DATAVERSE
DATAVERSE
A group of researchers focused in the field of Neurology, with a vision to help and support patients using Analytical Science.
ABOUT DATAVERSE
Behind the PR Curtain
We are DataVerse, an exclusive Healthcare Public Relations Agency based in San Diego. We’ve built up a team of passionate and thoughtful storytellers who put immense amounts of effort into producing great results for our Patients. Through a wide range of services, we provide strategic guidance by coming up with the right solution for each client we serve.
JOIN OUR RESEARCH GROUP
DATA FIELDS IN SURVEY
This Visualization shows the demographic fields and survey data frames considered by professionals during analysis.
MIND AND BRAIN FUNCTIONING TEST
TAP ( Psychological stability test)
A Test is conducted on many patients represented by ( Sub-010002..).The graph shows working memory mapping of the patient over the number of tests conducted.
BRAIN TUMOR RESEARCH
Research focusing on segmentation to determine Tumor presence
MRI IMAGE CLASSIFICATION
Tumor Graph - Feature Scaling
Feature scaling in machine learning is one of the most critical steps during the pre-processing of data before creating a machine learning model. Scaling can make a difference between a weak machine learning model and a better one. The most common techniques of feature scaling are Normalization and Standardization.
SEGMENTATION OF MRI IMAGES
The process of Data Augmentation is followed where the neural network classifies ’n’ images into four classes. Then we take votes from each class. If vote of a particular class is greater than threshold vote confidence, we declare that class label as the output which is sent to back to the user.
If the threshold is not met, the Image Augmentator is called which generated new ’n’ images and they are again sent to NN. This process is executed until, the threshold vote confidence is met or no of tries(’t’) is reached.
TUMOR IDENTIFICATION
Tumor is segregated as Cancerous/ Non-Cancerous
OUTPUT FORM
This is how the result of our research looks like.
The overall accuracy of the model is 96%.In the below Image, you can see the classification result.
TRAIN GRAPH
This graph tells about Trained +Â Validated smoothened graph scores
VALIDATION GRAPH
Validation Graph shows a linear scale input with smoothed values
ACCURACY GRAPH
Accuracy Graph explains that the Training dataset maintained a much more precision level whereas the testing dataset accuracy improved with the amount of input and at a later stage matched with the Training model.
.png)
DATA LOSS
This visualization shows the amount of data loss in each of the training model. Initially, the model experienced a Validation loss which comes from testing but was recovered at a later stage increasing the overall precision.
RESULTS OF THE RESEARCH ->MODEL ACCURACY
Our Model was successful in giving precision 99 percent and f1 score of 0.99 that explains the accuracy of the model.
.png)
MINDSET ANALYSIS AND PATIENT FEEDBACK ANALYSIS
The Word - Cloud shows the words which were frequently given by patients when asked for symptoms.
It also shows the behavioral analysis that shows how many patients still had a positive mindset.R word cloud uses Search Engine Optimization
.png)
FACTORS AFFECTING TUMOR
Factor Considered- Smoking and Drugs
Tumor can be caused by multiple factors. Research is conducted considering multiple criterions such as Age / Gender / Smoking Habits / Hamilton Scale- Depression analysis and cognitive stability. Demographic Factors are considered in this case that affect rate of Tumor Growth or Shrinkage.
SYMPTOM SURVEY
Geographical Survey Test
The Map shows the areas in which Fatigue , Headache was observed and thus highlights the areas where medical attention is needed.
Bigger Diameter of the Circle /Highlighted Portion implies that much more attention needs to be given in that area.
LIVE DATA FEED-WORD CLOUD MEMORIZATION ANALYSIS
Memorization results are integrated with geographic locations and are analyzed to understand the patients across the globe.
MEMORY PATTERN TEST
Test was conducted amongst patients to find the similarities between their behavior and understand patterns between them. Alertness/Attentiveness studied in Memory Pattern Test is the state of mind with general activity performance and ability to grasp routine activities that enables a person to respond and react quickly and appropriately to any given demand.
Below are the conditions given by Participants and the reasons provided.
DATA PRIVACY
At We Care we believe that Your data is yours—and only yours.
We understand that you have the right to information privacy.
Thus, taking consent for all purposes is our priority.
SUGGESTIONS
GET TO KNOW US
Behind the Scenes
SURBHI SAWANT
