Author Archives: Evelina Rosser

CAN YOU PROVIDE MORE EXAMPLES OF REAL WORLD BIOMEDICAL ENGINEERING CAPSTONE PROJECTS

Leave a reply

Development of an Upper Extremity Exoskeleton to Aid in Rehabilitation:

A team of students designed and built a robotic exoskeleton device to be worn over the arm and hand to assist in rehabilitation therapy for patients recovering from injuries such as strokes. The exoskeleton contained sensors to monitor the patient’s movements and provided assisted motions to help them regain range of motion and motor control abilities in a safe manner. It could be adjusted for different therapy exercises and tracked progress over time. The students had to research rehabilitation needs, design the mechanical components, implement control systems using motors and software, perform safety and usability testing, and develop manufacturing and assembly plans to demonstrate a potentially commercializable medical device.

Embedded Monitoring System for Neonatal Care:

Another group of students developed a non-invasive embedded monitoring system for use in the neonatal intensive care unit (NICU) to continuously track vital signs of premature infants without needing frequent disruptions to attach wired sensors. They designed wearable multi-sensor modules containing temperature, heart rate, respiration rate and oxygen saturation sensors that wirelessly transmitted data to a central station. Software was programmed to sound alarms for any unstable readings. Prototypes were tested on newborn infant simulators and feedback was gathered from NICU nurses. Regulations for medical devices were researched to outline pathways for FDA approval.

3D Printed Implants for Craniofacial Reconstruction:

In this project, biomedical engineering students partnered with facial trauma surgeons to address the need for custom implants used in complex craniofacial reconstruction surgeries. They developed a workflow using computer aided design (CAD) software and 3D printing technology to create patient-specific implants based on CT scans. Material properties of polymers and metals were analyzed to select appropriate biomaterials. Surgical planning, sterile manufacturing and regulatory issues were considered. Working prototypes of mandible, orbital and calvaria implants were fabricated and their precision-fit was verified. Collaboration continued with surgeons to refine the process and pursue clinical studies.

Biosensor for Detecting Bed sores:

Bedsores, or pressure ulcers, are a serious medical complication for patients confined to beds for extended periods. A team of students designed a flexible biosensor system that could be integrated into beds and mattresses to noninvasively monitor pressures at multiple surface points on a patient’s body in real-time. Different sensor technologies were tested and a capacitive sensor array was selected for its conformability. A microcontroller collected pressure maps which were analyzed using algorithms to detect pressures exceeding tolerance limits that pose risk of sores. Notifications were sent to caregivers’ mobile devices. Clinical feedback helped refine sensor placement and data visualization.

MRI-Compatible Robotic Biopsy Device:

Magnetic resonance imaging (MRI) provides excellent soft tissue contrast for diagnosing cancers, but current biopsy procedures require removing the patient from the scanner for needle placement. A group of students sought to address this limitation by designing a robotic biopsy device that could accurately insert biopsy needles under MRI guidance without interfering with the scanner’s magnet. They integrated non-ferrous actuators, piezoelectric motors and plastic gears into an MRI-safe mechanical design. Image processing and robot kinematics were used to precisely register needle positions from MRI images. Rigorous testing was performed to ensure no artifacts or distortions in images. Collaboration continued with radiologists to define clinical workflows and identify any remaining technical hurdles prior to pursuing FDA clearance.

This covers a sampling of some ambitious biomedical engineering capstone projects undertaken by students that involved developing real medical devices, technologies and solutions to address diverse clinical needs. The projects required integrating knowledge of human anatomy and physiology, materials selection, engineering design, manufacturing, regulations, and collaborating with medical experts. The level of innovation demonstrated in developing functional prototypes that advanced healthcare reflects the interdisciplinary training biomedical engineers receive to apply engineering principles for improving human health.

CAN YOU PROVIDE EXAMPLES OF QUALITY IMPROVEMENT CAPSTONE PROJECTS THAT HAVE BEEN SUCCESSFUL IN REDUCING HOSPITAL ACQUIRED INFECTIONS

Leave a reply

Hospital acquired infections, also known as healthcare-associated infections (HAIs), are a significant issue that impacts patient outcomes and increases healthcare costs. Implementing quality improvement projects focused on evidence-based practices to reduce HAIs has been shown to be an effective way for hospitals and healthcare workers to enhance patient safety. Here are some examples of successful capstone projects that have made a meaningful impact in reducing various types of hospital acquired infections:

One notable project took place at an academic medical center and focused on reducing central line-associated bloodstream infections (CLABSI) in the intensive care unit (ICU). CLABSIs occur when bacteria or viruses enter the bloodstream through a central line catheter. This project used the Model for Improvement framework to test changes. Interventions implemented included adopting a maximal sterile barrier during central line insertion, using chlorhexidine for skin antisepsis, and focusing on prompt removal of unnecessary lines. Compliance with best practices was tracked and deficiencies were addressed. After 12 months, the medical ICU saw a 65% reduction in CLABSI rates from a baseline of 3.7 infections per 1,000 line days to 1.3 infections. This reduction equated to 17 avoided infections and an estimated cost savings of $514,000 for the hospital.

Another successful capstone quality improvement project centered around reducing catheter-associated urinary tract infections (CAUTIs) in a surgical ICU. CAUTIs develop when bacteria enter the urinary tract through a catheter. The project team established evidence-based practices for catheter insertion and maintenance, including use of aseptic technique and sterile equipment during insertion, securing catheters properly after insertion, and only using catheters when necessary as indicated by daily reviews. Educational programming was provided to nurses. Visual aids served as daily reminders. Within 6 months of implementing the changes, monthly CAUTI rates dropped from a baseline of 2.6 per 1,000 catheter days to zero infections, representing a 100% reduction. An estimated 20 avoided infections resulted in cost savings of $400,000 for the hospital.

A capstone project at a community hospital targeted reducing ventilator-associated pneumonia (VAP) in its medical ICU. VAP occurs when bacteria enter the lungs through an endotracheal breathing tube in patients on mechanical ventilation. The core project team developed a multidisciplinary VAP bundle checklist and instituted “VAP champions” – nurses trained to serve as expert resources on VAP prevention. Education focused on maintaining the head of the bed at 30 degrees or higher, oral care with chlorhexidine, and ensuring peptic ulcer disease prophylaxis. Process measures showed near perfect compliance with the bundle elements. After 6 months, the VAP rate dropped from a baseline of 3.3 per 1,000 ventilator days to 1.7, representing almost a 50% reduction. An estimated 10 VAPs were prevented, saving the hospital approximately $300,000.

Another successful quality improvement capstone took place at a large tertiary care hospital and focused on reducing surgical site infections (SSIs) specifically after coronary artery bypass graft (CABG) surgery. SSIs occur when bacteria enter through an incision made during surgery. Best practices targeted in the project included pre-operative chlorhexidine showers or wipes for patients, appropriate antibiotic prophylaxis timing and selection, intra-operative normothermia maintenance, glucose control, wound protection, and smoking cessation support. educational in-services and visual prompts reinforced the changes. Over 18 months, compliance with all SSI prevention practices improved significantly from a baseline average of 65% to 95%. Simultaneously, the CABG SSI rate declined by 50%, from 2.5% of patients to 1.2%. This reduction meant 19 fewer infections annually and an estimated cost avoidance exceeding $500,000.

As demonstrated through these illustrative capstone quality improvement projects, multi-pronged, evidence-based approaches focused on consistent adherence to best practices can meaningfully reduce hospital acquired infection rates. Sustained reductions in CLABSI, CAUTI, VAP, and SSIs each lead to improved patient outcomes and substantial cost savings. A culture of safety, staff education, visual reminders, consistent leadership support, and multidisciplinary involvement all contributed to success. With applied efforts to optimize evidence-based care, hospitals can enhance quality and safety for patients through effective measures targeting the reduction of preventable HAIs.

DO YOU HAVE ANY TIPS FOR EFFECTIVELY PRESENTING A CAPSTONE PROJECT TO FACULTY AND STAKEHOLDERS

Leave a reply

First, you’ll want to prepare well in advance. Make sure you have a clear outline of the key points you want to cover so you stay organized and on track during your presentation. Spend time rehearsing your presentation out loud so you feel comfortable speaking about your project. Aim to have your presentation polished and refined after several practice runs.

Come up with a compelling opening that will grab your audience’s attention right away. You only have a limited amount of time, so an engaging introduction is crucial to set the right tone. Consider starting with an interesting fact, statistic, or scenario that establishes the relevance and importance of the work you did. This opening sets the stage for the rest of your presentation.

Be sure to clearly state the purpose and goals of your capstone project upfront. Define what problem or issue you sought to address and the objectives you established. Making your objectives explicit allows your audience to follow along and understand how and why you approached your project the way you did.

Provide some background context on the topic before delving into the key components of your work. Give your audience the necessary framework to comprehend the significance and complexity of the issue. You can discuss previous research, trends in the field, and why further exploration was needed. Painting this picture helps non-experts get up to speed.

Use visual aids judiciously and effectively. Include graphs, charts, images, or videos as appropriate – but only if they enhance comprehension rather than distract or overload the viewer. Well-designed visuals can help illustrate patterns and communicate messages more powerfully than words alone. Make sure any visual elements are readable from a distance.

Touch on your research methodology with just enough detail. Discuss the methods, tools, and processes you used while keeping explanations concise. Faculty need to know your work was rigorous and aligned with best practices, but stakeholders mainly care about the outcomes. Stick primarily to the most salient methodological aspects.

highlight your key findings and results through clear, compelling presentation of data. Analyze and interpret the most important and interesting outcomes of your work. Connect the dots from your objectives, through the approach and analysis, to the conclusions. Illustrate how the results addressed the issue at hand.

Tie your conclusions back to the big picture by discussing how your findings fit within the broader context and literature. Relate the implications and significance of your discoveries for both theory and practice. Consider directions for future research and applications stemming from your work. This level of synthesis and insight shows a deep understanding of the topic.

Leave ample time for questions by keeping your presentation timed appropriately. Most capstone advisors recommend limiting it to 15-20 minutes with another 5-10 minutes for Q&A. Practice keeping it on schedule. Field questions confidently by restating them concisely and linking responses back to your work. Ask for clarification if needed.

In your closing, summarize the key takeaways clearly and concisely while thanking your audience for their time and interest. Restate the importance of your work and its contributions. Provide a brief “call to action” if relevant for next steps. A polished conclusion leaves a strong lasting impression.

Practice good delivery techniques to engage your audience through your presentation. Make eye contact, vary your tone, and use dynamic body language and gestures judiciously. Smile, appear relaxed and confident, and exude passion for your topic to keep people’s attention. Rehearsal will help you deliver your capstone project presentation with impact and aplomb to faculty and stakeholders.

With thorough preparation, clear and compelling structure, appropriate use of visuals, strong data analysis and conclusions, engaging delivery techniques, and ability to field questions, you’ll be able to effectively communicate the value, insights and significance of your capstone project. Showcasing your excellent work in this impactful format is an excellent way to conclude your academic experience on a high note. I hope these tips provide helpful guidance as you prepare your capstone presentation.

CAN YOU EXPLAIN THE PROCESS OF CONVERTING CATEGORICAL FEATURES TO NUMERIC DUMMY VARIABLES

Leave a reply

Categorical variables are features in data that consist of categories or classes rather than numeric values. Some common examples of categorical variables include gender (male, female), credit card type (Visa, MasterCard, American Express), color (red, green, blue) etc. Machine learning algorithms can only understand and work with numerical values, so in order to use categorical variables in modeling, they need to be converted to numeric representations.

The most common approach for converting categorical variables to numeric format is known as one-hot encoding or dummy coding. In one-hot encoding, each unique category is represented as a binary variable that can take the value 0 or 1. For example, consider a categorical variable ‘Gender’ with possible values ‘Male’ and ‘Female’. We would encode this as:

Male = [1, 0]
Female = [0, 1]

In this representation, the feature vector will have two dimensions – one for ‘Male’ and one for ‘Female’. If an example is female, it will be encoded as [0, 1]. Similarly, a male example will be [1, 0].

This allows us to represent categorical information in a format that machine learning models can understand and work with. Some key things to note about one-hot encoding:

The number of dummy variables created will be one less than the number of unique categories. So for a variable with ‘n’ unique categories, we will generate ‘n-1’ dummy variables.

These dummy variables are usually added as separate columns to the original dataset. So the number of columns increases after one-hot encoding.

Exactly one of the dummy variables will be ‘1’ and rest ‘0’ for each example. This maintains the categorical information while mapping it to numeric format.

The dummy variable columns can then be treated as separate ordinal features by machine learning models.

One category needs to be omitted as the base level or reference category to avoid dummy variable trap. The effect of this reference category gets embedded in the model intercept.

Now, let’s look at an extended example to demonstrate the one-hot encoding process step-by-step:

Let’s consider a categorical variable ‘Color’ with 3 unique categories – Red, Green, Blue.

Original categorical data:

Example 1, Color: Red
Example 2, Color: Green
Example 3, Color: Blue

Steps:

Identify the unique categories – Red, Green, Blue

Create dummy variables/columns for each category

Column for Red
Column for Green
Column for Blue

Select a category as the base/reference level and exclude its dummy column

Let’s select Red as the reference level

Code other categories as 1 and reference level as 0 in dummy columns

Data after one-hot encoding:

Example 1, Red: 0, Green: 0, Blue: 0
Example 2, Red: 0, Green: 1, Blue: 0
Example 3, Red: 0, Green: 0, Blue: 1

We have now converted the categorical variable ‘Color’ to numeric dummy variables that machine learning models can understand and learn from as separate features.

This one-hot encoding process is applicable to any categorical variable with multiple classes. It allows representing categorical information in a numeric format required by ML algorithms, while retaining the categorical differences between classes. The dummy variables can then be readily used in modeling, feature selection, dimensionality reduction etc.

Some key advantages of one-hot encoding include:

It is a simple and effective approach to convert categorical text data to numeric form.

The categorical differences are maintained in the final numeric representation as dummy variables.

Dummy variables can be treated as nominal categorical variables in downstream modeling.

It scales well to problems with large number of categories by creating sparse feature vectors with mostly 0s.

Retains the option to easily convert back decoded categorical classes from model predictions.

It also has some disadvantages like increased dimensionality of the data after encoding and loss of any intrinsic ordering between categories. Techniques like targeted encoding and feature hashing can help alleviate these issues to some extent.

One-hot encoding is a fundamental preprocessing technique used widely to convert categorical textual features to numeric dummy variables – a requirement for application of most machine learning algorithms. It maintains categorical differences effectively while mapping to suitable numeric representations.

HOW CAN THE DATABASE APPLICATION BE DEPLOYED TO END USERS FOR FEEDBACK AND ENHANCEMENTS

Leave a reply

The first step in deploying the database application to end users is to ensure it is in a stable and complete state to be tested by others. All functionality should be implemented, bugs should be minimized, and performance should be adequate. It’s a good idea to do internal testing by other teams within the organization before exposing the application externally. This helps catch any major issues prior to sharing with end users.

Once internal testing is complete, the application needs to be prepared for external deployment. The deployment package should contain everything needed to install and run the application. This would include executables, configuration files, database scripts to set up the schema and seed data, documentation, and a readme file explaining how to get started. The deployment package is typically distributed as a downloadable file or files that can be run on the target system.

The next step is to determine the deployment strategy. Will it be a closed or controlled beta with a small number of selected users, or an open public beta? A controlled beta allows issues to be identified and fixed in a limited setting before widespread release, while an open beta garners broader feedback. The deployment strategy needs to be chosen based on the complexity of the application, goals of the beta period, and risk tolerance.

With the deployment package and strategy determined, it’s time to engage with users to participate in the beta. For a controlled beta, relevant people within the target user community should be directly contacted to request their participation. An open call for participation can also be used. When recruiting beta testers, it’s important to be clear about the purpose being feedback and testing rather than fully rolled-out production usage. Testers need to understand and accept that bugs may be encountered.

Each beta tester is provided with access to install and run the application from the deployment package. During onboarding, testers should be given documentation on application features and workflows, as well as guidelines on providing feedback. It’s useful to have testers sign a non-disclosure agreement and terms of use if it’s a controlled beta of an unreleased application.

With the application deployed, the feedback period begins. Testers use the application for its intended purposes, exploring features and attempting different tasks. They document any issues experienced, such as bugs, usability problems, missing features, or requests for enhancements. Feedback should be collected periodically through online questionnaires, interviews, support tickets, or other predefined mechanisms.

Throughout the beta, the development team monitors incoming feedback and works to address high priority problems. Fixes are deployed to testers as new versions of the application package. This continual feedback-implement-test cycle allows improvements to be made based on real-world usage experiences. As major issues are resolved, more testers may be onboarded to further stress test the application.

Once the feedback period ends, all input from testers is analyzed to finalize any outstanding work. Common feedback themes may indicate deeper problems or opportunities for enhancements. User experience metrics like task success rates and task completion times provide quantitative insights. The development team reviews all data to decide if the application is ready for general release, or if another beta cycle is needed.

When ultimately ready for launch, the final deployment package is published through appropriate channels for the intended user base. For example, a consumer-facing app would be released to Android and iOS app stores, while an enterprise product may be deployed through internal tools and support portals. Comprehensive documentation including setup guides, tutorials and product handbooks support the production rollout.

Deploying a database application to end users for testing and improvement is a structured process. It requires technical, process and communications work to carefully manage a productive feedback period, continually refine the product based on experiences, and validate readiness for production usage. The feedback obtained directly from target users is invaluable for creating a high quality application that genuinely meets real-world needs.