Embedded Files
Project Name: Changes in Psychiatric Diagnosis Associated With SARS-CoV-2 Infection and Predicting the Development of New Psychiatric Illness in COVID Patients by Using Machine Learning Approach: A Study Using the US National COVID Cohort Collaborative (N3C)
NIH Project
Summary:
This project investigates the complex link between SARS-CoV-2 infection and the onset of new psychiatric disorders, with a focus on Schizophrenia Spectrum and Psychotic Disorders (SSPD). Using data from the U.S. National COVID Cohort Collaborative (N3C), I developed predictive models to identify high-risk COVID-19 patients who may be prone to psychiatric complications post-infection. By comparing COVID-19 patients with Acute Respiratory Distress Syndrome (ARDS) and COVID-negative control groups, I established a significant association between COVID-19 and psychiatric outcomes, reinforcing the need for proactive mental health interventions in COVID-19 recovery. My analysis, utilizing machine learning models like Random Forest, Decision Tree, and Logistic Regression, identifies key predictors—including medication history, biological markers, and demographic factors—that influence psychiatric diagnoses. This work not only enhances our understanding of COVID-19’s mental health impact but also provides a foundation for targeted prevention and early intervention strategies, ultimately aiding healthcare providers in improving patient outcomes.
Change in Percentage of Common Features Over Different Time Frames
Change in Percentage of Common Features Over Different Time Frames
Comparison of Probability Distributions for Real vs. Synthetic Data
Comparison of Probability Distributions for Real vs. Synthetic Data
Key Steps and Techniques:
Data Collection and Preparation: Conducted data cleaning and cohort creation, using techniques like propensity score matching to ensure reliable comparisons across COVID-positive and control groups.
Exploratory Data Analysis: Analyzed demographic, clinical, and biochemical data to identify initial patterns and key variables correlated with psychiatric diagnoses.
Machine Learning Models: Built and evaluated various models to predict the likelihood of developing psychiatric conditions, including:
Random Forest: Achieved high accuracy in identifying key risk factors, leveraging the model’s feature importance capabilities.
Logistic Regression: Used to interpret how demographic and clinical features increase or decrease risk, providing a clear, probabilistic understanding.
Decision Tree and Support Vector Machine (SVM): Utilized to compare model performances, visualize decision paths, and refine predictive accuracy.
Survival Analysis: Implemented Cox Proportional Hazards regression to measure the temporal risk of psychiatric outcomes, highlighting significant predictors across multiple time frames.
Top 10 Variable with the Greatest Difference of Features between Two SSPD Groups
Top 10 Variable with the Greatest Difference of Features between Two SSPD Groups
Top 10 Feature Importances for Different ML Models
Top 10 Feature Importances for Different ML Models
Confusion Matrix for Different ML Models
Confusion Matrix for Different ML Models
Top 20 Variables with Highest Percentage of 1
Top 20 Variables with Highest Percentage of 1
Heart Failure Survival Analysis Dashboard
Heart Failure Survival Analysis Dashboard
I created this dashboard using heart failure patient data to analyze survival trends and key risk factors like anemia, diabetes, smoking, and blood pressure. The dashboard provides an intuitive visualization of survival distributions across demographics, lab results, and medical conditions.
Using Tableau, I incorporated histograms, scatter plots, and categorical breakdowns to highlight patterns in survival outcomes. This dashboard enables healthcare professionals to identify crucial factors influencing patient prognosis, supporting data-driven clinical decisions and improving patient care strategies.
UK Road Accident Insights Dashboard
UK Road Accident Insights Dashboard
UK road accident data was analyzed to create an interactive tableau dashboard by severity (Fatal, Serious, Slight, All), road type, and weather conditions. The dashboard also included year-over-year trends and interactive maps.
Final cohort selection by applying exclusion criteria
Project Name: SARS-CoV-2 infection is associated with an increase in new diagnoses of schizophrenia spectrum and psychotic disorder: A study using the US national COVID cohort collaborative (N3C)
NIH Project
Summary: In this study, I investigated the potential relationship between SARS-CoV-2 infection and the onset of schizophrenia spectrum and psychotic disorders (SSPD). Using a large dataset (almost 20M data) from the U.S. National COVID Cohort Collaborative (N3C), my analysis aimed to determine whether COVID-19 infection is associated with an increased risk of developing psychiatric disorders, specifically SSPD.
Key Highlights:
1) Study Design: The study compared psychiatric outcomes in COVID-positive patients with those in control groups, including patients with Acute Respiratory Distress Syndrome (ARDS) and COVID-negative individuals, to isolate the unique impact of COVID-19 on mental health.
2) Statistical Analyses:
Schoenfeld Residuals Test: Used to test the proportional hazards assumption in survival analysis, ensuring the reliability of our hazard ratio estimates.
Cochran-Mantel-Haenszel Test: Applied to control for confounding variables across stratified data, refining our comparison between COVID-positive and control groups.
Likelihood Ratio Test, Wald Test, and Logrank Test: These tests were conducted to assess the significance of predictor variables and compare survival curves between groups.
Cox Proportional Hazards Model: Employed as the primary model to estimate hazard ratios, revealing a significant association between COVID-19 infection and an increased risk of developing SSPD.
3) Implications: These findings highlight the critical need for mental health screening and interventions for COVID-19 patients, particularly those predisposed to psychiatric conditions, and lay the groundwork for further research on the psychiatric consequences of COVID-19.
This research contributes to a growing body of evidence on the mental health implications of COVID-19, offering insights that could guide clinical practices and public health policies.
SSPD hazard ratio comparisons
Project Name: Innovative Product Design with Fused Deposition Modeling (FDM).
Summary: This project explored the potential of Fused Deposition Modeling (FDM) to create optimized, lightweight, and structurally sound components for engineering applications. Using advanced design software, including Fusion 360 and Autodesk Netfabb, I developed two innovative products—a bionic aircraft bracket and a load-bearing bridge—that balance material efficiency with durability.
Bionic Aircraft Bracket
Inspiration: Modeled after a butterfly wing to achieve a lightweight, structurally efficient design for aerospace use.
Process:
Created a bio-inspired design in Fusion 360 to reduce material use while maintaining strength.
Used Autodesk Netfabb for STL file repair, ensuring precision for FDM printing.
Key Insight: Demonstrates the potential of bio-inspired design in aerospace, allowing significant weight reduction without compromising performance.
Bionic Aircraft Bracket. Material: CFRP
Multi-view of the Bionic Aircraft Bracket. Created in Fusion 360
STL file repair. Created in Netfabb
Multi-view of the Load Bearing Bridge. Created in Fusion 360
Load Bearing Bridge
Inspiration: Designed with an arc-based honeycomb structure, inspired by Roman arch bridges, to maximize load-bearing capacity.
Process:
Developed and optimized in Fusion 360; refined file in Netfabb to prepare for FDM printing.
Conducted simulation tests in Fusion 360, followed by lab testing, confirming a high load-bearing-to-weight ratio.
Key Insight: Highlights how additive manufacturing can create efficient, high-strength structural designs, applicable to civil engineering and research.
Load Bearing Bridge. Material: ABS
STL file repair. Created in Netfabb
USA Credit Card Complaints Analysis Dashboard
USA Credit Card Complaints Analysis Dashboard
This Tableau dashboard analyzes credit card complaints across the US, highlighting trends, resolution rates, and key issues with interactive heatmaps and filters. It provides actionable insights to improve customer service strategies.
Project Name: Optimizing energy consumption in directed energy deposition-based hybrid additive manufacturing: an integrated modeling and experimental approach.
NSF Project
Summary: This project explores ways to reduce energy consumption in Directed Energy Deposition (DED)-based Hybrid Additive Manufacturing (HAM), a process combining additive manufacturing with CNC machining. Using Inconel 718, a high-performance nickel-based superalloy, I developed and validated an energy consumption model to analyze the effects of process parameters such as laser power, scanning speed, and feed rate.
Key Highlights:
Process Optimization: By analyzing the influence of scanning speed, laser power, and feed rate on specific energy consumption (SEC), I identified optimal parameter settings that can reduce energy usage in DED-based HAM processes.
Statistical Methods: The study employed Lenth’s method and regression analysis to quantify the impact of each parameter, revealing that laser power is the most significant factor influencing energy consumption, followed by scanning speed and feed rate.
Practical Impact: The findings emphasize that higher scanning speeds combined with lower laser power and feed rates lead to energy-efficient operations. This insight contributes to sustainable manufacturing by minimizing energy requirements, aligning with the goals of Industry 4.0 and Industry 5.0 for eco-friendly production.
This research advances our understanding of energy-efficient strategies in hybrid additive manufacturing, providing a foundation for future studies in sustainable manufacturing practices.
Our Setup
Electricity Consumption during Subtractive Manufacturing VS Additive Manufacturing
Workforce Dynamics and Insights Dashboard
Workforce Dynamics and Insights Dashboard
This Tableau dashboard provides detailed insights into workforce metrics, including employee attrition rates, department-wise trends, job satisfaction ratings, and demographic distributions. Designed for HR analytics, it enables stakeholders to identify key patterns and make data-driven decisions to optimize workforce strategies.
Data Validation : SQL Meets Tableau
Data Validation : SQL Meets Tableau
This project involved using one of my interactive Tableau dashboards - 'Workforce Dynamics Dashboard' - to perform data validation. Using SQL, I performed data integrity checks, validated attrition rates, employee counts, and demographic trends, and ensured accurate alignment between raw datasets and visualization outputs.
Project Name: Efficient Manufacturing Design with Digital and Generative Tools.
Summary: This project aimed to optimize the design and manufacturing process of a mechanical hinge by integrating digital tools and generative design within Computer Integrated Manufacturing (CIM). The goal was to investigate methods to enhance the material stiffness, tool life, and machining efficiency while reducing overall manufacturing costs.
Objective: The project focused on maximizing stiffness with minimal material usage, generating efficient tool paths, and evaluating costs and manufacturing efficiency.
Process and Tools:
CAD and CAM Modeling: Using Fusion 360 for CAD modeling and Computer-Aided Process Planning (CAPP), I designed a 3D model of a mechanical hinge, optimized for production in both 3-axis and 5-axis CNC setups.
Generative Design: Leveraged generative design to explore alternative geometries and configurations, guided by AI-driven algorithms to achieve the optimal structural layout for stiffness and load-bearing capacity.
Material and Process Analysis: Investigated multiple materials, including Aluminum ALSi10Mg and Inconel 718, and compared machining approaches (3-axis vs. 5-axis milling and die casting) to determine the best method for cost efficiency and structural integrity.
Outcome: The project identified a cost-effective design and machining plan, demonstrating how digital manufacturing and generative tools can lead to efficient and sustainable production processes. By analyzing tool life, machining time, and material removal rate (MRR), the study provided actionable insights for reducing waste and enhancing productivity in mechanical manufacturing.
This project showcases the potential of digital manufacturing techniques to improve production quality and cost-efficiency, aligning with the goals of sustainable and integrated manufacturing practices.
3 Axis Milling Process
Page updated
Google Sites
Report abuse