A Study on C.5 Decision Tree Classification Algorithm for Risk Predictions During Pregnancy

Lakshmi, Baddireddi Subhadra; Indumathi, T. S.; Ravi, Nandini

doi:10.1016/j.protcy.2016.05.128

Cited by 69 publications

(26 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The detection of serum inflammatory markers is widely used in clinical practice, and the correlation between inflammatory markers and the severity and prognosis of patients with COPD is concerned. Some studies have shown that levels of inflammatory markers such as CRP and PCT are related to the severity of COPD patients and can guide the application of anti-infective therapy 24,25 .…”

mentioning

confidence: 99%

A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators

Peng

Chen

Zhou

et al. 2020

Sci Rep

View full text Add to dashboard Cite

patients with chronic obstructive pulmonary disease (copD) repeat acute exacerbations (Ae). Global initiative for chronic obstructive Lung Disease (GoLD) is only available for patients in stable phase. Currently, there is a lack of assessment and prediction methods for acute exacerbation of chronic obstructive pulmonary disease (AecopD) patients during hospitalization. to enhance the monitoring and treatment of AECOPD patients, we develop a novel C5.0 decision tree classifier to predict the prognosis of AecopD hospitalized patients with objective clinical indicators. the medical records of 410 hospitalized AECOPD patients are collected and 28 features including vital signs, medical history, comorbidities and various inflammatory indicators are selected. The overall accuracy of the proposed C5.0 decision tree classifier is 80.3% (65 out of 81 participants) with 95% Confidence Interval (CI):(0.6991, 0.8827) and Kappa 0.6054. In addition, the performance of the model constructed by C5.0 exceeds the C4.5, classification and regression tree (CART) model and the iterative dichotomiser 3 (ID3) model. The C5.0 decision tree classifier helps respiratory physicians to assess the severity of the patient early, thereby guiding the treatment strategy and improving the prognosis of patients. Chronic obstructive pulmonary disease (COPD) as a major cause of chronic morbidity and mortality is a global health threat, and will become the third leading cause of death in the world by 2030 1. In 2012, 3 million deaths caused by COPD, and the amount is equivalent to 6% of the total death that year 2. COPD is characterized by chronic bronchitis, chronic airway obstruction, and emphysema, which causes progressive, irreversible decline in lung function 3. COPD patients with acute exacerbation need to be admitted to the hospital with a mortality rate of approximately 10% 4. Inflammatory cells infiltrate the small airways, releasing destructive enzymes and inflammatory factors, leading to damage and remodeling of small airways 5. Neutrophils are the main inflammatory cells in patients with COPD, which release neutrophil elastase(NE) and myeloperoxidase(MPO) 6. Macrophages are another major inflammatory cell that produces TNF-α, IL-8,reactive oxygen species(ROS), and matrix metalloproteinases(MMP) 7. Eosinophils and lymphocytes are also widely present in the airways of patients with COPD, but their mechanisms of damage to the airways are still controversial 8. However, early intervention on these patients with COPD can reduce morbidity and mortality 9,10. The socioeconomic burden caused by the deterioration of COPD cannot be underestimated 11. Global Initiative for Chronic Obstructive Lung Disease (GOLD) has been employed to classify the severity of COPD patients since 2011 12. However, GOLD is unable to fully guide the clinical treatment of COPD patients due to the complexity of the progression of COPD, exacerbation recovery time, risk of re-admission and intensive care unit (ICU) admission 13-15. In order to accurately classify the severit...

show abstract

mentioning

confidence: 99%

A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators

Peng

Chen

Zhou

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Klasifikasi akan dilakukan dengan menggunakan algoritma pohon keputusan C4.5. Algoritma ini dinilai dapat menangani klasifikasi multi-class dengan baik [7]. Algoritma ini juga merupakan algoritma yang banyak digunakan dalam berbagai bidang penelitian karena model klasifikasi yang dihasilkannya mudah dipahami dan memiliki performa yang lebih baik dibandingkan algoritma pohon keputusan lainnya yaitu ID3 dan C5.0 [8].…”

Section: Pendahuluanunclassified

Klasifikasi Produk Retur dengan Algoritma Pohon Keputusan C4.5

Arifiyanti

Pradana²,

Novian³

2018

Media Komunikasi Teknologi

View full text Add to dashboard Cite

Pengembalian produk oleh konsumen kepada penjual bukan hal yang dapat dihindari. Aktivitas ini tidak terlihat merugikan pada awalnya, namun pengelolaan informasi dari pengembalian produk dapat memberikan informasi yang bermanfaat bagi penjual untuk digunakan dalam proses evaluasi. Salah satu cara pengelolaan informasi ini adalah dengan melakukan klasifikasi dari jenis produk yang dikembalikan oleh konsumen dan alasan-alasan yang menjadikan produk tersebut dikembalikan. Pada penelitian ini produk retur dimasukkan dalam tiga klasifikasi yaitu kuat, sedang, dan lemah. Hasil klasifikasi tersebut dapat menjadi evaluasi pada proses produksi hingga pengemasan dan pengiriman produk. Algoritma pohon keputusan C4.5 dipilih dalam penelitian ini karena algoritma ini dapat menangani multi-class, memiliki performa yang baik dalam klasifikasi, dan model klasifikasi yang dihasilkannya mudah dipahami. Pembagian data latih dan data uji dilakukan dengan menggunakan metode cross-validation 10 folds karena jumlah data yang terbatas. Model klasifikasi yang dihasilkan pada penelitian ini memiliki performa akurasi sebesar 95,6%, precision sebesar 0,943, dan recall sebesar 0,956. PENDAHULUANSalah satu tantangan bagi para pelaku bisnis di bidang manufaktur adalah adanya pengembalian produk yang dilakukan oleh konsumen. Pengembalian produk terjadi karena konsumen tidak merasa puas terhadap produk yang telah dibeli. Ketidakpuasan ini muncul dikarenakan berbagai alasan misalnya produk yang dibeli cacat, tidak sesuai harapan, dan alasan lainnya. Barang yang telah dikembalikan tersebut dapat digantikan dengan produk yang baru (exchange), pengembalian uang (refund), dan diberikannya jasa tambahan [1]. Pengembalian produk merupakan salah satu aktivitas yang bernilai tambah rendah bagi

show abstract

“…Indumathi.T.S, et al [6] Reducing the mortalities or complications arising in period of gestation.use C4.5 decision tree classification method main goal of compare the results obtained from C4.5 classifier on both un-standardized and standardized dataset and analyse the performance of the C4.5 algorithm in terms of its prediction accuracy when applied on the created database from collected and standardized pregnancy data. As The accuracy percentage for unstandardized dataset and standardized dataset accounts to 66.087% and 71.3043% respectively and error percentages are 33.913% and 28.6957% respectively.…”

Section: Related Workmentioning

confidence: 99%

“…These underweight babies are at risk of several early life complications such as ashypothermia, low blood-sugar, feeding difficulties and viral infections. Aim of proposed system is analyse and predict risk during pregnancy physiological parameters like blood pressure, blood glucose level and weight whose changes during pregnancy can lead to complications can be identified and further complications induced from these changes can be prevented [6].…”

Section: Introductionmentioning

confidence: 99%

Women Health Monitoring: A Survey

Shegokar¹,

Paswan²

2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:In medical area, various problem exist but gestation stage serious problem regarding women. Women undergo several physiological parameter changes which cause major problem. When we neglect such problem may result in complications or mortality of mother and fetus, so we need to protect pregnant women. In this paper we have discussed a few approaches for find risk during pregnancy and information regarding health care.

show abstract

A Study on C.5 Decision Tree Classification Algorithm for Risk Predictions During Pregnancy

Cited by 69 publications

References 1 publication

A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators

A Machine-learning Approach to Forecast Aggravation Risk in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease with Clinical Indicators

Klasifikasi Produk Retur dengan Algoritma Pohon Keputusan C4.5

Women Health Monitoring: A Survey

Contact Info

Product

Resources

About