Breast cancer prediction

Breast cancer prediction

How can we improve breast cancer prediction thanks to machine learning?

One of the main Machine Learning application in healthcare is the identification and diagnosis of diseases which are considered hard-to-diagnose. This includes anything from cancers, which are tough to diagnose during the initial stage, to many genetic diseases.

Problem to solve

  • Is it possible to predict if a patient is likely to have breast cancer?
  • Can we evaluate a cancer risk from the characteristics based on the cell nuclei characteristics extracted from a breast mass?
  • Can we help doctors be more performant in their diagnoses? Can we provide them with a ‘second opinion’ in minutes?
  • Can machine learning help in these matters and how accurate predictive models can be to make cancer prediction?
  • Benefits of TADA
    in breast cancer prediction

    Doctors, oncologists and medical staffs can use predictive models to help them in their diagnoses. However, they are not data scientists and they may not have the required skills in machine learning or the coding experience to build models. Most data handled by these professionals are small data, meaning that their historical data is related to a few hundred patients and not definitely millions (Big data). Typically, as soon as there is a suspicion due to a breast mass being detected, a fine needle aspirate is performed (FNA). The cell nuclei extracted are measured in radius, volume, texture and perimeter. Traditional machine learning tools work well with Big Data but do not perform well with these Small Data

    MyDataModels allows domain experts, in this case doctors, oncologists and researchers, to automatically build predictive models out of their collected Data. No training is required, and they can use their collected data directly without the need to normalize them nor to handle outliers. No feature engineering is required. Thanks to this simple data preparation, we obtained results from this specific dataset in a few clicks and in less than a minute, from a regular laptop.

    MyDataModels brings a self-service solution for those who have Small Data and no data scientists.

    TADA brings new possibilities for healthcare professionals

    Breast cancer is the most common cancer among women, accounting for 25% of all cancer cases worldwide. It affects 2.1 million people yearly. Early diagnoses significantly increases the chances of survival. However, research indicates that most experienced physicians can diagnose cancer with 79% accuracy, while 91% correct diagnosis is achieved using generic machine learning techniques.

    “Predictive model reached an 97% accuracy rate”

    In this breast cancer prediction use case, the results obtained from MyDataModels’ predictive models reach a 97% accuracy rate. The medical world could make more use of machine learning to detect diseases in general, and breast cancer in particular. This would allow doctors to save precious patient dedicated time and to get a “second opinion” about a cancer risk in a few clicks.