Predicting the probability of mortality of gastric cancer patients using decision tree

Mohammadzadeh, Fatemeh; Hoda, Noorkojuri; Pourhoseingholi, M. A.; Saadat, Siamak; Baghestani, Ahmad Reza

doi:10.1007/s11845-014-1100-9

Cited by 21 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the four decision tree methods available in SPSS, Chi-squared Automatic Interaction Detection (CHAID) and Classification and Regression Tree (CRT) stood out for highest accuracy and epidemiological plausibility of the structure. A reasonable strategy to construct the tree was adopted to get the optimal tree model [21][22][23][24][25][26][27]. Firstly, potential variables related to dependent variable in terms of temporal sequence, logic, and profession were selected out, all of which were set as independent variables to generate the tree as large as possible.…”

Section: Statistical Analysis and Model Parametermentioning

confidence: 99%

Management of imported malaria cases and healthcare institutions in central China, 2012–2017: application of decision tree analysis

Wang

Cao

et al. 2019

Malar J

View full text Add to dashboard Cite

Background: Imported malaria has been an important challenge for China. Fatality rates from malaria increased in China, particularly in Henan Province, primarily due to malpractice and misdiagnoses in healthcare institutions, and the level of imported malaria. This study aims to investigate the relationship between the state of diagnosis and subsequent complications among imported malaria cases at healthcare institutions, based on malaria surveillance data in Henan Province from 2012 to 2017. Methods: A retrospective descriptive analysis was performed using data from the Centre for Disease Control and Prevention, Zhengzhou City, the capital of Henan Province. A decision tree method was exploited to provide valuable insight into the correlation between imported malaria cases and healthcare institutions. Results: From 2012 to 2017, there were 371 imported malaria cases, mostly in males aged between 20 and 50 years, including 319 Plasmodium falciparum cases. First visits of 32.3%, 19.9% and 15.9% malaria cases for treatment were to provincial, municipal and county healthcare institutions, respectively. The time interval between onset and initial diagnosis of 284 cases (76.5%) and the time interval between initial diagnosis and final diagnosis of 197 cases (53.1%) was no more than 72 h. An apparent trend was found that there were notably fewer patients misdiagnosed at first visit to healthcare institutions of a higher administrative level; 12.5% of cases were misdiagnosed in provincial healthcare institutions compared to 98.2% in private clinics, leading to fewer complications at healthcare institutions of higher administrative level due to correct initial diagnosis. In the tree model, the rank of healthcare facilities for initial diagnosis, and number of days between onset and initial diagnosis, made a major contribution to the classification of initial diagnosis, which subsequently became the most significant factor influencing complications developed in the second tree model. The classification accuracy were 82.2 and 74.1%, respectively for the tree models of initial diagnosis and complications developed. Conclusion: Inadequate seeking medical care by imported malaria patients, and insufficient capacity to diagnose malaria by healthcare institutions of lower administrative level were identified as major factors influencing complications of imported malaria cases in Henan Province. The lack of connection between uncommon imported malaria

show abstract

Section: Statistical Analysis and Model Parametermentioning

confidence: 99%

Management of imported malaria cases and healthcare institutions in central China, 2012–2017: application of decision tree analysis

Wang

Cao

et al. 2019

Malar J

View full text Add to dashboard Cite

show abstract

“…Further, in many studies, it was unclear what outcome was being predicted. For example, authors mention ‘survival’ as an outcome[ 51 ], but it remained unclear whether overall survival or disease-specific survival was implied.…”

Section: Resultsmentioning

confidence: 99%

Prediction models for patients with esophageal or gastric cancer: A systematic review and meta-analysis

et al. 2018

View full text Add to dashboard Cite

BackgroundClinical prediction models are increasingly used to predict outcomes such as survival in cancer patients. The aim of this study was threefold. First, to perform a systematic review to identify available clinical prediction models for patients with esophageal and/or gastric cancer. Second, to evaluate sources of bias in the included studies. Third, to investigate the predictive performance of the prediction models using meta-analysis.MethodsMEDLINE, EMBASE, PsycINFO, CINAHL, and The Cochrane Library were searched for publications from the year 2000 onwards. Studies describing models predicting survival, adverse events and/or health-related quality of life (HRQoL) for esophageal or gastric cancer patients were included. Potential sources of bias were assessed and a meta-analysis, pooled per prediction model, was performed on the discriminative abilities (c-indices).ResultsA total of 61 studies were included (45 development and 16 validation studies), describing 47 prediction models. Most models predicted survival after a curative resection. Nearly 75% of the studies exhibited bias in at least 3 areas and model calibration was rarely reported. The meta-analysis showed that the averaged c-index of the models is fair (0.75) and ranges from 0.65 to 0.85.ConclusionMost available prediction models only focus on survival after a curative resection, which is only relevant to a limited patient population. Few models predicted adverse events after resection, and none focused on patient’s HRQoL, despite its relevance. Generally, the quality of reporting is poor and external model validation is limited. We conclude that there is a need for prediction models that better meet patients’ information needs, and provide information on both the benefits and harms of the various treatment options in terms of survival, adverse events and HRQoL.

show abstract

“…Other studies have used decision trees based on recursive partitioning techniques to predict prognosis in patients with cancer. 15 , 52 Radespiel-Tröger et al studied factors that predict recurrence of colon cancer after resection using tree-based methods. 53 Moreover, Manilich et al developed an RF prognostic model using clinical and histopathologic factors to predict 5-year survival of patients with colorectal cancer.…”

Section: Discussionmentioning

confidence: 99%

Combining statistical techniques to predict postsurgical risk of 1-year mortality for patients with colon cancer

Aróstegui¹,

González²,

Fernández-de-Larrea³

et al. 2018

CLEP

View full text Add to dashboard Cite

IntroductionColorectal cancer is one of the most frequently diagnosed malignancies and a common cause of cancer-related mortality. The aim of this study was to develop and validate a clinical predictive model for 1-year mortality among patients with colon cancer who survive for at least 30 days after surgery.MethodsPatients diagnosed with colon cancer who had surgery for the first time and who survived 30 days after the surgery were selected prospectively. The outcome was mortality within 1 year. Random forest, genetic algorithms and classification and regression trees were combined in order to identify the variables and partition points that optimally classify patients by risk of mortality. The resulting decision tree was categorized into four risk categories. Split-sample and bootstrap validation were performed. ClinicalTrials.gov Identifier: NCT02488161.ResultsA total of 1945 patients were enrolled in the study. The variables identified as the main predictors of 1-year mortality were presence of residual tumor, American Society of Anesthesiologists Physical Status Classification System risk score, pathologic tumor staging, Charlson Comorbidity Index, intraoperative complications, adjuvant chemotherapy and recurrence of tumor. The model was internally validated; area under the receiver operating characteristic curve (AUC) was 0.896 in the derivation sample and 0.835 in the validation sample. Risk categorization leads to AUC values of 0.875 and 0.832 in the derivation and validation samples, respectively. Optimal cut-off point of estimated risk had a sensitivity of 0.889 and a specificity of 0.758.ConclusionThe decision tree was a simple, interpretable, valid and accurate prediction rule of 1-year mortality among colon cancer patients who survived for at least 30 days after surgery.

show abstract

Predicting the probability of mortality of gastric cancer patients using decision tree

Cited by 21 publications

References 35 publications

Management of imported malaria cases and healthcare institutions in central China, 2012–2017: application of decision tree analysis

Management of imported malaria cases and healthcare institutions in central China, 2012–2017: application of decision tree analysis

Prediction models for patients with esophageal or gastric cancer: A systematic review and meta-analysis

Combining statistical techniques to predict postsurgical risk of 1-year mortality for patients with colon cancer

Contact Info

Product

Resources

About