Browsing by Author "Buckland, Daniel M"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Development, Deployment, and Implementation of a Machine Learning Surgical Case Length Prediction Model and Prospective Evaluation.
    (Annals of surgery, 2023-06) Zaribafzadeh, Hamed; Webster, Wendy L; Vail, Christopher J; Daigle, Thomas; Kirk, Allan D; Allen, Peter J; Henao, Ricardo; Buckland, Daniel M

    Objective

    Implement a machine learning model using only the restricted data available at case creation time to predict surgical case length for multiple services at different locations.

    Background

    The Operating Room (OR) is one of the most expensive resources in a health system, estimated to cost $22-133 per minute and generate about 40% of the hospital revenue. Accurate prediction of surgical case length is necessary for efficient scheduling and cost-effective utilization of the OR and other resources.

    Methods

    We introduced a similarity cascade to capture the complexity of cases and surgeon influence on the case length and incorporated that into a gradient boosting machine learning model. The model loss function was customized to improve the balance between over- and under-prediction of the case length. A production pipeline was created to seamlessly deploy and implement the model across our institution.

    Results

    The prospective analysis showed that the model output was gradually adopted by the schedulers and outperformed the scheduler-predicted case length in Aug-Dec 2022. In 33,815 surgical cases across outpatient and inpatient platforms, the operational implementation predicted 11.2% fewer under-predicted cases and 5.9% more cases within 20% of the actual case length compared with the schedulers and only over-predicted 5.3% more. The model assisted schedulers to predict 3.4% more cases within 20% of the actual case length and 4.3% fewer under-predicted cases.

    Conclusions

    We created a unique framework that is being leveraged every day to predict surgical case length more accurately at case posting time and could be potentially utilized to deploy future machine learning models.
  • Thumbnail Image
    ItemOpen Access
    Effect of language interpretation modality on throughput and mortality for critical care patients: A retrospective observational study
    (Journal of the American College of Emergency Physicians Open, 2021-08) Oca, Siobhan R; Navas, Angelo; Leiman, Erin; Buckland, Daniel M
  • Thumbnail Image
    ItemOpen Access
    Estimating medical risk in human spaceflight.
    (NPJ microgravity, 2022-03-31) Antonsen, Erik L; Myers, Jerry G; Boley, Lynn; Arellano, John; Kerstman, Eric; Kadwa, Binaifer; Buckland, Daniel M; Van Baalen, Mary
    NASA and commercial spaceflight companies will soon be retuning humans to the Moon and then eventually sending them on to Mars. These distant planetary destinations will pose new risks-in particular for the health of the astronaut crews. The bulk of the evidence characterizing human health and performance in spaceflight has come from missions in Low Earth Orbit. As missions last longer and travel farther from Earth, medical risk is expected to contribute an increasing proportion of total mission risk. To date, there have been no reliable estimates of how much. The Integrated Medical Model (IMM) is a Probabilistic Risk Assessment (PRA) Monte-Carlo simulation tool developed by NASA for medical risk assessment. This paper uses the IMM to provide an evidence-based, quantified medical risk estimate comparison across different spaceflight mission durations. We discuss model limitations and unimplemented capabilities providing insight into the complexity of medical risk estimation for human spaceflight. The results enable prioritization of medical needs in the context of other mission risks. These findings provide a reasonable bounding estimate for medical risk in missions to the Moon and Mars and hold value for risk managers and mission planners in performing cost-benefit trades for mission capability and research investments.