Unsupervised machine learning analysis to identify patterns of ICU medication use for fluid overload prediction.

INTRODUCTION: Intravenous (IV) medications are a fundamental cause of fluid overload (FO) in the intensive care unit (ICU); however, the association between IV medication use (including volume), administration timing, and FO occurrence remains unclear. METHODS: This retrospective cohort study included consecutive adults admitted to an ICU ≥72 hours with available fluid balance data. FO was defined as a positive fluid balance ≥7% of admission body weight within 72 hours of ICU admission. After reviewing medication administration record (MAR) data in three-hour periods, IV medication exposure was categorized into clusters using principal component analysis (PCA) and Restricted Boltzmann Machine (RBM). Medication regimens of patients with and without FO were compared within clusters to assess for temporal clusters associated with FO using the Wilcoxon rank sum test. Exploratory analyses of the medication cluster most associated with FO for medications frequently appearing and used in the first 24 hours was conducted. RESULTS: FO occurred in 127/927 (13.7%) of the patients enrolled. Patients received a median (IQR) of 31 (13-65) discrete IV medication administrations over the 72-hour period. Across all 47,803 IV medication administrations, ten unique IV medication clusters were identified with 121-130 medications in each cluster. Among the ten clusters, cluster 7 had the greatest association with FO; the mean number of cluster 7 medications received was significantly greater in patients in the FO cohort compared to patients who did not experience FO (25.6 vs.10.9. p<0.0001). 51 of the 127 medications in cluster 7 (40.2%) appeared in > 5 separate 3-hour periods during the 72-hour study window. The most common cluster 7 medications included continuous infusions, antibiotics, and sedatives/analgesics. Addition of cluster 7 medications to a prediction model with APACHE II score and receipt of diuretics improved the ability for the model to predict fluid overload (AUROC 5.65, p =0.0004). CONCLUSIONS: Using ML approaches, a unique IV medication cluster was strongly associated with FO. Incorporation of this cluster improved the ability to predict development of fluid overload in ICU patients compared with traditional prediction models. This method may be further developed into real-time clinical applications to improve early detection of adverse outcomes.

Analgesic Effect of Intraoperative Intravenous S(+)-Ketamine During Total Knee Arthroplasty Surgery: Study Protocol for a Randomized Controlled Clinical Trial.

BACKGROUND: Total knee arthroplasty (TKA) is currently the main treatment for end-stage knee disease. The number of cases of TKA in China increased from 53,880 in 2011 to 374,833 in 2019, representing a 5.9-fold increase. Moderate to severe pain often occurs after TKA, which seriously affects postoperative rehabilitation, patient satisfaction, and overall outcome. Multimodal analgesia is considered the ideal solution. Adequate postoperative analgesia can not only reduce pain, opioid consumption, and, consequently, opioid-related adverse events, but can also reduce the length of hospital stay and costs and improve rehabilitation and patient satisfaction. OBJECTIVE: Effective multimodal pain management in the early postoperative period is essential for anesthesiologists. Additional studies have demonstrated that a low-dose intravenous infusion of ketamine can be administered as an adjuvant drug to alleviate acute postoperative pain. Therefore, we aim to appraise the efficacy and safety of intraoperative intravenous injection of S(+)-ketamine to relieve acute pain after TKA in older patients. METHODS: This is a protocol for a randomized, placebo-controlled trial. A total of 144 participants aged 65 years and older undergoing TKA will be randomly allocated into the S(+)-ketamine and placebo groups in a 1:1 ratio. S(+)-ketamine or the placebo will be intravenously administered at 0.3 mg/kg/h during the operation by anesthesiologists. Blinded evaluation by trained investigators will be completed at 2 hours, 24 hours, and 48 hours after surgery. The primary outcome measure will be the numeric rating scale score at rest and movement at 24 hours after surgery. The secondary outcomes will include the numeric rating scale scores at rest and movement at 2 hours and 48 hours after surgery, the number of patients who require additional analgesics during the first 48 hours after operation, the total consumption of opioids or nonsteroid anti-inflammatory drugs during the first 48 hours after operation, and adverse events at 2, 24, and 48 hours after operation. RESULTS: The protocol was registered at Clinical Trials.gov on February 26, 2022. It was performed in accordance with the approved guidelines and regulations of the participating institutions. Recruitment began in April 2022. Data collection is expected to conclude in September 2024. Study completion is expected in December 2024. CONCLUSIONS: A randomized, controlled, clinical study was designed to observe the analgesic effect of intraoperative intravenous administration of a lower dose of S(+)-ketamine (0.3 mg/kg/h) in older patients after TKA surgery. The protocol will appraise the efficacy and safety of intraoperative intravenous injection of S(+)-ketamine to relieve acute pain after TKA in older patients who may benefit from the administration of S(+)-ketamine. TRIAL REGISTRATION: ClinicalTrials.gov NCT05289050; https://clinicaltrials.gov/ct2/show/NCT05289050. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/53063.

Early growth, development and allometry of glyphosate-resistant and susceptible Amaranthus palmeri in response to current and elevated temperature and CO2.

This study aimed to evaluate the influence of CO2 and temperature on glyphosate-resistant and susceptible biotypes of Amaranthus palmeri (Palmer amaranth) in terms of morphological development. Height (cm), stem diameter (cm), leaf area (cm2), number of leaves, leaf, stem, and root dry matter, plant volume (m3), as well as shoot-to-root allometry were evaluated. The Palmer amaranth biotypes were grown under four different scenarios: 1-low temperature (23/33 °C) and CO2 (410 ± 25 ppm); 2-low temperature (23/33 °C) and high CO2 (750 ± 25 ppm); 3-high temperature (26/36 °C) and low CO2 (410 ± 25 ppm); and 4-high temperature (26/36 °C) and CO2 (750 ± 25 ppm). Between CO2 and temperature, the majority of differences observed were driven by CO2 levels. Palmer amaranth grown under 750 ppm of CO2 was 15.5% taller, displayed 10% more leaf area (cm2), 18% more stem dry matter, and had a 28.4% increase in volume (m3) compared to 410 ppm of CO2. GA2017 and GA2020 were 18% and 15.5% shorter, respectively. The number of leaves was 27% greater for GA2005. Plant volume decreased in GA2017 (35.6%) and GA2020 (23.8%). The shoot-to-root ratio was isomeric, except at 14 and 21 DAT, where an allometric growth towards shoot development was significant. Palmer amaranth biotypes responded differently to elevated CO2, and the impacts of temperature need further investigation on weed physiology. Thus, environmental and genetic background may affect the response of glyphosate-resistant and susceptible populations to climate change scenarios.