Advanced analytics is being widely used in the field of health. Studying genetic factors, environmental influences, and physiological data allows practitioners to prevent, diagnose, and treat diseases more effectively to improve welfare. Artelnics uses artificial intelligence to analyze clinical data to take up new models of care and new technologies promoting health and wellbeing.

Some of these solutions that we offer are described below:

  1. Medical diagnosis.
  2. Medical prognosis.
  3. Microarray analysis.
  4. Protein design.

1. Medical diagnosis

Diagnosis picture

Medical science is moving fast through the application of advanced analytics technologies. But many challenges still need to be faced, such as determining the causes of complex diseases.

Artelnics can help you find new ways to prevent diseases and develop better diagnostics and more effective therapies. To do that, we use artificial intelligence to analyze clinical data. Some applications are described below:




Breast cancer hazard assessment
The goal is to predict if a patient could have a recurrence of cancer or not. The source of information is a data set provided by an Oncology Department, which contains relevant attributes of cancer patients. They include age, menopause, tumor size, number of invasive nodes, etc.

Diagnosing heart disease
The objective of this study is to diagnose the heart problems of patients by using medical data. Some attributes here are age, sex, smoke, exercise, resting blood pressure, serum cholesterol, etc.

2. Medical prognosis

Prognosis picture

Prognosis is the hypothesis regarding the development of a disease. Advances in medical technology will allow us to anticipate the patient's symptoms, estimate the chances of recovery, and know what the recovery period is.

Advanced analysis of patients' data allows doctors to perform more accurate forecasts of diseases. These forecasts could keep older people active and independent longer and help health and care systems remain sustainable. Some uses are:




Early prognostic in patients with liver disorders.
This study aims to evaluate a liver disorder in its early stages to treat the disease before it becomes dangerous. Design an algorithm using advanced analytics techniques that can split data into two sets through different blood test variables and the number of half-pints of alcohol consumed during the day. The output variable is the selector (field used to split data into two sets).

3. Microarray Analysis

Microarray picture

A microarray is typically a glass slide on to which DNA molecules are fixed in an orderly manner at specific locations called spots (or features).

Microarray analysis represents a wonderful opportunity for clinical research. Significant results here include identifying gene sets associated with a specific disease or predicting treatment responses. Some of the solutions are:




Ovarian cancer risk assessment
The study of ovarian cancer is significant to women as it can minimize the risk of suffering it. The goal of this experiment is to identify proteomic patterns in serum that distinguish ovarian cancer from non-cancer.

Colon cancer prediction by using gene expression
Colon cancer is one of the most common cancers that people suffer. Survival is directly related to early detection. The goal of this example is to detect colon cancer at an early stage. The samples from a colon dataset were taken from colon adenocarcinoma specimens snap-frozen in liquid nitrogen within 20 minutes of removal from patients. The microarray dataset consists of 22 regular and 40 tumor tissue samples.

4. Protein Design

Protein picture

Protein design has proven to be very useful for discovering new molecules that fold to a target structure. Computer simulations can design proteins from scratch or by making calculated variations on a known item.

Advanced analytics is being widely used to design very complex QSAR and QSPR models with improved accuracy. Some of the applications for protein design are:




Protein structure prediction
The structural alignment is a type of sequence alignment comparison based on the shape. These alignments try to establish equivalences between two or more polymer structures based on their shape and three-dimensional conformation. This study aims to predict the similarity between the partially folded protein structure and the native state structure.