POWER BI – ACROMEGALY – IGF ANALYSIS

Abstract

Acromegaly is a pituitary tumour that produces high levels of growth hormone. This research is to understand and analyze how high the IGF levels could rise. If there is any resistance to insulin and blood glucose levels, and whether patients’ physical appearance and physical characteristics change when affected by Acromegaly? The data set is acquired from opensource. The dataset is evaluated and preprocessed to build the appropriate data model. The transformed data model is then used to draw solutions for the mentioned business questions. This analysis states that Acromegaly causes a rise in IGF levels, higher insulin resistance, higher glucocorticoid levels and does not have significant changes concerning BMI, Age, and height. Except there was a marginal increase observed in height and BMI.

Introduction

Human beings are one of the most fantastic creatures in the world. Every single organ and single cell are essential for human survival. Among the parts of the human body, the pituitary is a tiny gland located behind the bridges of the nose attached to the human brain’s base. Though the gland’s size is small, it is still known as the master gland because it controls all the hormones produced in the human body.

  • The problems caused by the pituitary gland are broadly categorized into three types:
  • The conditions that alter the size or shape of the gland itself called empty Sella syndrome.
  • The conditions which make the pituitary secrete hormone in lower levels than that are required. These are hypopituitarism and diabetes insipidus.

The conditions that cause the pituitary to secrete hormones much more than required like Acromegaly, Cushing’s and prolactinoma.

In this thesis, we are interested in Acromegaly, which is a rare pituitary tumour and secretes too much growth hormone GH in the body. A tumour less than 1cm is called microadenoma, and > 1 cm known as pituitary macroadenoma. They develop DNA mutations and makes cells grow and divide rapidly. Acromegaly may also result in shortening the life expectancy of the patient. Scientists estimate that about 3 to 14 of every 100,000 people have been diagnosed with Acromegaly. Any research and analysis would be helpful in the medical field, which is snowballing. The DNA, transcript sequence counts, and patient-related data are enormous and complex to analyze or visualize using traditional algorithms and methods. Power BI would work wonders for the same purposes.

Purpose of Research

Knowing extraordinarily little about Acromegaly, my curiosity to understand the disease and its rarity by analyzing it in-depth encouraged me in choosing this dataset. During the current research, I intend to learn the complete process of data analysis and apply these skills systematically to find the required information from the huge data available in real-time scenarios.

Intended Findings in Study

We analyze the processed data to determine any significant physical differences between acromegaly patients and Control patients. Also, determine if the patient’s age factor plays any role in the medical condition. We also study the effects of IGF (IGF1, IGF2) and insulin (blood glucose levels) levels in both patient categories.

Data Model

This secondary research dataset contains the details gathered from 9 Acromegaly patients and 11 control patients. The gene sequences are generated and analyzed. The data model is a snowflake schema with a factless fact table, as shown in the picture below.

Data Model – Snowflake Schema

Key Findings

Growth hormone stimulates cell reproduction, cell regeneration and is also responsible for growth in the body.  The pituitary gland releases IGF1, and growth results from circulating this IGF1 in the body in deeper terms. Below are the plots between IGF components and the sequence counts.

From these plots, it is evident that the IGF levels have a rapid increase in the IGF levels. IGF complex functions show an enormous increase in IGFBP5, IGFBP3, and IGF. The donut plot shows the percentage increase, which is almost 3.5 times higher than the controls.

Conclusions

The following observations and conclusions have been made from the research.

  1. The average IGF1 levels are 3.5 times higher in Acromegaly patients.
  2. Acromegaly patients have higher insulin resistance and low levels of insulin sensitivity.
  3. Acromegaly patients tend to show higher averages for BMI and height.
  4. The probability of Acromegaly might increase with age. Since the analyzed data is a smaller sample, this may not be true for more significant models and real-time scenarios.
  5. Weight and Abdominal circumferences do not tend to change in considerable amounts, according to the research dataset.
Skip to content
%d bloggers like this: