Following the success of our previous UBRITE data science hackathons organized by the UAB Informatics Institute (2019, 2020, 2021, 2022), we are planning to run our 2023 Hackathon virtually from September 9-10, 2023, in collaboration with the Center for Clinical and Translational Science. We hope to encourage more UAB and non-UAB participants to take advantage of this opportunity to have fun by networking with peers in the scientific community and by participating on multidisciplinary teams to learn new skills and execute goals for novel project proposals.
The title this year is Intelligent Safety: Pioneering Patient Safety Solutions with AI/ML and Data Science. Intelligent Safety is a cutting-edge hackathon event aimed at revolutionizing patient safety through the power of machine learning, artificial intelligence, and data science. The event challenges participants to utilize these technologies to identify ways to prevent, detect, and address factors that affect patient safety in various focus areas, including medication errors, diagnostic errors, lapses in care, infections, and procedural/surgical errors. The high-level goals of Intelligent Safety are to improve patient safety and drive innovation in the use of health data.
This year, the hackathon will again be virtual via Zoom. Participants from any institution or organization are welcome to participate as team members or team leaders.
Registration is on a first-come, first-served basis. Don’t miss your chance to participate this year, so please register as a participant or submit project proposals by August 25, 2023. Prior participants are encouraged to register early.
To see the schedule for Hackathon 2023 Click here
In general, biomedical hackathons are driven by practical sessions where people from multidisciplinary backgrounds gather, discuss, and implement ideas and projects during intensive and productive coding sessions.
The theme for this year is Intelligent Safety: Pioneering Patient Safety Solutions with AI/ML and Data Science. We are excited about the opportunity to focus on using clinical data to improve quality and safety in healthcare. Clinical data are heterogenous and can present many challenges, such as availability, security, confidentiality, and de-identification. However, analyzing such data using artificial intelligence and machine learning can reveal novel patterns and trends. Studying these patterns can lead to new knowledge that can improve individual and population health.
There are many publicly available sources of health data, including de-identified data from real care settings as well as synthetic data. Electronic health record (EHR) systems include clinical entities, such as diagnoses, procedures, medications, allergies, medical devices, the care team, and adverse events. Quality metrics, such as times for encounters, procedures, and tasks in the EHR, provide information about workflow. There are also complex data such as genomic data, images (e.g., from x-rays and MRI scans, pathology, dermatology, retinal imaging), and waveforms (such from heart, brain, and blood pressure monitoring). In addition to EHR data, government databases contain public health data on statistics on location, demographics, socioeconomic status, diseases, hospitalizations, and deaths. Such data rose to great prominence during the Covid-19 pandemic.
In this hackathon, we’ll prepare participants with UAB’s high-performance biomedical research computing environment called U-BRITE, help participants prepare or gain access to a wide variety of health datasets, and provide training and mentoring on analysis software tools.
- Broaden the collaborative community and foster collaboration and innovation in patient safety by building teams of domain experts, scientists/researchers, and developers in the fields of machine learning, artificial intelligence, and data science.
- Enable teams to achieve outcomes, such as scripted pipelines, tools, tutorials, and novel analyses to identify actionable, and impactful solutions to prevent, identify, and address patient safety issues in healthcare.
- Encourage the development of novel research questions and hypotheses for future work in addressing patient safety.
- Strengthen the professional development of participants by providing opportunities for training, mentoring, and networking.
Participants and teams can choose one of the following focus areas for their projects:
- Medication Errors
- Diagnostic Errors
- Lapses in Care
- Procedural/Surgical Errors
Everyone including students, principal investigators, post-docs, staff scientists, clinicians, etc. is encouraged to participate. This hackathon does not require prior programming experience. We hope to have participants from backgrounds including but not limited to health care, patient safety, quality improvement, public health, biomedical science, computer science, genomics, genetics, developmental biology, biochemistry, neuroscience, health informatics, biomedical engineering, software development, microbiology, pathology, etc. While participants from outside UAB may participate, at least one member of each team must be affiliated with UAB or a partner organization.
JUDGING AND AWARDS
There will be awards for First Place ($2,000), Second Place ($1,500), and Third Places ($1,000), as well as a People’s Choice Award and a Team Science Award. A panel of experts will evaluate all projects
Core criteria for all awards:
Does the project address an important problem or a critical barrier to progress in the field? Is the prior research that serves as the key support for the proposed project rigorous? If the aims of the project are achieved, how will scientific knowledge, technical capability, and/or clinical practice be improved? How will successful completion of the aims change the concepts, methods, technologies, treatments, services, or preventative interventions that drive this field?
Are the team members well suited to the project? Do the investigators have complementary and integrated expertise? Is at least one team member affiliated with a participating or sponsoring organization (e.g., CTSA).
Does the application challenge and seek to shift current research or clinical practice paradigms by utilizing novel theoretical concepts, approaches or methodologies, instrumentation, or interventions? Are the concepts, approaches or methodologies, instrumentation, or interventions novel to one field of research or novel in a broad sense? Is a refinement, improvement, or new application of theoretical concepts, approaches or methodologies, instrumentation, or interventions proposed?
Are the overall strategy, methodology, and analyses well-reasoned and appropriate to accomplish the specific aims of the project? Have the investigators included plans to address weaknesses in the rigor of prior research that serves as the key support for the proposed project? Have the investigators presented strategies to ensure a robust and unbiased approach, as appropriate for the work proposed? Are potential problems, alternative strategies, and benchmarks for success presented? Will the strategy establish feasibility, and will particularly risky aspects be managed? Have the investigators presented adequate plans to address relevant biological variables, such as age, gender, and risk factors?
Scientific Rigor and Progress
Has the team presented prior work and cited appropriate scientific literature? Have they presented the current state of the problem and current challenges? Given the baseline, how much progress has the team made in addressing challenges during the hackathon? Are there clear plans for future work?
Integrity, Transparency, and Sharing
Have investigators used tools, datasets, and other resources that are publicly available? Have they agreed to share their findings (once published)? Do their work product and artifacts seem appropriate for the project, length of available time, and level of expertise? Are there any red flags?
How well have the reviewers presented their work? Please consider the quality of visuals, communication skills, and clarity and conciseness in the presentation.
Reviewers will provide an overall impact score to reflect their assessment of the likelihood for the project to exert a sustained, powerful influence on the research field(s) involved, in consideration of the following review criteria and additional review criteria (as applicable for the project).
Team Science Award – How well does the team demonstrate the following characteristics?
- Interdisciplinary, with diverse fields and areas of expertise
- Members across the translational spectrum
- Multiple institutions
- Different career stages (e.g., students, fellows, faculty, staff)
- Significant contributions from all members in the research, work, and presentation