https://github.com/abhishekmali21/liver-patient-analysis
This project aims to reduce the time delay caused due to the unnecessary back and forth shuttling between the hospital and the pathology lab. Here a machine learning algorithm will be trained to predict a liver disease in patients using a data-set collected from North East of Andhra Pradesh, India.
https://github.com/abhishekmali21/liver-patient-analysis
dataset ibm-bluemix ibm-watson liver-disease liver-patient liver-patient-analysis machine-learning-algorithm ml-project node-red node-red-project
Last synced: 2 months ago
JSON representation
This project aims to reduce the time delay caused due to the unnecessary back and forth shuttling between the hospital and the pathology lab. Here a machine learning algorithm will be trained to predict a liver disease in patients using a data-set collected from North East of Andhra Pradesh, India.
- Host: GitHub
- URL: https://github.com/abhishekmali21/liver-patient-analysis
- Owner: AbhishekMali21
- License: mit
- Created: 2019-07-20T15:04:53.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2020-03-29T13:43:00.000Z (about 5 years ago)
- Last Synced: 2025-03-26T16:12:00.284Z (3 months ago)
- Topics: dataset, ibm-bluemix, ibm-watson, liver-disease, liver-patient, liver-patient-analysis, machine-learning-algorithm, ml-project, node-red, node-red-project
- Language: Jupyter Notebook
- Homepage:
- Size: 3.65 MB
- Stars: 10
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LIVER-PATIENT-ANALYSIS
[](https://www.linkedin.com/in/abhishekmali/)
[](https://github.com/AbhishekMali21?tab=followers)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/watchers)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/stargazers)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/network/members)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/issues?q=is%3Aopen+is%3Aissue)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/issues?q=is%3Aissue+is%3Aclosed)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/pulls?q=is%3Aopen+is%3Apr)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/pulls?q=is%3Apr+is%3Aclosed)
[](https://github.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS/blob/master/LICENSE)
[](http://hits.dwyl.com/AbhishekMali21/LIVER-PATIENT-ANALYSIS)
### Objectives of Research
In India, delayed diagnosis of diseases is a fundamental problem due to a shortage of medical
professionals. A typical scenario, prevalent mostly in rural and somewhat in urban areas is:
1. A patient going to a doctor with certain symptoms.
2. The doctor recommending certain tests like blood test, urine test etc depending on the
symptoms.
3. The patient taking the aforementioned tests in an analysis lab.
4. The patient taking the reports back to the reports back to the hospital, where they are
examined and the disease is identified.
This project aims to reduce the time delay caused due to the unnecessary back and forth shuttling between the hospital and the pathology lab. Here a machine learning algorithm will be trained to predict a liver disease in patients using a data-set collected from North East of Andhra Pradesh, India.
### Problem Statement
The problem statement is formally defined as:
‘Given a dataset containing various attributes of 584 Indian patients, use the features
available in the dataset and define a supervised classification algorithm which can identify
whether a person is suffering from liver disease or not. This data set contains 416 liver patient
records and 167 non- liver patient records.The data set was collected from north east of Andhra
Pradesh, India. This data set contains 441 male patient records and 142 female patient records.
Any patient whose age exceeded 89 is listed as being of age "90"
### Team Members
- [@AbhishekMali21](https://github.com/abhishekmali21) - **Abhishek Mali** (Project Head)
- [@AdityaSindol](https://github.com/AdityaSindol) - **Aditya Sindol**
- [@KeshavPola](https://github.com/keshavpola) - **Keshav Pola**
- [@KaranDange](https://github.com/KaranDange) - **Karan Dange**
- [@Veereshsg](https://github.com/Veereshsg) - **Veeresh Gobbur**
### Context
Patients with Liver disease have been continuously increasing because of excessive
consumption of alcohol, inhale of harmful gases, intake of contaminated food, pickles and
drugs. This dataset was used to evaluate prediction algorithms in an effort to reduce burden on
doctors.
### Content
This data set contains 416 liver patient records and 167 non liver patient records
collected from North East of Andhra Pradesh, India. The "Dataset" column is a class label used
to divide groups into liver patient (liver disease) or not (no disease). This data set contains 441
male patient records and 142 female patient records. Any patient whose age exceeded 89 is
listed as being of age "90".
### Columns:
* Age of the patient
* Gender of the patient
* Total Bilirubin
* Direct Bilirubin
* Alkaline Phosphotase
* Alamine Aminotransferase
* Aspartate Aminotransferase
* Total Protiens
* Albumin
* Albumin and Globulin Ratio
* Dataset: field used to split the data into two sets (patient with liver disease, or no disease)
### Screenshots
👉 **Node Red Flow**
👉 **ML Model UI**
### Conclusion
Initially, the dataset was explored and made ready to be fed into the classifiers. This
was achieved by removing some rows containing null values, transforming some columns
which were showing skewness and using appropriate methods (Label Encoding) to convert
the labels so that they can be useful for classification purposes. Performance metrics on which
the models would be evaluated were decided. The dataset was then split into a training and
testing set.
Firstly, a naive predictor and a benchmark model ('Logistic Regression') were run on
the dataset to determine the benchmark value of accuracy. The greatest difficulty in the
execution of this project was faced in two areas- determining the algorithms for training and
choosing proper parameters for fine-tuning. Initially, I found it very vexing to decide upon 3
or 4 techniques out of the numerous options available in sklearn.
This exercise made me realize that parameter tuning is not only a very interesting but
also a very important part of machine learning. I think this area can warrant further
improvement, if we are willing to invest a greater amount of time as well as computing power.