Identification of Risk Factors of Multidrug-Resistant Tuberculosis by using Classification Tree Method

Tan, Dixin; Wang, Bin; Li, Xuhui; Cai, Xiaonan; Zhang, Dandan; Li, Mengyu; Tang, Cong; Yan, Yunjun; Yu, Songlin; Chu, Qian; Xu, Yu

doi:10.4269/ajtmh.17-0029

Cited by 4 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We found only a few works that developed other techniques than logistic regression to predict multiresistant bacteria (CHANG et al, 2011;GOODMAN et al, 2019;LI;TANG;HE, 2016;SONG;JEONG, 2018;TAN et al, 2017). Goodman et al (2019) explored decision tree and logistic regression methods, finding similar results among these two.…”

Section: Comparing Related Workmentioning

confidence: 94%

“…The most common methods were wrapper algorithm (KAUR; KUMARI, 2018;LORETO;LISBOA;MOREIRA, 2020) and stepwise variable selection (GOODMAN et al, 2019;KIM;KIM;PARK, 2011;TAN et al, 2017). Li et al (2016) used only the automatic feature selection.…”

Section: Learning Methods In the Healthcare Contextmentioning

confidence: 99%

“…Logistic Regression (LR) (ALEXIOU et al, 2012;AN et al, 2017;CHAISATHAPHOL;CHAYAKULKEEREE, 2014;CHANG et al, 2011;DANTAS et al, 2019;DEBBY et al, 2012;FALCONE et al, 2018;FERREIRA et al, 2017;GOMILA et al, 2018;GOODMAN et al, 2019;HU et al, 2016;HUANG et al, 2012;JUNG et al, 2010;KENGKLA et al, 2016;KIDDEE et al, 2018;LEE et al, 2017;MARCHENAY et al, 2015;PARK et al, 2011;PATEL et al, 2014;PLAYFORD;CRAIG;IREDELL, 2007;ROMANELLI et al, 2009;ROUTSI et al, 2013;SCHWABER et al, 2008;SONG;JEONG, 2018;SURASARANG et al, 2007;TACCONELLI et al, 2008;TAN et al, 2017;TSENG et al, 2017;TUMBARELLO et al, 2011aTUMBARELLO et al, , 2011bVARDAKAS et al, 2015;VASUDEVAN et al, 2014;WILLMANN et al, 2014;YANG et al, 2016) Neural Network (NN) (CHANG et al, 2011 As shown in Table 2, most of the selected studies used the traditional application originating from logistic regression. Of the 35 papers, only five develope...…”

Section: Referencementioning

confidence: 99%

“…Besides, only four works used more than one method (CHANG et al, 2011;LI;TANG;HE, 2016;SONG;JEONG, 2018;TAN et al, 2017). It is possible to conclude a lack of studies that use efficient alternatives to traditional methods to predict multi-resistant acquisitions.…”

Section: Referencementioning

confidence: 99%

“…The severity of illness (DANTAS et al, 2019;DEBBY et al, 2012;PARK et al, 2011;TUMBARELLO et al, 2011a), and respiratory disease (DANTAS et al, 2019;JUNG et al, 2010;TAN et al, 2017) are also considered as risk factors. All the essential features can be seen in Table 4.…”

Section: Gram-negative Bacillimentioning

confidence: 99%

See 4 more Smart Citations

Predicting the Acquisition of Resistant Pathogens in Icus Using Machine Learning Techniques

DANTAS¹

View full text Add to dashboard Cite

show abstract

Section: Comparing Related Workmentioning

confidence: 94%

Section: Learning Methods In the Healthcare Contextmentioning

confidence: 99%

Section: Referencementioning

confidence: 99%

Section: Referencementioning

confidence: 99%

Section: Gram-negative Bacillimentioning

confidence: 99%

See 3 more Smart Citations

Predicting the Acquisition of Resistant Pathogens in Icus Using Machine Learning Techniques

DANTAS¹

View full text Add to dashboard Cite

show abstract

A simple prediction model of hyperuricemia for use in a rural setting

Shi¹,

Chen²,

Yang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Currently, the most widely used screening methods for hyperuricemia (HUA) involves invasive laboratory tests, which are lacking in many rural hospitals in China. This study explored the use of non-invasive physical examinations to construct a simple prediction model for HUA, in order to reduce the economic burden and invasive operations such as blood sampling, and provide some help for the health management of people in poor areas with backward medical resources. Data of 9252 adults from April to June 2017 in the Affiliated Hospital of Guilin Medical College were collected and divided randomly into a training set (n = 6364) and a validation set (n = 2888) at a ratio of 7:3. In the training set, non-invasive physical examination indicators of age, gender, body mass index (BMI) and prevalence of hypertension were included for logistic regression analysis, and a nomogram model was established. The classification and regression tree (CART) algorithm of the decision tree model was used to build a classification tree model. Receiver operating characteristic (ROC) curve, calibration curve and decision curve analyses (DCA) were used to test the distinction, accuracy and clinical applicability of the two models. The results showed age, gender, BMI and prevalence of hypertension were all related to the occurrence of HUA. The area under the ROC curve (AUC) of the nomogram model was 0.806 and 0.791 in training set and validation set, respectively. The AUC of the classification tree model was 0.802 and 0.794 in the two sets, respectively, but were not statistically different. The calibration curves and DCAs of the two models performed well on accuracy and clinical practicality, which suggested these models may be suitable to predict HUA for rural setting.

show abstract

Riwayat Pengobatan Tuberkulosis dan Penyakit Komorbid Sebagai Faktor Risiko Multi-Drugs Resistant Pasien Tuberkulosis Paru

Andi Fajri Rahmat,

Lelly Yuniarti,

Nugraha Sutadipura

2024

BCSMS

View full text Add to dashboard Cite

Abstract. Multidrug Resistant Tuberculosis (MDR-TB) is a type of tuberculosis that is resistant to at least two first-line antibiotics isoniazid (INH) and rifampicin (RMP) with or without resistance to other anti-tuberculosis drugs (OAT). This study aims to explore and analyze articles that discuss the history of tuberculosis treatment as a risk factor for multi-drug resistance in adult pulmonary tuberculosis patients. The research used literature studies between 2012-2022 from the Pubmed, Springer Link, ScienceDirect, Proquest, and Taylor and Francis databases. Based on the results of the analysis and discussion of the descriptions of the research articles reviewed, it can be concluded that a history of previous TB treatment is the main risk factor for increasing the incidence of MDR-TB. Abstrak. Multidrug Resistant Tuberculosis (MDR-TB) merupakan jenis tuberkulosis yang resisten terhadap setidaknya dua antibiotik lini pertama isoniazid (INH) dan rifampisin (RMP) dengan atau tanpa resistensi terhadap obat anti tuberkulosis (OAT) lain. Penelitian ini bertujuan untuk mengeksplorasi dan menganalisis artikel yang membahas riwayat pengobatan tuberkulosis sebagai faktor risiko terjadinya multi-drugs resistant pada pasien tuberkulosis paru dewasa. Penelitian menggunakan studi literatur antara tahun 2012-2022 dari database Pubmed, Springer Link, ScienceDirect, Proquest, dan Taylor and Francis. Berdasarkan hasil analisis dan pembahasan dari uraian artikel penelitian yang di-review dapat disimpulkan bahwa riwayat pengobatan TB sebelumnya menjadi faktor risiko utama dari meningkatnya kejadian MDR-TB.

show abstract

Identification of Risk Factors of Multidrug-Resistant Tuberculosis by using Classification Tree Method

Cited by 4 publications

References 31 publications

Predicting the Acquisition of Resistant Pathogens in Icus Using Machine Learning Techniques

Predicting the Acquisition of Resistant Pathogens in Icus Using Machine Learning Techniques

A simple prediction model of hyperuricemia for use in a rural setting

Riwayat Pengobatan Tuberkulosis dan Penyakit Komorbid Sebagai Faktor Risiko Multi-Drugs Resistant Pasien Tuberkulosis Paru

Contact Info

Product

Resources

About