In order to use our Yosnalab shopping services, you need to read carefully about our terms and conditions. If You disagree any part of terms then you cannot access our service.
I agree to pay the rental rate for the period we used the product and in transit and further agrees to promptly return the products at the end of the rental period in the same condition as received.
I will give alert to Yosnalab if my contact information changes.
I also agree to pay for any damages to, or loss of, the rented merchandise occurring during their time of possession or because of loss and or damage of the products. Upon return and inspection if any and all repairs necessary and or accessories missing that were itemized will be charged at our current rates and billed to you.
A full day rental is charged, even for a partial day use. There are absolutely no refunds for early returns.
The products can be used upto 4 weeks only, Cost will be calculated as per day of usage. We are not responsible for the damage of materials or other liability of any kind resulting from the use or malfunction of the equipment. We will not return the initial deposit of money until the product is returned back.
I am responsible for keeping track of my due dates. I understand that any notices sent out by Yosnalab are a courtesy only and failure to receive them does not excuse me from any charges.
A copy of both sides of their valid institution identification card need to be present. Depositing the money can be done only in the form of cash, not through credit/debit cards.
If you have questions or suggestions, please contact us.
Nowadays, Diabetes is considered a chronic disease. But it causes great damage to the health of our people. When the glucose level in blood is higher than the usual limit, then it leads to diabetes which means the secretion of insulin is affected, thereby affecting almost every organ of the human body. Among pregnant women, diabetes is termed as gestational diabetes mellitus (GDM) which means the glucose intolerance of variable degree with the appearance of symptoms or first detection during pregnancy. A survey result shows that abnormalities of glucose regulation either pregestational or gestational occur in 3-8% of pregnant women. By predicting the disease earlier, proper treatments can be administered to the patients before the case becomes critical. The goal of this project is to develop a system that will help in the prediction of the diabetic risk levels of a patient with higher accuracy. We have decided to find the solution to the existing problem by Data Analysis and Machine Learning which helps to predict if the patient has diabetes or not.
Why: Problem statement
Usually, to test diabetes, the person has to visit the nearby medical lab and spend almost a day waiting at the diagnostic centre to get the result. The patient has to pay in order to get the result each time.
How: Solution description
Detailed antenatal history regarding present and past pregnancies were noted. Special attention was given to diabetic status, time of onset of diabetes, treatment details, history of LGA and fetal loss in past pregnancies.
The diabetic mothers were divided into 3 categories.
Group A: Gestational diabetes,
Group B: Diabetic status not known
Group C: Pregestational diabetes
The dataset for the diagnosis of gestational diabetes is obtained from medical reports of the patients collected from maternity hospitals in Pondicherry. There are 51 instances with 19 different attributes related to gestational diabetes like age, parity, diabetic status, treatment details, fetal loss, mode of delivery, liquor, Apgar, gender, the weight of baby, gestational age, Agalgasga, symptoms in baby, cardiovascular findings, chest x-ray, Echo and followup.
We have undergone three processes for data cleaning.
Ø Data Preprocessing
Ø Checking for missing data
Ø Replacing missing ("?") and ("t?") data with NaN values
SPLITTING DATA FOR TRAINING AND TESTING:
This dataset contains 51 diabetic Mellitus pregnant patient records. We split the training and testing data with a ratio of 7:3. That is 70% of data is for training and 30% is for testing. We used the train_test_split method from sklearn to split the data.
TRAINING USING MACHINE LEARNING MODELS:
First, we tried Naive Bayes Classifier. A Naive Bayes classifier is a simple probabilistic classifier based on applying Bayes theorem (from Bayesian statistics) with strong (naive) independence assumptions. A more descriptive term for the underlying probability model would be an independent feature model. We got the testing accuracy of 87.5% with Gaussian Naive Bayes, 72.5% with Multinomial Naive Bayes and 62.5% with Bernoulli Naive Bayes.
Then, we used Random Forest Classifier. It comes under the category of ensemble methods. It employs ‘bagging’ and ‘boosting’ methods to draw a random subset from the data, and train a Decision Tree on that. We got an accuracy of 87.5% with this method.
How is it different from competition
We have boosted our proposed model using xgboost algorithm. The speciality of this powerful algorithm lies in its scalability, which drives fast learning through parallel and distributed computing and offers efficient memory usage. We reached an accuracy of 93.75% with the xgboost algorithm.
Who are your customers
Pregnant women and Gynecologists are our customers.