EasyMed Mobile Application

Lingshuang Kong：This insight comes from our visit to the geriatrics department at UCSD Health Medicine, as the physicians told us that many older adults are taking many drugs and they are often concerned about the medical complications and potential interactions. However, the doctor often lacks time to explain every detail to the patients and they also have trouble managing the drugs prescribed by different doctors. To ease the concerns of many older adults or patients who are taking multiple drugs at the same time and reduce the workload for physicians, we decided to design an easily accessible mobile app - EasyMed to help them check any potential drug or food interactions.

Yumei Feng: Our primary focus in designing this work is to bridge the gap between medical practitioners and the general population. Our research revealed that doctors often lack the time to provide comprehensive explanations and thoroughly check all medications while understanding patients' medical histories, leading to misunderstandings and adverse drug reactions. We aim to enhance communication and empowerment, particularly for the elderly who are vulnerable to medication errors, by providing an accessible tool for managing medications safely. Additionally, we strive to empower the general public with knowledge, promote medication safety, and improve health literacy. Our goal is to ensure patients understand their medication regimens, make informed healthcare decisions, and experience peace of mind.

Lingshuang Kong: There are a couple of things we want to do for EasyMed including further improving the model, iterating on the features, and conducting more user testing. Although the model we used is already close to the highest standard in the industry, we still want to improve the reliability and accuracy of the algorithm through further iteration to ensure we are giving more trustable results to the users. From user research, we also realized that dosage information is important for analyzing drug interactions so we also want to further train our model with this parameter. Through user research, we also learned that doctors and patients use medical record systems like Mychart a lot so we also want to possibly integrate our app with it to improve user experience. In conclusion, the submission of the project doesn’t mark the end of our exploration, we would like to carry this project further and possibly launch it in the Google Store and develop the IOS version in the future so it can benefit more people.

The development journey behind achieving a 93% accuracy rate in drug interaction detection for EasyMed involved a combination of rigorous data processing, machine learning models, and domain expertise.Initially, our focus was on building a comprehensive and reliable database that included not only drug-drug interactions but also drug-food interactions. This required extensive collaboration with healthcare professionals and pharmacists to curate and verify data from multiple authoritative sources. Given the vast and continuously evolving nature of medical information, one of the primary technical challenges was managing data quality and consistency.To tackle this, we leveraged a hybrid approach combining traditional rule-based algorithms with machine learning techniques. The rule-based system allowed us to encode well-known, clinically validated interactions, while machine learning models, particularly Natural Language Processing (NLP), helped us detect more nuanced or less documented interactions from medical literature and reports.A significant breakthrough was optimizing our models to handle large-scale datasets efficiently. We developed a custom data preprocessing pipeline that reduced redundancy and noise, which improved the training process and accuracy of our predictions. Additionally, we implemented a dynamic update mechanism, enabling our database to stay current with the latest drug information without compromising system performance.Collaboration within the team was key in overcoming these challenges. We had frequent iterations, testing, and validation phases to ensure robustness. Our interdisciplinary team, including data scientists, software engineers, and medical experts, played a crucial role in refining the model, leading to the 93% accuracy rate.This journey underscored the importance of combining technological innovation with domain-specific knowledge, ultimately allowing EasyMed to provide users with reliable, real-time drug interaction checks, thereby enhancing medication safety and adherence.

Our decision to focus on polypharmacy risks in the EasyMed Mobile Application was driven by a deep awareness of the challenges faced by older adults, a demographic that is often overlooked in digital healthcare solutions.Globally, over 500 million older adults are at a higher risk of adverse drug interactions due to polypharmacy, as they are frequently prescribed multiple medications to manage chronic conditions. The inspiration for EasyMed came from recognizing this growing healthcare challenge, especially as medication regimens become more complex with age. Our team wanted to create a solution that could empower older adults and their caregivers to manage medications more safely and independently, reducing the risk of harmful interactions.Understanding the specific needs of this demographic significantly influenced our design decisions. We prioritized user-friendliness and accessibility, ensuring the interface was intuitive and straightforward. This involved incorporating larger text sizes, high-contrast visuals, and voice-assisted functionalities to accommodate users with visual impairments or limited dexterity. We also added a simplified onboarding process with step-by-step guidance to make the app approachable, even for those who may not be tech-savvy.Moreover, we integrated personalized medication reminders and easy-to-understand interaction alerts, which were essential for enhancing adherence and safety. Our AI technology is designed to provide clear, actionable insights, avoiding medical jargon so users can quickly grasp the significance of potential drug-drug or drug-food interactions.By focusing on polypharmacy risks, EasyMed not only supports the health and well-being of older adults but also contributes to reducing the burden on healthcare systems by preventing medication-related complications. This user-centered approach has been fundamental to our mission of making healthcare more inclusive and accessible for everyone, especially vulnerable populations.

Creating an inclusive user experience for the EasyMed Mobile Application required a thoughtful balance between accessibility and sophisticated AI functionality. Our goal was to ensure that users, especially older adults, could easily navigate the app while benefiting from its advanced AI-powered drug interaction detection.From the start, we prioritized accessibility by integrating age-friendly design principles. We chose legible fonts with adjustable sizes, ensuring readability across different devices. To accommodate users with visual impairments, including color blindness, we implemented a high-contrast, color-blind friendly palette for reduced eye strain.Balancing these accessibility features with sophisticated AI functionality was a key challenge. We focused on making the AI-driven insights intuitive and user-friendly. For instance, instead of overwhelming users with complex medical data, the app translates AI findings into simple, clear language with actionable recommendations. Users receive easy-to-understand alerts and interaction summaries that help them make informed decisions about their medication regimens.Our team also incorporated a streamlined, guided onboarding process to familiarize users with the app’s capabilities. We tested the design with real users, including older adults, to refine the interface based on their feedback. This iterative testing process helped us strike the right balance between advanced AI features and a seamless, accessible user experience.Ultimately, by focusing on inclusivity and accessibility, we ensured that EasyMed not only provides powerful AI-driven drug interaction detection but also empowers users of all ages to take control of their medication safety with confidence and ease.