Constructing and implementing a performance evaluation indicator set for artificial intelligence decision support systems in pediatric outpatient clinics: an observational study.

Artificial intelligence (AI) decision support systems in pediatric healthcare have a complex application background. As an AI decision support system (AI-DSS) can be costly, once applied, it is crucial to focus on its performance, interpret its success, and then monitor and update it to ensure ongoing success consistently. Therefore, a set of evaluation indicators was explicitly developed for AI-DSS in pediatric healthcare, enabling continuous and systematic performance monitoring. The study unfolded in two stages. The first stage encompassed establishing the evaluation indicator set through a literature review, a focus group interview, and expert consultation using the Delphi method. In the second stage, weight analysis was conducted. Subjective weights were calculated based on expert opinions through analytic hierarchy process, while objective weights were determined using the entropy weight method. Subsequently, subject and object weights were synthesized to form the combined weight. In the two rounds of expert consultation, the authority coefficients were 0.834 and 0.846, Kendall's coordination coefficient was 0.135 in Round 1 and 0.312 in Round 2. The final evaluation indicator set has three first-class indicators, fifteen second-class indicators, and forty-seven third-class indicators. Indicator I-1(Organizational performance) carries the highest weight, followed by Indicator I-2(Societal performance) and Indicator I-3(User experience performance) in the objective and combined weights. Conversely, 'Societal performance' holds the most weight among the subjective weights, followed by 'Organizational performance' and 'User experience performance'. In this study, a comprehensive and specialized set of evaluation indicators for the AI-DSS in the pediatric outpatient clinic was established, and then implemented. Continuous evaluation still requires long-term data collection to optimize the weight proportions of the established indicators.

A novel remnant liver-first strategy for liver autotransplantation in patients with end-stage hepatic alveolar echinococcosis: a retrospective case series.

BACKGROUND: Ex vivo liver resection combined with autotransplantation is an effective therapeutic strategy for unresectable end-stage hepatic alveolar echinococcosis (HAE). However, ex vivo liver resection combined with autotransplantation is a technically demanding and time-consuming procedure associated with significant morbidity and mortality. The authors aimed to present our novel remnant liver-first strategy of in vivo liver resection combined with autotransplantation (IRAT) technique for treating patients with end-stage HAE. METHODS: This retrospective study included patients who underwent IRAT between January 2014 and December 2020 at two institutions. Patients with end-stage HAE were carefully assessed for IRAT by a multidisciplinary team. The safety, feasibility, and outcomes of this novel technique were analyzed. RESULTS: IRAT was successfully performed in six patients, with no perioperative deaths. The median operative time was 537.5 min (range, 501.3-580.0), the median anhepatic time was 59.0 min (range, 54.0-65.5), and the median cold ischemia time was 165.0 min (range, 153.8-201.5). The median intraoperative blood loss was 700.0 ml (range, 475.0-950.0). In-hospital complications occurred in two patients. No Clavien-Dindo grade III or higher complications were observed. At a median follow-up of 18.6 months (range, 15.4-76.0) , all patients were alive. No recurrence of HAE was observed. CONCLUSION: The remnant liver-first strategy of IRAT is feasible and safe for selected patients with end-stage HAE. The widespread adoption of this novel technique requires further studies to standardize the operative procedure and identify patients who are most likely to benefit from it.

Comparative survey among paediatricians, nurses and health information technicians on ethics implementation knowledge of and attitude towards social experiments based on medical artificial intelligence at children's hospitals in Shanghai: a cross-sectional study.

OBJECTIVES: Implementing ethics is crucial to prevent harm and promote widespread benefits in social experiments based on medical artificial intelligence (MAI). However, insufficient information is available concerning this within the paediatric healthcare sector. We aimed to conduct a comparative survey among paediatricians, nurses and health information technicians regarding ethics implementation knowledge of and attitude towards MAI social experiments at children's hospitals in Shanghai. DESIGN AND SETTING: A cross-sectional electronic questionnaire was administered from 1 July 2022 to 31 July 2022, at tertiary children's hospitals in Shanghai. PARTICIPANTS: All the eligible individuals were recruited. The inclusion criteria were as follows: (1) should be a paediatrician, nurse and health information technician, (2) should have been engaged in or currently participating in social experiments based on MAI, and (3) voluntary participation in the survey. PRIMARY OUTCOME: Ethics implementation knowledge of and attitude to MAI social experiments among paediatricians, nurses and health information technicians. RESULTS: There were 137 paediatricians, 135 nurses and 60 health information technicians who responded to the questionnaire at tertiary children's hospitals. 2.4-9.6% of participants were familiar with ethics implementation knowledge of MAI social experiments. 31.9-86.1% of participants held an 'agree' ethics implementation attitude. Health information technicians accounted for the highest proportion of the participants who were familiar with the knowledge of implementing ethics, and paediatricians or nurses accounted for the highest proportion among those who held 'agree' attitudes. CONCLUSIONS: There is a significant knowledge gap and variations in attitudes among paediatricians, nurses and health information technicians, which underscore the urgent need for individualised education and training programmes to enhance MAI ethics implementation in paediatric healthcare.

Development, Reliability, and Structural Validity of the Scale for Knowledge, Attitude, and Practice in Ethics Implementation Among AI Researchers: Cross-Sectional Study.

BACKGROUND: Medical artificial intelligence (AI) has significantly contributed to decision support for disease screening, diagnosis, and management. With the growing number of medical AI developments and applications, incorporating ethics is considered essential to avoiding harm and ensuring broad benefits in the lifecycle of medical AI. One of the premises for effectively implementing ethics in Medical AI research necessitates researchers' comprehensive knowledge, enthusiastic attitude, and practical experience. However, there is currently a lack of an available instrument to measure these aspects. OBJECTIVE: The aim of this study was to develop a comprehensive scale for measuring the knowledge, attitude, and practice of ethics implementation among medical AI researchers, and to evaluate its measurement properties. METHODS: The construct of the Knowledge-Attitude-Practice in Ethics Implementation (KAP-EI) scale was based on the Knowledge-Attitude-Practice (KAP) model, and the evaluation of its measurement properties was in compliance with the COnsensus-based Standards for the selection of health status Measurement INstruments (COSMIN) reporting guidelines for studies on measurement instruments. The study was conducted in 2 phases. The first phase involved scale development through a systematic literature review, qualitative interviews, and item analysis based on a cross-sectional survey. The second phase involved evaluation of structural validity and reliability through another cross-sectional study. RESULTS: The KAP-EI scale had 3 dimensions including knowledge (10 items), attitude (6 items), and practice (7 items). The Cronbach α for the whole scale reached .934. Confirmatory factor analysis showed that the goodness-of-fit indices of the scale were satisfactory (χ2/df ratio:=2.338, comparative fit index=0.949, Tucker Lewis index=0.941, root-mean-square error of approximation=0.064, and standardized root-mean-square residual=0.052). CONCLUSIONS: The results show that the scale has good reliability and structural validity; hence, it could be considered an effective instrument. This is the first instrument developed for this purpose.

The impact of a closed-loop electronic blood transfusion system on transfusion errors and staff time in a children's hospital.

OBJECTIVES: To assess the impact of a closed-loop electronic blood transfusion system on transfusion errors and staff time. MATERIALS AND METHODS: Before and after study in all wards of a children's hospital, involving patients and staff of all the wards. The changes were closed-loop electronic blood transfusion, barcode patient identification, electronic blood transfusion administration records and error pop-up warning. The main outcome measures were percentage of blood transfusion errors, time spent on transfusion tasks. RESULTS: Transfusion errors were identified in 3.87% of 2556 blood transfusion orders pre-intervention and 0.78% of 2577 orders afterwards (P<0.01). Phlebotomists, nurses, and physicians may make mistakes, including wrong blood type when apply for blood, wrong patient when blood draw or transfusion, wrong dose when apply for blood and the wrong tube label when blood draw or cross-matching, which are significantly reduced after change (1.09% vs 0.31%, 1.13% vs 0%, 0.31% vs 0%, 1.33% vs.0.78%, P<0.01). Time spent on blood apply was 5.3±1.2min, hand over blood bag at the transfusion department was 14.9±1.4min and blood transfusion was 15.8±2.4min. Time per transfusion round decreased to 2.6±1.0min, 6.3±1.6min and 9.3±2.2min respectively (P<0.01). CONCLUSIONS: A closed-loop electronic blood transfusion, barcode patient identification and error pop-up warning reduced transfusion errors, and increased confirmation of patient and blood types identity before transfusion. Time spent on blood transfusion tasks reduced.

Development and Implementation of Pediatric Nursing-Clinical Decision Support System for Hyperthermia: A Pre- and Post-Test.

Firstly, we form the Pediatric Nursing-Knowledge Base for Hyperthermia, which combines publicly clinical practice guidelines and nursing routines of hyperthermia management. Then, following the nursing process framework, the system is developed by clinical decision support technology. Finally, a pre- and post-test is adopted to examine the effectiveness, usability and feasibility before and after using the system. Its effectiveness is examined by nursing records quality including completeness of nursing assessment, timeliness of nursing diagnosis, individualization of nursing interventions, and timeliness of nursing evaluation. Its usability and feasibility are assessed using the Clinical Nursing Information System Effectiveness Evaluation Scale. There is a significant difference between the two groups in effectiveness, usability and feasibility. Although the system is developed specifically for our hospital workflow and processes, the Pediatric Nursing-Knowledge Base for Hyperthermia and workflow for hyperthermia management in this study can be used as a reference to other hospitals.

Development and Implementation of a Pediatric Nursing-Clinical Decision Support System for Hyperthermia: A Pre- and Post-test.

This article describes the development process and application of the Pediatric Nursing-Clinical Decision Support System for Hyperthermia. Firstly, we formed the Pediatric Nursing-Knowledge Base for Hyperthermia, which combines publicly available clinical practice guidelines and nursing routines of hyperthermia management. Then, following the nursing process framework, the system was developed using clinical decision support technology. Finally, a pre- and post-test were adopted to examine the effectiveness, usability, and feasibility before (1st to 31st of August 2018) and after (1st to 31st of December 2019) using the system. Its effectiveness was examined by analysis of nursing records' quality, including completeness of nursing assessment, timeliness of nursing diagnosis, individualization of nursing interventions, and timeliness of nursing evaluation. Its usability and feasibility were assessed using the Clinical Nursing Information System Effectiveness Evaluation Scale. There was a significant difference between the two groups in effectiveness, usability, and feasibility. Although the system was developed specifically for our hospital workflow and processes, the Pediatric Nursing-Knowledge Base for Hyperthermia and workflow for hyperthermia management in this study can be used as a reference to other hospitals.

An internet-based multidisciplinary online medical consultation system to help cope with pediatric medical needs during the COVID-19 outbreak: a cross-sectional study.

BACKGROUND: Telemedicine is becoming an emerging innovative supplement to the traditional medical system in China. In the present study, we described the rapid implementation of the telemedicine in pediatrics during the coronavirus disease 2019 (COVID-19) outbreak and explored its value in response to the demand for pediatric medical services during the epidemic. METHODS: An Internet-based platform for multidisciplinary online medical consultation was established on February 8, 2020, by a national children's medical center in China. The medical data of the traditional hospital visits and novel online visits from the first two months (February 8 to March 31) after the establishment of the platform were collected and analyzed. The demographic features, changes in the disease spectrum and characteristics of online medical services were described. RESULTS: The total number of visits was significantly lower (by 75.3%) than that of in the same period in the previous year. The disease spectrum was different with a significant decrease of >95% in the number of patients with infectious or contagious diseases. The online visits accounted for 14.7% of all visits. Online patients came from all over the country, covering 91% of the administrative regions of China, and the largest proportion of inquiries were for infants (33.7%) (P<0.01). The response rate of experts to requests for online consultations was 100%. During the study period, 266 experts from 25 pediatric specialties completed 12,318 effective consultations, proving different degrees of online supplementation for various specialties (4.3-168.4%). Online consultations mainly addressed two types of problems: (I) accessibility of the traditional hospital visits and (II) consultations regarding an illness. Data from pediatric nephrology showed that 96% of the patients with stable chronic kidney disease successfully received follow-up medication adjustment guidance through the online platform. CONCLUSIONS: The traditional hospital medical services have been affected by the COVID-19 outbreak. The multidisciplinary online medical consultation system is a strategy to actively respond to the medical needs of children during unique periods.

The pretransplant neutrophil-lymphocyte ratio as a new prognostic predictor after liver transplantation for hepatocellular cancer: a systematic review and meta-analysis.

AIM: Recently, many reports showed that the pretransplant neutrophil-lymphocyte ratio (NLR) may be correlated with the prognosis of patients undergoing liver transplantation (LT) for hepatocellular cancer (HCC). However, their results still remained controversial. Thus we performed a meta-analysis of 13 studies to estimate the prognostic value of pretransplant NLR. METHODS: Databases including PubMed, Embase, Cochrane Library and Web of Science were searched to September 2017. Hazard ratio (HR) or odds ratio (OR) with its 95% CI was used to evaluate the association between elevated NLR and the prognosis or clinical features of liver cancer patients. RESULTS: A total of 13 studies including 1936 patients were included in this meta-analysis. Elevated pretransplant NLR had a close association with the overall survival (HR: 2.22; 95% CI: 1.34-3.68), recurrence-free survival (HR: 3.77; 95% CI: 2.01-7.06) and disease-free survival (HR: 2.51; 95% CI: 1.22-5.15) of patients undergoing LT for HCC, respectively. In addition, elevated NLR was associated with the presence of vascular invasion (OR: 2.39; 95% CI: 1.20-4.77) and Milan criteria (OR: 0.26; 95% CI: 0.17-0.40). CONCLUSION: The results of this meta-analysis showed that elevated pretransplant NLR may be used as a new prognostic predictor after LT for HCC.

[The relationship between systemic inflammatory response syndrome and severity of acute pancreatitis combined with plateau erythrocythemia].

OBJECTIVE: To explore the relationship between systemic inflammatory response syndrome(SIRS) and severity of acute pancreatitis combined with plateau erythrocythemia in the high altitude. METHODS: A retrospective analysis on the clinical data which involved acute pancreatitis combined with plateau erythrocythemia (n = 40) and without plateau erythrocythemia (n = 40) admitted from September 2006 to September 2009 was conducted. According to the unified standards, these cases were divided into plateau erythrocythemia group and no plateau erythrocythemia group. The patients in plateau erythrocythemia group were further divided into severe group and mild group according to scores of APACHEII. The data was analyzed according to the patient with (or without) SIRS, SIRS's standard indicators, diagnostic parameter and relation of severity and duration of SIRS in acute pancreatitis combined with plateau erythrocythemia. RESULTS: There was significantly discrepancy between plateau erythrocythemia group and no plateau erythrocythemia group not only in the incidence of patients who developed SIRS, but also in two items of patients fulfilling or not fulfilling diagnostic criteria of SIRS (P < 0.05). There was significant statistical difference in three items of diagnostic parameter of SIRS between plateau erythrocythemia group and no plateau erythrocythemia group (P < 0.05). Significant difference in two and three diagnostic parameter was found on severity of SIRS in acute pancreatitis combined with plateau erythrocythemia (P < 0.05). The more severity acute pancreatitis combined with plateau erythrocythemia was, the longer duration of SIRS was. CONCLUSION: SIRS is highly correlated with the severity of SIRS in acute pancreatitis combined with plateau erythrocythemia in the high altitude.

[The changes and significance of multiple organ functions in acute pancreatitis patients under hypoxic condition on plateau].

OBJECTIVE: To explore characteristics of the pathogenesis and progression of the acute pancreatitis (AP) in high altitude and the relationship between AP and plateau erythrocythemia. METHODS: Retrospective analysis of the clinical data of AP was conducted for 103 inpatients who were admitted during 2003 and 2005 to the People's Hospital of Qinghai Province, including 12 cases of AP complicated with plateau erythrocythemia and 91 cases of AP no complicating plateau erythrocythemia. The patients were divided into a group of 57 cases living in high altitude (>3 000 m) and 46 patients in lower altitude group (<2 200 m). Clinical data of the patients were collected at admission, and liver, kidney and lung functions were determined for all patients. RESULTS: Alanine aminotransferase (ALT) and creatinine (Cr) were significantly higher in AP complicating plateau erythrocythemia compared with AP patients without complicating plateau erythrocythemia [ALT: (160.70 + or - 19.14) U/L vs. (78.00 + or - 14.96) U/L, Cr: (135.45 + or - 11.99) micromol/L vs. (91.42 + or - 17.08) micromol/L, both P<0.05]. Arterial partial pressure of oxygen (PaO(2)) and arterial oxygen saturation (SaO(2)) were significantly lower in AP with complication of plateau erythrocythemia than in AP without complicating plateau erythrocythemia [PaO(2): (45.10 + or - 0.40) mm Hg vs. (65.48 + or - 1.36) mm Hg, 1 mm Hg=0.133 kPa, SaO(2): 0.851 + or - 0.004 vs. 0.940 + or - 0.009, both P<0.05]. There was no difference in aspartate aminotransferase (AST), blood urea nitrogen (BUN) and arterial partial pressure of carbon dioxide (PaCO(2)), however, their levels were higher in plateau erythrocythemia cases than those without plateau erythrocythemia [AST: (87.35 + or - 8.10) U/L vs. (83.00 + or - 18.61) U/L, BUN:(10.90 + or - 0.97) mmol/L vs. (7.37 + or - 0.98) mmol/L, PaCO(2): (33.20 + or - 0.31) mm Hg vs. (25.32 + or - 1.14) mm Hg , all P>0.05]. ALT and Cr were significantly higher in high altitude cases than those in lower altitude cases [ALT: (126.92 + or - 15.46) U/L vs. (86.00 + or - 10.23) U/L, Cr:(126.10 + or - 10.01)micromol/L vs. (101.84 + or - 5.46) micromol/L, both P<0.05]. There was no difference in AST, BUN and PaCO(2), however, the values were slightly higher in high altitude cases compared with lower altitude cases [AST: (98.70 + or - 8.10) U/L vs. (93.14 + or - 21.46) U/L, BUN: (8.15 + or - 1.00) mmol/L vs. (5.86 + or - 0.40) mmol/L, PaCO(2): (32.32 + or - 1.01) mm Hg vs. (30.12 + or - 2.76) mm Hg, all P>0.05]. There was no difference in PaO(2) and SaO(2), however, it was slightly lower in high altitude cases than lower altitude cases [PaO(2): (58.80 + or - 1.20) mm Hg vs. (66.86 + or - 3.20) mm Hg, SaO(2): 0.910 + or - 0.011 vs. 0.930 + or - 0.008, both P>0.05]. CONCLUSION: The results showed that the deterioration of hepatic, kidney and lung function in AP patients living in the plateau was related to high altitude and erythrocythemia.