Dissatisfaction-considered waiting time prediction for outpatients with interpretable machine learning.

Long waiting time in outpatient departments is a crucial factor in patient dissatisfaction. We aim to analytically interpret the waiting times predicted by machine learning models and provide patients with an explanation of the expected waiting time. Here, underestimating waiting times can cause patient dissatisfaction, so preventing this in predictive models is necessary. To address this issue, we propose a framework considering dissatisfaction for estimating the waiting time in an outpatient department. In our framework, we leverage asymmetric loss functions to ensure robustness against underestimation. We also propose a dissatisfaction-aware asymmetric error score (DAES) to determine an appropriate model by considering the trade-off between underestimation and accuracy. Finally, Shapley additive explanation (SHAP) is applied to interpret the relationship trained by the model, enabling decision makers to use this information for improving outpatient service operations. We apply our framework in the endocrinology metabolism department and neurosurgery department in one of the largest hospitals in South Korea. The use of asymmetric functions prevents underestimation in the model, and with the proposed DAES, we can strike a balance in selecting the best model. By using SHAP, we can analytically interpret the waiting time in outpatient service (e.g., the length of the queue affects the waiting time the most) and provide explanations about the expected waiting time to patients. The proposed framework aids in improving operations, considering practical application in hospitals for real-time patient notification and minimizing patient dissatisfaction. Given the significance of managing hospital operations from the perspective of patients, this work is expected to contribute to operations improvement in health service practices.

Risk of Hyponatremia after Tramadol/Acetaminophen Single-Pill Combination Therapy: A Real-World Study Based on the OMOP-CDM Database.

BACKGROUND AND OBJECTIVE: Tramadol has been reported to cause hyponatremia but the evidence is conflicting. The risk of hyponatremia resulting from combination oral tramadol/acetaminophen (TA) therapy is thus unknown. This study examined whether, compared with acetaminophen (AA), TA use is associated with an increased risk of hyponatremia. METHODS: Hospital data compatible with the Observational Medical Outcomes Partnership-Common Data Model (OMOP-CDM; version 5.3) for 30,999 patients taking TA or AA from 2011 through 2020 were analyzed. New-onset hyponatremia was defined as a serum sodium level < 135 mEq/L within 10 days after drug initiation. The incidence rate ratio was calculated based on crude and 1:1 propensity-score-matched models. Subgroup analyses compared patients taking TA extended-release (TA-ER) and TA immediate-release (TA-IR) formulations. RESULTS: Among the 30,999 patients, 12,122 (39.1%) were aged > 65 years and 16,654 (53.7%) were male. Hyponatremia within 10 days developed in 1613 (8.4%) of the 19,149 patients in the TA group; the incidence rate was higher than in the AA group (4.2%; 493 out of 11,850 cases). In the propensity-score-matched model, the incidence rate of hyponatremia in the TA group was 6.8 per 1000 person-days (PD), which was 1.57-fold (1.31, 1.89) higher than that in the AA group (4.3 per 1000 PD). In both the crude and propensity-score-matched models, the incidence rate of hyponatremia was significantly higher in the TA-ER than TA-IR subgroup. CONCLUSION: In this real-world study, hyponatremia was more frequently observed in the TA than AA group, and in the TA-ER than TA-IR subgroup. Therefore, it is imperative to prescribe tramadol cautiously and closely monitor electrolyte levels.

Process Mining-Supported Emergency Room Process Performance Indicators.

Emergency room processes are often exposed to the risk of unexpected factors, and process management based on performance measurements is required due to its connectivity to the quality of care. Regarding this, there have been several attempts to propose a method to analyze the emergency room processes. This paper proposes a framework for process performance indicators utilized in emergency rooms. Based on the devil's quadrangle, i.e., time, cost, quality, and flexibility, the paper suggests multiple process performance indicators that can be analyzed using clinical event logs and verify them with a thorough discussion with clinical experts in the emergency department. A case study is conducted with the real-life clinical data collected from a tertiary hospital in Korea tovalidate the proposed method. The case study demonstrated that the proposed indicators are well applied using the clinical data, and the framework is capable of understanding emergency room processes' performance.

Electroacupuncture as a complement to usual care for patients with non-acute pain after back surgery: a study protocol for a pilot randomised controlled trial.

INTRODUCTION: Recurrent or persistent low back pain is common after back surgery but is typically not well controlled. Previous randomised controlled trials on non-acute pain after back surgery were flawed. In this article, the design and protocol of a randomised controlled trial to treat pain and improve function after back surgery are described. METHODS AND ANALYSIS: This study is a pilot randomised, active-controlled, assessor-blinded trial. Patients with recurring or persistent low back pain after back surgery, defined as a visual analogue scale value of ≥50 mm, with or without leg pain, will be randomly assigned to an electroacupuncture-plus-usual-care group or to a usual-care-only group. Patients assigned to both groups will have usual care management, including physical therapy and patient education, twice a week during a 4-week treatment period that would begin at randomisation. Patients assigned to the electroacupuncture-plus-usual-care group will also have electroacupuncture twice a week during the 4-week treatment period. The primary outcome will be measured with the 100 mm pain visual analogue scale of low back pain by a blinded evaluator. Secondary outcomes will be measured with the EuroQol 5-Dimension and the Oswestry Disability Index. The primary and secondary outcomes will be measured at 4 and 8 weeks after treatment. ETHICS AND DISSEMINATION: Written informed consent will be obtained from all participants. This study was approved by the Institutional Review Board (IRB) of Pusan National University Korean Hospital in September 2013 (IRB approval number 2013012). The study findings will be published in peer-reviewed journals and presented at national and international conferences. TRIAL REGISTRATION NUMBER: This trial was registered with the US National Institutes of Health Clinical Trials Registry: NCT01966250.

Enhancement of primary neuronal cell proliferation using printing-transferred carbon nanotube sheets.

Artificial nerve guidance conduits (aNGCs) prepared from polymer scaffolds and carbon nanotubes (CNTs) possess unique chemical and physical properties, and have been widely used in preclinical trials to promote neuronal differentiation and growth. However, there have been only a few reports on the clinical applicability of CNT sheets for proliferation of primary neuronal cells due to safety concerns. The present study assesses the ability and potential applicability of multiwalled CNTs (MWNTs) composited with polydimethylsiloxane (PDMS) sheets to promote and enhance the proliferation of primary neuronal cells. In this study, the aqueous MWNT dispersion was filtered, and the PDMS/MWNT sheets were prepared using a simple printing transfer method. Characterization of PDMS/MWNT sheets demonstrated their unique physical properties such as superior mechanical strength and electroconductivity when compared with PDMS sheets. The effect of the PDMS/MWNT sheets on the neural cell proliferation and cytotoxicity was evaluated using MTT and alamar blue assays. Our results indicate the viability and proliferation of primary neuronal cells and Schwann cells in PDMS/MWNT sheets increased over twice when compared with a noncoated dish that is not usual in the primary neuronal cell growth control (p < 0.05). In addition, PDMS/MWNT sheets enhanced the adhesion and viability of the cells compared with poly-l-lysine coated dishes, which are most commonly used for improving cell adherence. Additionally, the PDMS/MWNT sheets exhibited excellent biocompatibility for culturing neuronal and Schwann cells. Overall, all assessments indicate that PDMS/MWNT sheets are ideal candidates for the development of artificial nerve conduits for clinical use following peripheral nerve injury.

Reduction of ischemia-induced cerebral injury by all-trans-retinoic acid.

Ischemia-induced cerebral injury evolves over a longer period than previously believed through post-ischemic inflammation. Retinoic acid (RA) has been shown to exert cytoprotective effects on several cells, but its effects on ischemia-induced cerebral injury have been poorly characterized. The aim of the present study was to examine the effects of all-trans-RA on ischemia-induced cerebral injury and elucidate the underlying mechanism. All-trans-RA treatment reduced the size of the ischemia-induced cerebral infarct. To elucidate the underlying mechanism, ischemia-induced cerebral inflammation was studied by examination of expressions of interleukin 1beta (IL-1beta) and ED-1. RA treatment significantly reduced the cerebral inflammation. Moreover, cerebral ischemic induction of cyclooxygenase-2 (COX-2) and CCAAT/enhancer binding protein beta (C/EBPbeta), which binds to the COX-2 promoter, was also inhibited by RA. These results suggest that RA can reduce ischemia-induced cerebral injury by an anti-inflammatory action, which may be effected via inhibition of C/EBPbeta-mediated COX-2 induction.