Scribd
Upload
825 views11 pages

Project Title: A Machine Learning Methodology For Diagnosing Chronic Kidney Disease

1) The document proposes a machine learning methodology using random forest classification to diagnose chronic kidney disease. 2) It evaluates various machine learning algorithms on a public kidney disease dataset and finds random forest achieves the highest accuracy of 100% for identifying chronic kidney disease subjects. 3) The proposed approach investigates using machine learning techniques like logistic regression, decision trees, and random forests to systematically and automatically diagnose chronic kidney disease based on clinical data.

Uploaded by

fdfdfdfd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
825 views11 pages

Project Title: A Machine Learning Methodology For Diagnosing Chronic Kidney Disease

1) The document proposes a machine learning methodology using random forest classification to diagnose chronic kidney disease. 2) It evaluates various machine learning algorithms on a public kidney disease dataset and finds random forest achieves the highest accuracy of 100% for identifying chronic kidney disease subjects. 3) The proposed approach investigates using machine learning techniques like logistic regression, decision trees, and random forests to systematically and automatically diagnose chronic kidney disease based on clinical data.

Uploaded by

fdfdfdfd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

PROJECT TITLE

A MACHINE LEARNING METHODOLOGY FOR


DIAGNOSING CHRONIC KIDNEY DISEASE
PROBLEM STATEMENT

• The existing system predicts the chronic diseases which are for a particular region and for the
particular community. Only particular diseases are predicted by this system.
• In this System, Big Data & CNN Algorithm is used for Disease risk prediction. For S type
data, the system is using Machine Learning algorithm i.e K-nearest Neighbors, Decision Tree,
Naïve Bayesian.
• The accuracy of the existing System is up to 94.8%.
• It has gotten another sort of clinical instrument with the improvement of data innovation
what's more, has an expansive application prospect in view of the fast improvement of
electronic wellbeing record.
• In the clinical field, has just been utilized to detect human body status break down the
significant components of the infection and analyze different sicknesses.
EXISTING SYSTEM

• In the existing work, they streamline machine learning


algorithms for the effective prediction of chronic disease
outbreak in disease-frequent communities. They experiment
with the modified prediction models over real-life hospital
data collected from central China.
• They propose a convolutional neural network-based
multimodal disease risk prediction (CNN-MDRP) algorithm
using structured and unstructured data from the hospital.
METHODOLOGY

• They used picture enrollment to recognize renal morphologic changes and set up a classifier dependent on

neural organization utilizing enormous scope CKD information, and the exactness of the model on their test

information.

• Moreover, the majority of the past examines used the CKD informational index that was acquired from the

UCI AI store.

• They utilized k-closest neighbor (KNN), uphold vector machine and delicate autonomous displaying of

class relationship to analyze KNN and Logistic regression, Decision tree, Random forest system for

diagnosing CKD accomplished the most elevated exactness of 100% Chronic kidney disease (CKD) is a

global public health problem, affecting approximately 10% of the population worldwide.

• Yet, there is little direct evidence on how CKD can be diagnosed in a systematic and automatic manner.
ARCHITECTURE DIAGRAM
PROPOSED WORK
• This work investigates how CKD can be diagnosed by using machine learning (ML) techniques. ML algorithms have
been a driving force in detection of abnormalities in different physiological data, and are, with a great success,
employed in different classification tasks.
• In the present study, a number of different ML classifiers are experimentally validated to a real data set, taken from the
UCI Machine Learning Repository, and our findings are compared with the findings reported in the recent literature.
• The results are quantitatively and qualitatively discussed and our findings reveal that the random forest (RF) classifier
achieves the near-optimal performances on the identification of CKD subjects.
• Hence, we show that ML algorithms serve important function in diagnosis of CKD, with satisfactory robustness, and
our findings suggest that RF can also be utilized for the diagnosis of similar diseases.Their examinations have
accomplished great outcomes in the finding of CKD.
• In the above models, the mean ascription is utilized to fill in the missing qualities and it relies upon the demonstrative
classifications of the examples. Therefore, their technique couldn't be utilized at the point when the demonstrative
consequences of the examples are obscure. In reality, patients may miss a few estimations for different reasons prior to
diagnosing.
ALGORITHM

• To analyze KNN and Logistic regression, Decision tree, Random forest


system for diagnosing CKD accomplished the most elevated exactness of
100% Chronic kidney disease (CKD) is a global public health problem,
affecting approximately 10% of the population worldwide. Yet, there is
little direct evidence on how CKD can be diagnosed in a systematic and
automatic manner.
• The results are quantitatively and qualitatively discussed and our findings
reveal that the random forest (RF) classifier achieves the near-optimal
performances on the identification of CKD subjects
LIST OF MODULES

• DATA PROCESSING

• EXTRACTING FEATURE SELECTION


• PERFORMANCE INDICATORS

• ESTABLISHING AND EVALUATING INDIVIDUAL MODELS


• MISJUDGMENT ANALYSIS AND SELECTING COMPONENT
MODELS
DATASET USED

• Kaggle dataset
METRICS CONSIDERED FOR EVALUATION

Classifier Class Precision F- Accuracy (%)


Measure

LR CKD 0.996 0.988 98

No-CKD 0.968 0.980 99.3

Weighted Average 0.985 0.985 98.5

K-NN CKD 1.000 0.965 93.2

No-CKD 0.898 0.946 100

Weighted Average 0.962 0.958 95.75

DECISION TREE CKD 0.988 0.992 99.6

No-CKD 0.993 0.987 98

Weighted Average 0.990 0.990 99

RANDOM FOREST CKD 1 1 100

No-CKD 1 1 100

Weighted Average 1 1 100


REFERENCES

• M. M. Hossain et al., “Mechanical anisotropy assessment in kidney cortex using ARFI peak
displacement: Preclinical validation and pilot in vivo clinical results in kidney allografts,” IEEE
Trans. Ultrason. Ferr., vol. 66, no. 3, pp. 551-562, Mar. 2019.

• E. Hodneland et al., “In vivo detection of chronic kidney disease using tissue deformation fields
from dynamic MR imaging,” IEEE Trans. BioMed. Eng., vol. 66, no. 6, pp. 1779-1790, Jun. 2019.

• G. R. Vasquez-Morales et al., “Explainable prediction of chronic renal disease in the colombian


population using neural networks and case-based reasoning,” IEEE Access, vol. 7, pp. 152900-
152910, Oct. 2019.

• N. Almansour et al., “Neural network and support vector machine for the prediction of chronic
kidney disease: A comparative study,” Comput. Biol. Med., vol. 109, pp. 101-111, Jun. 2019

• M. Alloghani et al., “Applications of machine learning techniques for software engineering learning
and early prediction of students’ performance,” in Proc. Int. Conf. Soft Computing in Data Science,
Dec. 2018, pp. 246- 258.

You might also like