Yazar "Awan, Fahim Gohar" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    Survivability Period Prediction in Colon Cancer Patients using Machine Learning
    (Institute of Electrical and Electronics Engineers Inc., 2023) Tahir, Anoosha; Wajid, Bilal; Anwar, Faria; Awan, Fahim Gohar; Rashid, Umar; Afzal, Fareeha; Anwar, Abdul Rauf; Wajid, Imran
    Knowledge of survivability is crucial for cancer patients and their families. This paper employs the Surveillance, Epidemiology, and End Results (SEER) database to predict the survivability of colon cancer patients. The research presents four experiments each improving over the previous one, attempting to develop the optimal model. Here (i) experiment 1 conducts regression analyses; (ii) experiment 2 conducts multinomial classification; (iii) experiment 3 emphasizes a multi-tier prediction framework and lastly; (iv) experiment 4 concludes by developing a hybrid model for better prediction of survivability.
  • Küçük Resim
    Öğe
    Survival Rate Prediction of Blood Cancer (Leukemia) Patients Using Machine Learning Algorithms
    (Institute of Electrical and Electronics Engineers Inc., 2022) Zarish; Wajid, Bilal; Rashid, Umar; Zahid, Sajida; Anwar, Faria; Awan, Fahim Gohar; Anwar, Abdul Rauf; Wajid, Imran
    Survival rate prediction for medical diseases is a complex task that requires high precision. With a low survival rate among reported patients, leukemia is a type of cancer of blood which is caused by the abnormal growth of white blood cells. It is critical to numerically evaluate the rate of survivability of patients suffering from leukemia. To this end, this paper employs a comprehensive database, namely Surveillance, Epidemiology, and End Results (SEER) maintained by The National Cancer Institute in MD, USA, to construct a survivability model for leukemia patients. To accurately predict the survival months of the patients, we develop a multi-class classification problem by binning the target variable into four bins. The resulting accuracy is improved by utilizing a multi-tier classification framework. Although, the final numerical results hold significance from biological viewpoint, it is recommended that a clinically relevant model be drawn with caution.
  • Küçük Resim Yok
    Öğe
    Unearthing Insights into Metabolic Syndrome by Linking Drugs, Targets, and Gene Expressions Using Similarity Measures and Graph Theory
    (Bentham Science Publishers, 2024) Zafar, Alwaz; Wajid, Bilal; Shabbir, Ans; Awan, Fahim Gohar; Ahsan, Momina; Ahmad, Sarfraz; Wajid, Imran; Anwar, Faria; Mazhar, Fazeelat
    Aims and Objectives: Metabolic syndrome (MetS) is a group of metabolic disorders that includes obesity in combination with at least any two of the following conditions, i.e., insulin resistance, high blood pressure, low HDL cholesterol, and high triglycerides level. Treatment of this syndrome is challenging because of the multiple interlinked factors that lead to increased risks of type-2 diabetes and cardiovascular diseases. This study aims to conduct extensive insilico analysis to (i) find central genes that play a pivotal role in MetS and (ii) propose suitable drugs for therapy. Our objective is to first create a drug-disease network and then identify novel genes in the drug-disease network with strong associations to drug targets, which can help in increasing the therapeutical effects of different drugs. In the future, these novel genes can be used to calculate drug synergy and propose new drugs for the effective treatment of MetS. Methods: For this purpose, we (i) investigated associated drugs and pathways for MetS, (ii) employed eight different similarity measures to construct eight gene regulatory networks, (iii) chose an optimal network, where a maximum number of drug targets were central, (iv) determined central genes exhibiting strong associations with these drug targets and associated disease-causing pathways, and lastly (v) employed these candidate genes to propose suitable drugs. Results: Our results indicated (i) a novel drug-disease network complex, with (ii) novel genes associated with MetS. Conclusion: Our developed drug-disease network complex closely represents MetS with associated novel findings and markers for an improved understanding of the disease and suggested therapy.