Category: healthtech

  • A Comparison of Scikit Learn Algorithms for Breast Cancer Classification – 2. Cross Validation vs Performance

    A Comparison of Scikit Learn Algorithms for Breast Cancer Classification – 2. Cross Validation vs Performance

    The post is a continuation of a previous breast cancer study comparing Scikit-Learn binary classifiers for cross validation and model performance. The classifiers compared include Logistic Regression, GaussianNB, SVC, KNN, Random Forest, Extra Trees, and Gradient Boosting. Learning curves show the comparison of classifier performance. Results indicate GaussianNB is more efficient than SVC in terms…

  • A Comparison of Binary Classifiers for Enhanced ML/AI Breast Cancer Diagnostics – 1. Scikit-Plot

    A Comparison of Binary Classifiers for Enhanced ML/AI Breast Cancer Diagnostics – 1. Scikit-Plot

    The post compares binary classifiers in Scikit-Learn using the breast cancer dataset. It includes data analysis, ML preparation, learning curves, feature dominance, calibration curves, confusion matrix, ROC curve, precision-recall curve, KS statistic, cumulative gains, lift curves, PCA, and classification reports. Various models’ performances are compared with focus on key metrics and feature evaluations.

  • DL-Assisted ECG/EKG Anomaly Detection using LSTM Autoencoder

    DL-Assisted ECG/EKG Anomaly Detection using LSTM Autoencoder

    This project implements an ECG anomaly detection framework using an LSTM Autoencoder to accurately identify abnormal ECG events. It trains the autoencoder on normal rhythms, using reconstruction errors to identify anomalies. The proposed method aims to improve abnormal ECG detection, as demonstrated by test results on the ECG5000 dataset, providing valuable information for patient health…

  • ML/AI Breast Cancer Diagnosis with 98% Confidence

    ML/AI Breast Cancer Diagnosis with 98% Confidence

    We demonstrate the importance of hyperparameter optimization (HPO) for enhancing ML prediction accuracy. Specifically, we will focus on the Random Forest Classifier (RFC) as an ensemble of decision trees. RFC is a supervised ML algorithm that has been applied successfully to the BC binary classification. 

  • Cloud-Native Tech Autumn 2022 Fair

    Cloud-Native Tech Autumn 2022 Fair

    Let’s dive deeper into the cloud-native tech trends and features to follow in Q4 2022 and beyond. Contents: Markets Services Serverless Cybersecurity DevSecOps ML/AI/IoT Use-Cases Events Training Explore More Infographic

  • Breast Cancer ML Classification – Logistic Regression vs Gradient Boosting with Hyperparameter Optimization (HPO)

    Breast Cancer ML Classification – Logistic Regression vs Gradient Boosting with Hyperparameter Optimization (HPO)

    Breast Cancer (BC) is the leading cause of death among women worldwide. The present study optimizes the use of supervised Machine Learning (ML) algorithms for detecting, analyzing, and classifying BC. We compare Logistic Regression (LR) against Gradient Boosting (GB) Classifier within the Hyperparameter Optimization (HPO) loop given by GridSearchCV. We use the publicly available BC dataset…

  • A Comparative Analysis of Breast Cancer ML/AI Binary Classifications

    A Comparative Analysis of Breast Cancer ML/AI Binary Classifications

    This study is dedicated to #BreastCancerAwarenessMonth2022 #breastcancer #BreastCancerDay @Breastcancerorg @BCAction @BCRFcure @NBCF @LivingBeyondBC @breastcancer @TheBreastCancer @thepinkribbon @BreastCancerNow. One of the most common cancer types is breast cancer (BC), and early diagnosis is the most important thing in its treatment. Recent studies have shown that BC can be accurately predicted and diagnosed using machine learning (ML) technology. Our…

  • ML/AI for Diabetes-2 Risk Management, Lifestyle/Daily-Life Support

    ML/AI for Diabetes-2 Risk Management, Lifestyle/Daily-Life Support

    The surge of Type-2 Diabetes (T2D) is majorly impacting developing nations, heightened mortality, and morbidity rates. The study explores AI/ML methods in assisting T2D management with potential challenges. The study discovered ML/AI techniques, like Random Forest Classifier and others, progressively aiding in clinical and self-management of diabetes. The study used datasets like PIMA and data…

  • Technology Focus Weekly Update 16 Oct ’22

    Technology Focus Weekly Update 16 Oct ’22

    Get top data-driven technology highlights of the week: new SaaS products, tech business applications and learnings of the week: DevOps, DevSecOps, Cybersecurity, public cloud platforms (AWS/GCP/Azure), MarTech, ML/AI, MLOPs, NLP, edtech, e-courses, upcoming events, and related Infographics. Contents: DevOps November 8th, 2022     |     11 a.m. ET Providing reliable and secure services doesn’t just happen.  Traditionally,…

  • A Comparison of ML/AI Diabetes-2 Binary Classification Algorithms

    A Comparison of ML/AI Diabetes-2 Binary Classification Algorithms

    The post discusses the increasing urgency to diagnose and treat Type-2 Diabetes (T2D), particularly in developing nations. It delves into the use of data-driven techniques, including ML/AI, in processing T2D data. Different ML/AI methods including DNN, SVM, and DT are applied to the Kaggle PIMA Indian Diabetes (PID) dataset, and performance is assessed using Python…

  • HPO-Tuned ML Diabetes-2 Prediction

    HPO-Tuned ML Diabetes-2 Prediction

    The blog details the author’s tests with machine learning (ML) for enhanced prediction of Type-2 diabetes. The workflows used include RandomizedSearchCV HPO, accuracy metrics, and cross-validation. The post provides in-depth analysis and comparisons of different ML algorithms, such as RandomForestClassifier, GaussianNB, and DecisionTreeClassifier. The experiment findings indicate that RandomForestClassifier with RandomizedSearchCV provides the highest accuracy,…

  • HealthTech ML/AI Q3 ’22 Round-Up

    HealthTech ML/AI Q3 ’22 Round-Up

    Featured Photo by Andy Kelly on Unsplash This blog presents a Q3 ’22 summary of current healthtech ML/AI innovation methods, trends and challenges. Virtual reality, artificial intelligence, augmented reality, and machine learning are all healthcare technology trends that are going to play a vital role across the entire healthcare system. Let’s take a look at…

  • AI-Guided Drug Recommendation

    AI-Guided Drug Recommendation

    AI-Guided Drug Recommendation in Python using NLP text processing. Key steps: WordCount images, NLP Pre-Processing, NER via spacy, LDA topic modelling, and Word2Vec Vectorization for reviews using pretrained glove model. Input data: the Kaggle UCI ML Drug Review dataset. Applications in the pharmaceutical industry, including drug R&D, drug repurposing, improving pharmaceutical productivity, and clinical trials,…

  • ANOVA-OLS Prediction of Surgical Volumes

    Operating rooms (ORs) are some of the most valuable hospital assets, generating a large part of hospital revenue.  Statistical models have been developed using datasets to predict daily surgical volumes weeks in advance. We focus on the VUMC dataset for evaluation of our statistical models. We use the ANOVA null-hypothesis test for the total number…

  • Drug Review Data Analytics

    UCI Drag Review Data Analytics An AI assisted medication recommender framework is truly vital with the goal that it can assist specialists and help patients to build their knowledge of drugs on specific health conditions. We Build a Drug Recommendation System that recommends the most effective drug for a certain condition based on available reviews…

  • AI-Driven Skin Cancer Diagnosis

    AI-Driven Skin Cancer Diagnosis

    Using TensorFlow library in Python, we can implement an image recognition skin cancer classifier that tries to distinguish between benign (nevus and seborrheic keratosis) and malignant (melanoma) skin diseases from only photographic 2D RGB images

  • The Application of ML/AI in Diabetes

    The study uses machine learning (ML) to predict diabetes in patients. Classifying diabetics is complex, but ML can offer quick and accurate predictions. The study focuses on type 2 diabetes and uses the Pima Indians database for diagnostic measurements. Models were trained with Python and the Anaconda library. Feature engineering and exploratory data analysis revealed…

  • AI-Powered Stroke Prediction

    Contents: Introduction Stroke, also known as brain attack, happens when blood flow to the brain is blocked, preventing it from getting oxygen and nutrients from it and causing the death of brain cells within minutes. According to the World Health Organization (WHO) stroke is the 2nd leading cause of death globally after ischemic heart disease,…

  • Diabetes Prediction using ML/AI in Python

    The post focuses on developing a machine-learning model to predict diabetes using patient diagnostic data from the UCI Machine Learning Repository, featuring blood tests and obesity metrics. Implemented classifiers include a random forest, decision tree, XGBoost, and an SVM. The model is trained on this data, achieving highest accuracy with the random forest method (approx.…

  • HealthTech ML/AI Use-Cases

    About Supervised ML/AI Breast Cancer Diagnostics Python Use-Case Supervised ML/AI in Breast Cancer (BC) Classification Heart Failure Prediction using Supervised ML/AI Technique Diabetes Prediction using ML/AI in Python