An ensemble model for predicting dispositions of emergency department patients.

OBJECTIVE: The healthcare challenge driven by an aging population and rising demand is one of the most pressing issues leading to emergency department (ED) overcrowding. An emerging solution lies in machine learning's potential to predict ED dispositions, thus leading to promising substantial benefits. This study's objective is to create a predictive model for ED patient dispositions by employing ensemble learning. It harnesses diverse data types, including structured and unstructured information gathered during ED visits to address the evolving needs of localized healthcare systems. METHODS: In this cross-sectional study, 80,073 ED patient records were amassed from a major southern Taiwan hospital in 2018-2019. An ensemble model incorporated structured (demographics, vital signs) and pre-processed unstructured data (chief complaints, preliminary diagnoses) using bag-of-words (BOW) and term frequency-inverse document frequency (TF-IDF). Two random forest base-learners for structured and unstructured data were employed and then complemented by a multi-layer perceptron meta-learner. RESULTS: The ensemble model demonstrates strong predictive performance for ED dispositions, achieving an area under the receiver operating characteristic curve of 0.94. The models based on unstructured data encoded with BOW and TF-IDF yield similar performance results. Among the structured features, the top five most crucial factors are age, pulse rate, systolic blood pressure, temperature, and acuity level. In contrast, the top five most important unstructured features are pneumonia, fracture, failure, suspect, and sepsis. CONCLUSIONS: Findings indicate that utilizing ensemble learning with a blend of structured and unstructured data proves to be a predictive method for determining ED dispositions.

The accuracy of artificial intelligence used for non-melanoma skin cancer diagnoses: a meta-analysis.

BACKGROUND: With rising incidence of skin cancer and relatively increased mortality rates, an improved diagnosis of such a potentially fatal disease is of vital importance. Although frequently curable, it nevertheless places a considerable burden upon healthcare systems. Among the various types of skin cancers, non-melanoma skin cancer is most prevalent. Despite such prevalence and its associated cost, scant proof concerning the diagnostic accuracy via Artificial Intelligence (AI) for non-melanoma skin cancer exists. This study meta-analyzes the diagnostic test accuracy of AI used to diagnose non-melanoma forms of skin cancer, and it identifies potential covariates that account for heterogeneity between extant studies. METHODS: Various electronic databases (Scopus, PubMed, ScienceDirect, SpringerLink, and Dimensions) were examined to discern eligible studies beginning from March 2022. Those AI studies predictive of non-melanoma skin cancer were included. Summary estimates of sensitivity, specificity, and area under receiver operating characteristic curves were used to evaluate diagnostic accuracy. The revised Quality Assessment of Diagnostic Studies served to assess any risk of bias. RESULTS: A literature search produced 39 eligible articles for meta-analysis. The summary sensitivity, specificity, and area under receiver operating characteristic curve of AI for diagnosing non-melanoma skin cancer was 0.78, 0.98, & 0.97, respectively. Skin cancer typology, data sources, cross validation, ensemble models, types of techniques, pre-trained models, and image augmentation became significant covariates accounting for heterogeneity in terms of both sensitivity and/or specificity. CONCLUSIONS: Meta-analysis results revealed that AI is predictive of non-melanoma with an acceptable performance, but sensitivity may become improved. Further, ensemble models and pre-trained models are employable to improve true positive rating.

Impact of COVID-19 Pandemic on Emergency Department Volume and Acuity in Low Incidence Area: Taiwan's Experience in Three Hospitals.

Background: The decrease in emergency department (ED) patient visits during the COVID-19 pandemic was reported by various studies. Our study aimed to investigate whether a similar trend can be observed in a country with a low incidence of COVID-19 as well as the impact caused by the pandemic on ED patients in different triage levels and categories. Methods: This multicenter retrospective study collected data from three regional hospitals between March 2019 and December 2020. We evaluated the differences between patient volume, disease severity, and patient composition in ED before and after the COVID-19 pandemic among these hospitals. Results: There was a 23% reduction in ED patient volume in the urban hospital (hospital A) as well as a 16% reduction in suburban hospitals (hospitals B and C) during the pandemic period, respectively. The regression analysis showed a high correlation in the change in monthly patient volume among these hospitals. In terms of severity, there was a 24% reduction in ED visits with high severity levels (Taiwan Triage and Acuity Scale [TTAS] I, II) in hospital A, as well as 16% and 12% in hospitals B and C during the pandemic period, respectively. Similarly, there was a 23% reduction in ED visits with low severity levels (TTAS III, IV, V) in hospital A, as well as 20% and 16% in hospitals B and C during the pandemic period, respectively. In terms of patient types, there was a significant decline in non-traumatic adult patients (19%, 17%, and 10%), and pediatric patients (49%, 50%, and 46%) in hospitals A, B, and C, respectively. Conclusions: Despite the low incidence of COVID-19 in Taiwan, a decrease in total ED visits was still found during the pandemic, especially in non-trauma adult visits and pediatric visits. In addition, ED visits in both high and low severity levels decreased in these regional hospitals.

Effects of dietary Lactobacillus reuteri and Pediococcus acidilactici on the cultured water qualities, the growth and non-specific immune responses of Penaeus vannamei.

This study discussed the effects of two types of lactic acid bacteria, Lactobacillus reuteri (L. reuteri) and Pediococcus acidilactici (P. acidilactici), on the growth and nonspecific immunity of Penaeus vannamei (P. vannamei) and developed probiotic applications for shrimp cultivation. This study incorporated two types of lactic acid bacteria in shrimp feed through spraying. The shrimps were grouped according to the type and concentration of effective bacteria incorporated into their feed. This research was separated into 3 individual feeding treatment as control, L. reuteri (Lr groups) and P. acidilactici (Pa groups). The shrimp was feeding with 103, 105, and 107 cfu/feed (g) L. reuteri namely as Lr3, Lr5, and Lr7. The shrimp was feeding with 103, 105, and 107 cfu/feed (g) P. acidilactici were named Pa3, Pa5, and Pa7, respectively. Through 8 weeks of feeding, the results revealed that the use of shrimp feed incorporated with lactic acid bacteria did not cause negative effects on water quality. The testing items include ammonia-nitrogen concentration, nitrite-nitrogen concentration, and total vibrio count in the water. In addition, the lactic acid bacteria concentration in the water were in the range of 1.33 ± 0.58 × 101 to 9.77 ± 1.34 × 102 cfu/mL. Observations of the growth performance of the white shrimps after 8 weeks of feeding revealed that both bacteria were beneficial to shrimp growth. In particular, group Lr7 had the highest percentage weight gain (107.99 ± 3.92%), special growth rate (1.93 ± 0.07%), feed conversion ratio (3.34 ± 0.05), and survival rate (97.22 ± 4.81%). Furthermore, observations of the nonspecific immunity reactions of the white shrimps after 4 weeks of feeding indicated that on day 4, the total number of haemocyte in shrimps in groups Lr5, Lr7, Pa3, and Pa5 significantly increased. On days 1 and 4, the phenoloxidase activity and superoxide axion production rates of the Lr group and Ls group increased. This phenomenon was the most significant in group Lr7, and the effect continued until day 28. After day 7, the phagocytic rate of groups Lr5 and Lr7 significantly increased. In addition, Lr and Pa groups exhibited significant increases in the phagocytic index after days 4 and 14, respectively. This phenomenon was also the most significant in group Lr7.

The accuracy of machine learning approaches using non-image data for the prediction of COVID-19: A meta-analysis.

OBJECTIVE: COVID-19 is a novel, severely contagious disease with enormous negative impact on humanity as well as the world economy. An expeditious, feasible tool for detecting COVID-19 remains yet elusive. Recently, there has been a surge of interest in applying machine learning techniques to predict COVID-19 using non-image data. We have therefore undertaken a meta-analysis to quantify the diagnostic performance of machine learning models facilitating the prediction of COVID-19. MATERIALS AND METHODS: A comprehensive electronic database search for the period between January 1st, 2021 and December 3rd, 2021 was undertaken in order to identify eligible studies relevant to this meta-analysis. Summary sensitivity, specificity, and the area under receiver operating characteristic curves were used to assess potential diagnostic accuracy. Risk of bias was assessed by means of a revised Quality Assessment of Diagnostic Studies. RESULTS: A total of 30 studies, including 34 models, met all of the inclusion criteria. Summary sensitivity, specificity, and area under receiver operating characteristic curves were 0.86, 0.86, and 0.91, respectively. The purpose of machine learning models, class imbalance, and feature selection are significant covariates useful in explaining the between-study heterogeneity, in terms of both sensitivity and specificity. CONCLUSIONS: Our study findings show that non-image data can be used to predict COVID-19 with an acceptable performance. Further, class imbalance and feature selection are suggested to be incorporated whenever building models for the prediction of COVID-19, thus improving further diagnostic performance.

A modified cardiac triage strategy reduces door to ECG time in patients with ST elevation myocardial infarction.

Timely performing electrocardiography (ECG) is crucial for early detection of ST-elevation myocardial infarction (STEMI). For shortening door-to-ECG time, a chief complaint-based "cardiac triage" protocol comprising (1) raising alert among medical staff with bedside triage tags, and (2) immediate bedside ECG after focused history-taking was implemented at the emergency department (ED) in a single tertiary referral center. All patients diagnosed with STEMI visiting the ED between November 2017 and January 2020 were retrospectively reviewed to investigate the effectiveness of strategy before and after implantation. Analysis of a total of 117 ED patients with STEMI (pre-intervention group, n = 57; post-intervention group, n = 60) showed significant overall improvements in median door-to-ECG time from 5 to 4 min (p = 0.02), achievement rate of door-to-ECG time < 10 min from 45 to 57% (p = 0.01), median door-to-balloon time from 81 to 70 min (p < 0.01). Significant trends of increase in achievement rates for door-to-ECG and door-to-balloon times (p = 0.032 and p = 0.002, respectively) was noted after strategy implementation. The incidences of door-to-ECG time > 10 min for those with initially underestimated disease severity (from 90 to 10%, p < 0.01) and walk-in (from 29.2 to 8.8%, p = 0.04) were both reduced. In conclusion, a chief complaint-based "cardiac triage" strategy successfully improved the quality of emergency care for STEMI patients through reducing delays in diagnosis and treatment.

Physician-related factors associated with unscheduled revisits to the emergency department and admission to the intensive care unit within 72 h.

Investigation of physician-related causes of unscheduled revisits to the emergency department (ED) within 72 h with subsequent admission to the intensive care unit (ICU) is an important parameter of emergency care quality. Between 2012 and 2017, medical records of all adult patients who visited the ED and returned within 72 h with subsequent ICU admission were retrospectively reviewed by three experienced emergency physicians. Study parameters were categorized into "input" (Patient characteristics), "throughput" (Time spent on first ED visit and seniority of emergency physicians, and "output" (Charlson Comorbidity Index). Of the 147 patients reviewed for the causes of ICU admission, 35 were physician-related (23.8%). Eight belonged to more urgent categories, whereas the majority (n = 27) were less urgent. Patients who spent less time on their first ED visits before discharge (< 2 h) were significantly associated with physician-related causes of ICU admission, whereas there was no significant difference in other "input," "throughput," and "output" parameters between the "physician-related" and "non-physician-related" groups. Short initial management time was associated with physician-related causes of ICU admission in patients with initial less urgent presentations, highlighting failure of the conventional triage system to identify potentially life-threatening conditions and possibility of misjudgement because of the patients' apparently minor initial presentations.

The Effect of Processing Donor Milk on Its Nutrient and Energy Content.

Background: The pasteurization is a mandatory step to inactivate pathogenic microorganisms of bank milk. For storage, freezing and thawing are necessary. The concentration of macronutrients and energy of bank milk could be influenced by these procedures which are routinely used in human milk bank. Research Aim: The aim of this study is to analyze the effect of bank milk processing (pasteurization and freezing/thawing) on the macronutrients (fat, protein, and carbohydrate) concentration and energy content. Materials and Methods: The samples of donor milk were collected and studied before/after pasteurization and after frozen for 3 months. Total 100 samples of bank milk were tested using an infrared analyzer. The measurements of fat, protein, carbohydrate, and energy were statistically analyzed by SPSS. Results: There was a prominent reduction of fat mean concentration following pasteurization and frozen (20.5% and 6.5%, respectively). The processing did not cause significant changes in protein content, but there were significant increase after pasteurization and decrease after frozen in carbohydrate (p < 0.05). Overall (postpasteurization and frozen storage), a 9.6% decrease was observed for energy content. Conclusion: This study revealed that the processing of bank milk (including Holder Pasteurization and frozen storage) decreased fat and energy content of human milk significantly, and this could not meet the specific needs of preterm infants.

Alternative Motor Task-Based Pattern Training With a Digital Mirror Therapy System Enhances Sensorimotor Signal Rhythms Post-stroke.

Mirror therapy (MT) facilitates motor learning and induces cortical reorganization and motor recovery from stroke. We applied the new digital mirror therapy (DMT) system to compare the cortical activation under the three visual feedback conditions: (1) no mirror visual feedback (NoMVF), (2) bilateral synchronized task-based mirror visual feedback training (BMVF), and (3) reciprocal task-based mirror visual feedback training (RMVF). During DMT, EEG recordings, including time-dependent event-related desynchronization (ERD) signal amplitude in both mu and beta bands, were obtained from the standard C3 (ispilesional hemisphere, IH), C4 (contralesional hemisphere, CH), and Cz scalp sites (supplementary motor area, SMA). The entire ERD curve was separated into three time-phases: P0 (-2 to 0 s), P1 (0 to 2 s), and P2 (2 to 4 s). Four-way and subsequent repeated-measures analyses of variance were used to examine the effects of group (stroke vs. control group), test condition (NoMVF, BMVF, and RMVF), time-phase (P0, P1, and P2), and brain area (IH, CH, SMA) on the ERD areas (%) in mu and beta bands. For the mu band, generally, ERD areas (%) were larger in the control than in the stroke group. The ERD areas (%) were largest under the RMVF condition, followed by BMVF and NoMVF conditions. Similar results were found in the beta bands. The main effects of group, time-phase, and test condition on the ERD areas (%) were significant for the three brain areas, except the main effect of group in the SMA (Cz) and CH (C4) brain area. The ERD areas (%) were larger in the control than in the stroke group. The ERD area (%) was significantly larger during P1 than during P0 and P2 (ps < 0.02), and during P2 than during P0 (ps < 0.01). The ERD area (%) under the RMVF condition was significantly larger than that under the BMVF condition and NoMVF condition (ps < 0.05). The present study suggests that cortical activation particularly in the SMA (Cz) of the brain increases in the RMVF condition in both healthy subjects and stroke patients. This result supports the hypothesis that stroke patients may benefit from RMVF training.

Low-intensity-ultrasound-accelerated nerve regeneration using cell-seeded poly(D,L-lactic acid-co-glycolic acid) conduits: an in vivo and in vitro study.

This study investigated the effects of low intensity ultrasound on seeded Schwann cells within poly(DL-lactic acid-co-glycolic acid) (PLGA) conduits by in vitro and in vivo trials for peripheral nerve regeneration. The possible differences in the ultrasonic effects when using biodegradable and non-biodegradable materials as the conduits were also studied, using silicone rubber tubes as comparisons. In the in vitro study, seeded Schwann cells were cultured in serum deprivation culture medium that simulated the environment of mechanical trauma on injury nerve site. After 12, 24, and 48 h, only the PLGA conduit groups exposed to 0.05 W/cm(2), 3 min/treatment of ultrasound exhibited decreased LDH release and increased MTT values compared to the sham groups. Based on the results of the in vitro experiment in LDH and MTT testing, the silicone conduits with seeded Schwann cells group was ignored in the in vivo study. The PLGA nerve conduits seeded with Schwann cells (9 x 10(3) cells) were implanted to 15-mm right sciatic nerve defects in rats. Each conduit received 12 ultrasonic treatment sessions over 2 weeks after 1 day of rest. Ultrasound was applied as follows: frequency, 1MHz; intensity, 0.3 W/cm(2) (SATP); treatment, 5 min/day. Implanted graft specimens were harvested for histological analysis at 8 weeks following surgery. PLGA groups (with and without Schwann cells) treated with pulsed ultrasonic stimulation were found to have significantly greater number and area of regenerated axons at the mid-conduit of implanted grafts, as compared to the sham groups. Ultrasonic stimulation on silicone groups was found to induce a mass of fibrous tissues that covered the nerve conduits and retarded axon regeneration.