The ability of Machine Learning tools to detect critical features from complex datasets reveals their importance in cancer diagnosis.

The components of early detection of cancer are early diagnosis and screening. Early diagnosis focuses on detecting symptomatic patients as early as possible while screening tests healthy individuals to identify those having cancers before symptoms appear.

The cancer type’s early diagnosis and prognosis have become necessary in cancer research. Indeed, it can facilitate the subsequent clinical management of patients.

Here are some examples of cancer diagnosis solved using Neural Designer. Download the free trial to follow them step by step.

Pancreatic cancer diagnosis

This example is about a non-invasive way to diagnose pancreatic cancer, the urinary biomarkers. The most commonly used was plasma, an invasive blood biomarker a few years back. Although combining these two methods improves the model’s accuracy in a pancreatic cancer diagnosis.

In this example, we divide our main dataset into four subsets. Each allows to study whether a patient is healthy, has a benign tumour, or pancreatic cancer stages I, II, III, or IV.
Read more.

Lung cancer

The main goal of this study is to build a model which provides a lung cancer risk assessment and decision support tool to facilitate prevention and screening discussions between people and their doctors. This task will be satisfied through a questionnaire with different questions about cancer risk factors and pathologies.
Read more

Breast cancer diagnosis

This example aims to diagnose whether a lump in a breast could be malignant (cancerous) or benign (non-cancerous).
We use imaging parameters from digitized images of a fine-needle aspiration biopsy to build the classification model.
Read more.

Leukemia microarray analysis

This example aims to diagnose the leukaemia of patients and differentiate between Acute Lymphoblastic Leukemia (ALL) or Acute Myeloid Leukemia (AML), depending on their DNA coding.
Read more.

Colon cancer treatment

This example examines data from an RCT, measuring the effect of a particular drug combination on colon cancer.
Specifically, we are looking at the effect of Levamisole and Fluorouracil on patients who have had surgery to remove their colon cancer. After surgery, the evolution of the patient depends on the remaining residual cancer. This study shows which drug combination had a beneficial effect, Chemotherapy or Levamisole and Fluorouracil.
Read more.

Cervical cancer prognosis

This study aims to create a prognostic model based on Artificial Neural Networks that focuses on the initial screening stages.
Read more.

Lung cancer recurrence

This example assesses the probability of suffering a relapse in lung cancer patients. We use expression data from 335 patients with eighteen thousand genes and some phenotypic variables.
Read more.

Breast cancer mortality prediction

This example predicts the mortality of breast cancer patients over five years. We use different data types, including clinical and treatment variables, an expression, and a mutation panel.
Read more.

Colorectal cancer

This example assesses the risk of a patient with colorectal cancer of developing liver metastasis. We use mutational data from 492 genes and phenotypic variables using machine learning.
Read more.

Related posts

No related posts.