Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Oct 30:7:e7969.
doi: 10.7717/peerj.7969. eCollection 2019.

Machine learning analysis to identify the association between risk factors and onset of nosocomial diarrhea: a retrospective cohort study

Ken Kurisu  1   2 , Kazuhiro Yoshiuchi  1 , Kei Ogino  1   2 , Toshimi Oda  2
Affiliations

Machine learning analysis to identify the association between risk factors and onset of nosocomial diarrhea: a retrospective cohort study

Ken Kurisu et al. PeerJ. .

Abstract

Background: Although several risk factors for nosocomial diarrhea have been identified, the detail of association between these factors and onset of nosocomial diarrhea, such as degree of importance or temporal pattern of influence, remains unclear. We aimed to determine the association between risk factors and onset of nosocomial diarrhea using machine learning algorithms.

Methods: We retrospectively collected data of patients with acute cerebral infarction. Seven variables, including age, sex, modified Rankin Scale (mRS) score, and number of days of antibiotics, tube feeding, proton pump inhibitors, and histamine 2-receptor antagonist use, were used in the analysis. We split the data into a training dataset and independant test dataset. Based on the training dataset, we developed a random forest, support vector machine (SVM), and radial basis function (RBF) network model. By calculating an area under the curve (AUC) of the receiver operating characteristic curve using 5-fold cross-validation, we performed feature selection and hyperparameter optimization in each model. According to their final performances, we selected the optimal model and also validated it in the independent test dataset. Based on the selected model, we visualized the variable importance and the association between each variable and the outcome using partial dependence plots.

Results: Two-hundred and eighteen patients were included. In the cross-validation within the training dataset, the random forest model achieved an AUC of 0.944, which was higher than in the SVM and RBF network models. The random forest model also achieved an AUC of 0.832 in the independent test dataset. Tube feeding use days, mRS score, antibiotic use days, age and sex were strongly associated with the onset of nosocomial diarrhea, in this order. Tube feeding use had an inverse U-shaped association with the outcome. The mRS score and age had a convex downward and increasing association, while antibiotic use had a convex upward association with the outcome.

Conclusion: We revealed the degree of importance and temporal pattern of the influence of several risk factors for nosocomial diarrhea, which could help clinicians manage nosocomial diarrhea.

Keywords: Antibiotics; Cerebral infarction; Machine learning; Nosocomial diarrhoea; Random forest; Tube feeding.

PubMed Disclaimer

Conflict of interest statement

The authors declare there are no competing interests.

Figures

Figure 1
Figure 1. Flow chart of the study cohort.
Flow chart shows the number of included and excluded patients and the reasons for exclusion.
Figure 2
Figure 2. Variable importance according to mean decrease in Gini coefficient.
Bar graphs show the mean decrease in the Gini coefficient of each variable, which is considered as the index of importance. mRS, modified Rankin Scale.
Figure 3
Figure 3. Partial dependence plots.
(A) Temporal changes in the influence of tube feeding use. (B) The association between mRS score and influence. (C) Temporal changes in the influence of antibiotics use. (D) The association between age and influence. (E) The association between sex and influence. mRS, modified Rankin Scale.
See this image and copyright information in PMC

References

    1. Adams Jr HP, Bendixen BH, Kappelle LJ, Biller J, Love BB, Gordon DL, Marsh 3rd EE. Classification of subtype of acute ischemic stroke. Definitions for use in a multicenter clinical trial. TOAST. Trial of Org 10172 in acute stroke treatment. Stroke. 1993;24:35–41. doi: 10.1161/01.str.24.1.35. - DOI - PubMed
    1. Arevalo-Manso JJ, Martinez-Sanchez P, Juarez-Martin B, Fuentes B, Ruiz-Ares G, Sanz-Cuesta BE, Parrilla-Novo P, Diez-Tejedor E. Enteral tube feeding of patients with acute stroke: when does the risk of diarrhea increase? Internal Medicine Journal. 2014;44:1199–1204. doi: 10.1111/imj.12586. - DOI - PubMed
    1. Bair E, Ohrbach R, Fillingim RB, Greenspan JD, Dubner R, Diatchenko L, Helgeson E, Knott C, Maixner W, Slade GD. Multivariable modeling of phenotypic risk factors for first-onset TMD: the OPPERA prospective cohort study. The Journal of Pain. 2013;14:T102–T115. doi: 10.1016/j.jpain.2013.09.003. - DOI - PMC - PubMed
    1. Bauer TM, Lalvani A, Fehrenbach J, Steffen I, Aponte JJ, Segovia R, Vila J, Philippczik G, Steinbrückner B, Frei R, Bowler I, Kist M. Derivation and validation of guidelines for stool cultures for enteropathogenic bacteria other than Clostridium difficile in hospitalized adults. Journal of the American Medical Association. 2001;285:313–319. doi: 10.1001/jama.285.3.313. - DOI - PubMed
    1. Baur D, Gladstone BP, Burkert F, Carrara E, Foschi F, Döbele S, Tacconelli E. Effect of antibiotic stewardship on the incidence of infection and colonisation with antibiotic-resistant bacteria and Clostridium difficile infection: a systematic review and meta-analysis. The Lancet Infectious Diseases. 2017;17:990–1001. doi: 10.1016/S1473-3099(17)30325-0. - DOI - PubMed

LinkOut - more resources