Alzheimer's Disease Machine Learning Project Proposal

import pandas as pd


# data file
df_alzheimers = pd.read_csv('alzheimers.csv')
df_alzheimers.head()

	Group	M/F	Age	EDUC	SES	MMSE	CDR	eTIV	nWBV	ASF
0	Nondemented	M	87	14	2.0	27.0	0.0	1987	0.696	0.883
1	Nondemented	M	88	14	2.0	30.0	0.0	2004	0.681	0.876
2	Demented	M	75	12	NaN	23.0	0.5	1678	0.736	1.046
3	Demented	M	76	12	NaN	28.0	0.5	1738	0.713	1.010
4	Demented	M	80	12	NaN	22.0	0.5	1698	0.701	1.034

Features:

- Group: whether the individual has exhibits symptoms of dementia
- M/F: sex of individual
- Age: age of individual
- EDUC: years of education the individual has undergone
- SES: socioeconomic status of the individual on a scale of 1 to 5 (with 1 being the most wealthy)
- MMSE: mini mental state evaluation
- CDR: clinical dementia rating
- eTIV: estimated intracranial volume in mL. Total volume of the individual's brain
- nWBV: normalize whole brain volume
- Atlas scaling factor

Motivation:

Current treatments for alheimer's disease can only temporarily slow its progression. Thus, the sooner the disease can be detected and diagnosed, the sooner treatments can be applied before irreversible damage has been done to afford patients the longest time with the highest quality of life possible. Machine learning may be able to improve the detection of alzhiemer's disease and could imporve the lives of millioins with the disease. Furthermore, analyzing the relationships between certian factors and the incidence of alzheimer's disease could provide insight into where to begin searching for preventative measures.

Method:

The goal is to cluster individuals based on whether the exhibit symptoms of dementia to identify characteristics that may aid in the diagnosis of alzheimer's disease.