Intelligent clinical decision support for small patient datasets
The ways of substantiating the clinical decision of doctors in the absence of clinical treatment protocols are considered. A comparative evaluation of various statistical methods for ranking clinical symptoms in terms of significance for predicting the outcome of the disease in a small sample of p...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)
2023-06-01
|
Series: | Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki |
Subjects: | |
Online Access: | https://ntv.ifmo.ru/file/article/22068.pdf |
_version_ | 1797798480627892224 |
---|---|
author | Alexandra S. Vatian Alexander A. Golubev Natalia F. Gusarova Natalia V. Dobrenko Aleksei A. Zubanenko Ekaterina S. Kustova Anna A. Tatarinova Ivan V. Tomilov Grigorii F. Shovkoplyas |
author_facet | Alexandra S. Vatian Alexander A. Golubev Natalia F. Gusarova Natalia V. Dobrenko Aleksei A. Zubanenko Ekaterina S. Kustova Anna A. Tatarinova Ivan V. Tomilov Grigorii F. Shovkoplyas |
author_sort | Alexandra S. Vatian |
collection | DOAJ |
description | The ways of substantiating the clinical decision of doctors in the absence of clinical treatment protocols are considered.
A comparative evaluation of various statistical methods for ranking clinical symptoms in terms of significance for
predicting the outcome of the disease in a small sample of patients with COVID-19 and a history of cardiovascular
diseases was performed. The data set (141 patients, 81 factors) was formed based on the materials of electronic
medical records of patients of the Federal State Budgetary Institution “National Medical Research Center named after
V.A. Almazov”. A subset of controllable risk factors (51 factors) was identified. Descriptive statistics methods (one-way
ANOVA, Mann-Whitney and χ² tests) and dimensionality reduction methods (univariate linear regression combined with
multiple logistic regression, generalized discriminant analysis, and various decision tree algorithms) were used to rank
the factors. To compare the ranking results and evaluate the statistical stability, Kendall’s correlation was used, visualized
as a heat map and a positional graph. It has been established that the use of descriptive statistics methods is justified
when ranking on a small sample size of patients. It is shown that the ensemble of ranking results may be statistically
inconsistent. It is concluded that the positions of the same features obtained by ranking them as part of a complete set
and a subset of features do not match; therefore, when choosing a statistical processing method for expert evaluation,
one should take into account the meaningful formulation of the problem. It is shown that the statistical stability of
ranking under conditions of small samples depends on the number of features taken into account, and this dependence
is significantly different for different ranking methods. The proposed method of intellectual support and verification of
clinical decisions in terms of choosing the most significant clinical signs can be used to select and justify the tactics of
managing patients in the absence of clinical protocols. |
first_indexed | 2024-03-13T04:04:21Z |
format | Article |
id | doaj.art-8382cd31ddad424bac949d1e079863f9 |
institution | Directory Open Access Journal |
issn | 2226-1494 2500-0373 |
language | English |
last_indexed | 2024-03-13T04:04:21Z |
publishDate | 2023-06-01 |
publisher | Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) |
record_format | Article |
series | Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki |
spelling | doaj.art-8382cd31ddad424bac949d1e079863f92023-06-21T09:38:53ZengSaint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki2226-14942500-03732023-06-0123359560710.17586/2226-1494-2023-23-3-595-607Intelligent clinical decision support for small patient datasetsAlexandra S. Vatian0https://orcid.org/0000-0002-5483-716XAlexander A. Golubev1https://orcid.org/0000-0001-7417-6947Natalia F. Gusarova2https://orcid.org/0000-0002-1361-6037Natalia V. Dobrenko3https://orcid.org/0000-0001-6206-8033Aleksei A. Zubanenko4https://orcid.org/0000-0001-6953-5239Ekaterina S. Kustova5https://orcid.org/0000-0001-6117-1266Anna A. Tatarinova6https://orcid.org/0000-0002-9046-2457Ivan V. Tomilov7https://orcid.org/0000-0003-1886-2867Grigorii F. Shovkoplyas8https://orcid.org/0000-0001-7777-6972PhD, Assistant Professor, ITMO University, Saint Petersburg, 197101, Russian Federation, sc 57191870868PhD Student, ITMO University, Saint Petersburg, 197101, Russian FederationPhD, Associate Professor, ITMO University, Saint Petersburg, 197101, Russian Federation, sc 57162764200PhD, Associate Professor, ITMO University, Saint Petersburg, 197101, Russian Federation, sc 56499375200Clinical Director, Imaging Medical Vision (IMV) LLC, Saint Petersburg, 191119, Russian Federation, sc 57215436184Student, ITMO University, Saint Petersburg, 197101, Russian FederationPhD (Medicine), Senior Researcher, Senior Researcher, Almazov National Medical Research Center, Saint Petersburg, 197341, Russian Federation, sc 6603195545Senior Laboratory Assistant, ITMO University, Saint Petersburg, 197101, Russian Federation, sc 57772599000Engineer, ITMO University, Saint Petersburg, 197101, Russian Federation, sc 57222048908The ways of substantiating the clinical decision of doctors in the absence of clinical treatment protocols are considered. A comparative evaluation of various statistical methods for ranking clinical symptoms in terms of significance for predicting the outcome of the disease in a small sample of patients with COVID-19 and a history of cardiovascular diseases was performed. The data set (141 patients, 81 factors) was formed based on the materials of electronic medical records of patients of the Federal State Budgetary Institution “National Medical Research Center named after V.A. Almazov”. A subset of controllable risk factors (51 factors) was identified. Descriptive statistics methods (one-way ANOVA, Mann-Whitney and χ² tests) and dimensionality reduction methods (univariate linear regression combined with multiple logistic regression, generalized discriminant analysis, and various decision tree algorithms) were used to rank the factors. To compare the ranking results and evaluate the statistical stability, Kendall’s correlation was used, visualized as a heat map and a positional graph. It has been established that the use of descriptive statistics methods is justified when ranking on a small sample size of patients. It is shown that the ensemble of ranking results may be statistically inconsistent. It is concluded that the positions of the same features obtained by ranking them as part of a complete set and a subset of features do not match; therefore, when choosing a statistical processing method for expert evaluation, one should take into account the meaningful formulation of the problem. It is shown that the statistical stability of ranking under conditions of small samples depends on the number of features taken into account, and this dependence is significantly different for different ranking methods. The proposed method of intellectual support and verification of clinical decisions in terms of choosing the most significant clinical signs can be used to select and justify the tactics of managing patients in the absence of clinical protocols.https://ntv.ifmo.ru/file/article/22068.pdfclinical decision supportclinical expertisefeature rankingsmall cohortsstatistical methods |
spellingShingle | Alexandra S. Vatian Alexander A. Golubev Natalia F. Gusarova Natalia V. Dobrenko Aleksei A. Zubanenko Ekaterina S. Kustova Anna A. Tatarinova Ivan V. Tomilov Grigorii F. Shovkoplyas Intelligent clinical decision support for small patient datasets Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki clinical decision support clinical expertise feature ranking small cohorts statistical methods |
title | Intelligent clinical decision support for small patient datasets |
title_full | Intelligent clinical decision support for small patient datasets |
title_fullStr | Intelligent clinical decision support for small patient datasets |
title_full_unstemmed | Intelligent clinical decision support for small patient datasets |
title_short | Intelligent clinical decision support for small patient datasets |
title_sort | intelligent clinical decision support for small patient datasets |
topic | clinical decision support clinical expertise feature ranking small cohorts statistical methods |
url | https://ntv.ifmo.ru/file/article/22068.pdf |
work_keys_str_mv | AT alexandrasvatian intelligentclinicaldecisionsupportforsmallpatientdatasets AT alexanderagolubev intelligentclinicaldecisionsupportforsmallpatientdatasets AT nataliafgusarova intelligentclinicaldecisionsupportforsmallpatientdatasets AT nataliavdobrenko intelligentclinicaldecisionsupportforsmallpatientdatasets AT alekseiazubanenko intelligentclinicaldecisionsupportforsmallpatientdatasets AT ekaterinaskustova intelligentclinicaldecisionsupportforsmallpatientdatasets AT annaatatarinova intelligentclinicaldecisionsupportforsmallpatientdatasets AT ivanvtomilov intelligentclinicaldecisionsupportforsmallpatientdatasets AT grigoriifshovkoplyas intelligentclinicaldecisionsupportforsmallpatientdatasets |