Modern Intensive Care Units (ICUs) provide continuous monitoring of critically ill patients susceptible to many complications affecting morbidity and mortality. ICU settings require a high staff-to-patient ratio and generates a sheer volume of data. For clinicians, the real-time interpretation of data and decision-making is a challenging task. Machine Learning (ML) techniques in ICUs are making headway in the early detection of high-risk events due to increased processing power and freely available datasets such as the Medical Information Mart for Intensive Care (MIMIC). We conducted a systematic literature review to evaluate the effectiveness of applying ML in the ICU settings using the MIMIC dataset. A total of 322 articles were reviewed and a quantitative descriptive analysis was performed on 61 qualified articles that applied ML techniques in ICU settings using MIMIC data. We assembled the qualified articles to provide insights into the areas of application, clinical variables used, and treatment outcomes that can pave the way for further adoption of this promising technology and possible use in routine clinical decision-making. The lessons learned from our review can provide guidance to researchers on application of ML techniques to increase their rate of adoption in healthcare.

Infusion-related iatrogenic retinal breaks (IRBs) are a significant complication in vitrectomies, particularly when smaller-gauge cannulas are used during fluid infusion. Using two-dimensional finite element analysis (FEA), we analyzed forces exerted on the retina from different cannulas: traditional 25-gauge, 20-gauge, 23-gauge, and 27-gauge, then investigated four alternative new cannula designs: (A) oblique orifices, (B) external obstruction, (C) side ports, and (D) perpendicular orifices. The analysis revealed that the standard 25-gauge cannula had a force of 0.546 milli-Newtons (mN). Optimized cannulas demonstrated decreased forces: 0.072 mN (A), 0.266 mN (B), 0.417 mN (C), and 0.117 mN (D). While all the designs decrease fluid jet force, each has unique challenges: Design A may complicate manufacturing, B requires unique attachment techniques, C could misdirect fluid toward the lens and peripheral retina, and D requires a sealed trocar/cannula design to prevent unwanted fluid ejection. These four innovative cannula designs, identified with detailed engineering simulations, provide promising strategies to reduce the risk of IRBs during vitrectomy, bridging the gap between engineering insights and clinical application.

Background: Telemedicine (TM) usage increased rapidly during the COVID-19 pandemic. This study is part of a larger mixed-methods study comparing TM and in-person visits of older adults with heart failure (HF) and describes patient’s TM experiences during the pandemic. Methods: This study employed qualitative design using survey responses and individual interviews. Study eligibility requirements included >55 years old, HF diagnosis, and TM visit between September 1, 2020 and May 31, 2021, at one of two participating health systems in the southern United States. Results: Twenty-two TM recipients completed qualitative interviews, and 91 of 125 online survey respondents answered open-ended questions. Data were gathered, sorted, and revealed five themes. Discussion: Interview respondents identified benefits, e.g., convenience, inclusion, decreased exposure, and problems, e.g., connectivity issues, inadequate equipment, and medical conditions impacting use. Recommendations included allocating sufficient appointment time, tailoring visits, and increasing written communication. This study was part of a larger clinical trial registered at ClinicalTrials.gov: NCT04304833.