANN correctly classified all cases of successful treatment (n=51, 100{\%}) but only half of the unsuccessful cases (n=14, 52{\%}). Patterns of response and areas of uncertainty were analyzed in a topological approach. Copyright (C) 1999 Elsevier Science Ireland Ltd.",
keywords = "Affective disorder, Anxiety disorder, Moclobemide, Statistics, Systems theory, Treatment outcome",
author = "Ernestina Politi and Carlo Balduzzi and Riccardo Bussi and Laura Bellodi",
year = "1999",
month = "10",
day = "11",
doi = "10.1016/S0165-1781(99)00049-9",
language = "English",
volume = "87",
pages = "203--215",
journal = "Psychiatry Research",
issn = "0165-1781",
publisher = "Elsevier Ireland Ltd",
number = "2-3",

}

TY - JOUR

T1 - Artificial neural networks

T2 - A study in clinical psychopharmacology

AU - Politi, Ernestina

AU - Balduzzi, Carlo

AU - Bussi, Riccardo

AU - Bellodi, Laura

PY - 1999/10/11

Y1 - 1999/10/11

N2 - Controlled trials in clinical psychopharmacology may fail to provide reliable information about the benefit of treatment when the patient is viewed in a real-life setting rather than as part of a well-defined sampling procedure. A viewpoint, rooted in systems theory, is proposed based on the identification of complex relationships among such dimensions as clinician's reasoning, drug properties, and patient's condition. Artificial Neural Network (ANN) technology provides efficient tools for data analysis within a systems-oriented approach. This study proposes a way to predict the outcome of psychopharmacological treatment. Analysis was conducted on retrospective data from clinical records of psychiatric patients treated with moclobemide. Twelve pharmacological, diagnostic, and topological variables were identified as the decisional items considered by six clinicians: age at onset, sex, previous treatment, duration and dose of moclobemide treatment, other drugs, psychiatric diagnosis and other clinical features. Data were binarily coded and transformed into observed frequencies in the sampling space; treatment outcome was binarily scored as the model's target. A Back-Propagation ANN based on the Delta rule with logistic transfer function was used. ANN correctly classified all cases of successful treatment (n=51, 100%) but only half of the unsuccessful cases (n=14, 52%). Patterns of response and areas of uncertainty were analyzed in a topological approach. Copyright (C) 1999 Elsevier Science Ireland Ltd.

AB - Controlled trials in clinical psychopharmacology may fail to provide reliable information about the benefit of treatment when the patient is viewed in a real-life setting rather than as part of a well-defined sampling procedure. A viewpoint, rooted in systems theory, is proposed based on the identification of complex relationships among such dimensions as clinician's reasoning, drug properties, and patient's condition. Artificial Neural Network (ANN) technology provides efficient tools for data analysis within a systems-oriented approach. This study proposes a way to predict the outcome of psychopharmacological treatment. Analysis was conducted on retrospective data from clinical records of psychiatric patients treated with moclobemide. Twelve pharmacological, diagnostic, and topological variables were identified as the decisional items considered by six clinicians: age at onset, sex, previous treatment, duration and dose of moclobemide treatment, other drugs, psychiatric diagnosis and other clinical features. Data were binarily coded and transformed into observed frequencies in the sampling space; treatment outcome was binarily scored as the model's target. A Back-Propagation ANN based on the Delta rule with logistic transfer function was used. ANN correctly classified all cases of successful treatment (n=51, 100%) but only half of the unsuccessful cases (n=14, 52%). Patterns of response and areas of uncertainty were analyzed in a topological approach. Copyright (C) 1999 Elsevier Science Ireland Ltd.

KW - Affective disorder

KW - Anxiety disorder

KW - Moclobemide

KW - Statistics

KW - Systems theory

KW - Treatment outcome

UR - http://www.scopus.com/inward/record.url?scp=0032697035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032697035&partnerID=8YFLogxK

U2 - 10.1016/S0165-1781(99)00049-9

DO - 10.1016/S0165-1781(99)00049-9

M3 - Article

AN - SCOPUS:0032697035

VL - 87

SP - 203

EP - 215

JO - Psychiatry Research

JF - Psychiatry Research

SN - 0165-1781

IS - 2-3

ER -