Identification of significant risks in pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) approach

Nasir Mahmood, Saman Shahid, Taimur Bakhshi, Sehar Riaz, Hafiz Ghufran, Muhammad Yaqoob

Research output: Contribution to journalArticlepeer-review


Pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) technique was analyzed to determine the significance of clinical and phenotypic variables as well as environmental conditions that can identify the underlying causes of child ALL. Fifty pediatric patients (n = 50) included who were diagnosed with acute lymphoblastic leukemia (ALL) according to the inclusion and exclusion criteria. Clinical variables comprised of the blood biochemistry (CBC, LFTs, RFTs) results, and distribution of type of ALL, i.e., T ALL or B ALL. Phenotypic data included the age, sex of the child, and consanguinity, while environmental factors included the habitat, socioeconomic status, and access to filtered drinking water. Fifteen different features/attributes were collected for each case individually. To retrieve most useful discriminating attributes, four different supervised ML algorithms were used including classification and regression trees (CART), random forest (RM), gradient boosted machine (GM), and C5.0 decision tree algorithm. To determine the accuracy of the derived CART algorithm on future data, a ten-fold cross validation was performed on the present data set. The ALL was common in children of age below 5 years in male patients whole belonged to middle class family of rural areas. (B-ALL) was most frequent as compared with T-ALL. The consanguinity was present in 54% of cases. Low levels of platelets and hemoglobin and high levels of white blood cells were reported in child ALL patients. CART provided the best and complete fit for the entire data set yielding a 99.83% model fit accuracy, and a misclassification of 0.17% on the entire sample space, while C5.0 reported 98.6%, random forest 94.44%, and gradient boosted machine resulted in 95.61% fitting. The variable importance of each primary discriminating attribute is platelet 43%, hemoglobin 24%, white blood cells 4%, and sex of the child 4%. An overall accuracy of 87.4% was recorded for the classifier. Platelet count abnormality can be considered as a major factor in predicting pediatric ALL. The machine learning algorithms can be applied efficiently to provide details for the prognosis for better treatment outcome. [Figure not available: see fulltext.]
Original languageEnglish
Pages (from-to)2631-2640
Number of pages10
JournalMedical and Biological Engineering and Computing
Issue number11
Publication statusPublished - 1 Nov 2020
Externally publishedYes


  • Classification and regression trees (CART)
  • Environmental factors
  • Hemoglobin
  • Machine learning (ML)
  • Pediatric ALL
  • Platelets
  • alanine aminotransferase
  • alkaline phosphatase
  • aspartate aminotransferase
  • creatinine
  • drinking water
  • hemoglobin
  • uric acid
  • acute lymphoblastic leukemia
  • adult
  • alanine aminotransferase blood level
  • alkaline phosphatase blood level
  • article
  • aspartate aminotransferase blood level
  • blood biochemistry
  • cancer diagnosis
  • cancer prognosis
  • cancer risk
  • childhood leukemia
  • classification and regression trees
  • classifier
  • clinical article
  • consanguinity
  • controlled study
  • creatinine blood level
  • cross validation
  • decision tree
  • environmental exposure
  • environmental factor
  • female
  • gradient boosted machine
  • habitat
  • human
  • leukocyte count
  • machine learning
  • male
  • outcome assessment
  • platelet count
  • priority journal
  • random forest
  • rural area
  • social status
  • uric acid blood level


Dive into the research topics of 'Identification of significant risks in pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) approach'. Together they form a unique fingerprint.

Cite this