RESUMEN
OBJECTIVE: Colorectal cancer (CRC) is the fourth most common cancer in the UK. Patients with symptoms suggestive of CRC should be referred for urgent investigation. However, gastrointestinal symptoms are often non-specific and there is a need for suitable triage tools to enable prioritisation of investigations. In this study, the performance of the faecal immunochemical test (FIT), anaemia and the artificial intelligence algorithm ColonFlag were retrospectively examined and evaluated for their potential clinical benefits in patients who had been referred on an urgent lower gastrointestinal cancer pathway. DESIGN: All patients aged over 40 years referred in a 12-month period were included. After 6 months, clinical outcomes were determined and the performance of the triage tests was evaluated. RESULTS: A total of 3822 patients completed investigations and received a diagnosis. 143 had CRC, 126 high-risk adenomas (HRA). ColonFlag would have missed 27 CRC and 29 HRA. Faecal haemoglobin (f-Hb) at a cut-off of 10 µg/g would have missed 10 CRC and 26 HRA; f-Hb in combination with anaemia would have missed 2 CRC and 14 HRA. Using f-Hb in combination with ColonFlag would have missed only 1 CRC and 5 HRA and would have reduced the need for urgent referral by over 400 patients. CONCLUSION: ColonFlag has potential to assist detection of CRC and HRA, alone where no faecal sample is present and in combination with FIT and to reduce the need for urgent referral.
Asunto(s)
Anemia , Inteligencia Artificial , Neoplasias Colorrectales , Detección Precoz del Cáncer , Hemoglobinas , Sangre Oculta , Humanos , Femenino , Masculino , Estudios Retrospectivos , Persona de Mediana Edad , Anciano , Neoplasias Colorrectales/diagnóstico , Anemia/diagnóstico , Detección Precoz del Cáncer/métodos , Hemoglobinas/análisis , Algoritmos , Adulto , Heces/química , Triaje/métodos , Adenoma/diagnóstico , Adenoma/patología , Reino Unido/epidemiología , Derivación y Consulta/estadística & datos numéricos , Anciano de 80 o más AñosRESUMEN
Background: In the general population, primary human papillomavirus (HPV) testing is advocated for cervical cancer (CC) screening. HPV E6/E7 mRNA (Aptima HPV, AHPV) assays have garnered considerable traction due to their higher specificity when compared with HPV DNA assays. Here, we investigated age-specific primary AHPV screening assays and different triage strategies versus cytology to identify the best approach. Methods: Between April 2018 and December 2021, we recruited female participants from 34 communities across Liaoning province and Qingdao City, China. Primary cervical screening protocols included liquid-based cytology (LBC) and AHPV assays, with females positive for any assays undergoing colposcopy. Genotyping (AHPV-GT) was conducted on all HPV-positive samples. Our primary outcomes were the identification of age-specific detection rates, colposcopy referral rates, and sensitivity and specificity values for high-grade squamous intraepithelial lesions or worse (HSIL+). AHPV and different triage strategy performances were also examined across different age cohorts. Results: Our investigation included 9911 eligible females. Age-specific abnormal cytology rates were in the 6.1%-8.0% range, and were highest in 45-54-year olds. When compared with 35-44-or 45-54-year olds, HPV prevalence was highest in 55-64-year olds (12.2% or 11.6% vs.14.1%, P = 0.048 and P = 0.002, respectively). In 35-44-year olds, AHPV sensitivity for detecting HSIL+ was 96.6 (95% confidence interval [CI]: 89.7-100) - significantly higher than LBC sensitivity (65.5 [95% CI: 48.3-82.8], P < 0.001). When compared with LBC, HSIL+ detection rates by AHPV-GT using reflex LBC triage increased by 31.5% (9.6 vs. 7.3), and colposcopy referral rates decreased by 16.4% (5.1% vs. 6.1%). In 45-54-year olds, HSIL+ detection rates for AHPV-GT using reflex LBC triage were lower than LBC rates (6.2 vs. 6.6). In 55-64-year olds, AHPV sensitivity (97.2 [95% CI: 91.7-100.0]) was higher than LBC sensitivity (66.7 [95% CI: 50.0-80.6], P = 0.003). The area under the curve (AUC) value was not significantly different between AHPV-GT with reflex LBC triage and LBC (0.845 [95% CI: 0.771-0.920] vs. 0.812 [95% CI: 0.734-0.891], P = 0.236). Conclusions: Primary AHPV screening using different triage strategies were different across different age cohorts. Thus, AHPV may be an appropriate primary screening method for 35-44 and 55-64 year old females, while AHPV-GT with reflex LBC triage may be more apt for 35-44 year old females.
Asunto(s)
Detección Precoz del Cáncer , Infecciones por Papillomavirus , Sensibilidad y Especificidad , Triaje , Neoplasias del Cuello Uterino , Humanos , Femenino , Neoplasias del Cuello Uterino/diagnóstico , Neoplasias del Cuello Uterino/virología , Persona de Mediana Edad , China/epidemiología , Adulto , Detección Precoz del Cáncer/métodos , Infecciones por Papillomavirus/diagnóstico , Infecciones por Papillomavirus/virología , Triaje/métodos , Anciano , Factores de Edad , Colposcopía , Papillomaviridae/genética , Papillomaviridae/aislamiento & purificación , ARN Mensajero/genética , Proteínas Oncogénicas Virales/genética , Adulto Joven , Genotipo , Tamizaje Masivo/métodos , Virus del Papiloma Humano , CitologíaRESUMEN
AIM: Geriatric patients are increasingly dominating the daily routine in emergency department (ED). The atypical clinical presentation of disease, multimorbidity, frailty and cognitive impairment of geriatric patients pose particular challenges for triage in the ED. Efficient and accurate emergency triage plays a key role in differentiating between geriatric patients who need timely treatment and those who can wait safely. The purpose of this study was to evaluate the performance of the modified Manchester Triage System (mMTS) in classifying geriatric patients. DESIGN: An observational retrospective study. METHODS: A retrospective study of 18,796 geriatric patients (≥65 years) attending the ED of a tertiary care hospital in Zhejiang province between 1 June 2020 and 30 June 2022. Baseline information on patients was collected and divided into two different study groups according to triage level: high priority (red/orange) and low priority (yellow/green). The sensitivity and specificity of the mMTS were estimated by verifying the triage classification received by the emergency geriatric patients and their survival at 7 days or the need for acute surgery within 72 h. RESULTS: The study included a total of 17,764 geriatric patients with a median age of 72 years in ED. 10.7% (1896/17,764) of the geriatric patients were assigned to the high priority code group (red/orange) and 89.3% (15,868/17,764) were in the low priority code group (yellow/green). The sensitivity of the mMTS associated with death within 7 days was 85.7% (77.5-91.4), specificity was 89.8% (89.3-90.2), and accuracy was 89.8% (89.3-90.2). 1.8% of patients required surgery within 72 h. The sensitivity was 62.6% (57.0-67.9), specificity was 90.3% (89.8-90.7), and negative predictive value was 99.2% (99.0-99.4). CONCLUSIONS: The mMTS has good specificity, accuracy and negative predictive value for geriatric patients. However, its incorrect prediction of triage in high-priority code patients results in lower sensitivity, which may serve as a protective strategy for these individuals. The current emergency triage system does not completely screen geriatric patients with severe acute illness who present to the ED, and it is necessary to add comprehensive assessment tools that match the characteristics of geriatric patients to improve triage outcomes.
Asunto(s)
Servicio de Urgencia en Hospital , Evaluación Geriátrica , Triaje , Humanos , Triaje/métodos , Anciano , Estudios Retrospectivos , Masculino , Femenino , Anciano de 80 o más Años , Evaluación Geriátrica/métodos , China , Sensibilidad y EspecificidadRESUMEN
BACKGROUND: Prediction-based strategies for physiologic deterioration offer the potential for earlier clinical interventions that improve patient outcomes. Current strategies are limited because they operate on inconsistent definitions of deterioration, attempt to dichotomize a dynamic and progressive phenomenon, and offer poor performance. OBJECTIVE: Can a deep learning deterioration prediction model (Deep Learning Enhanced Triage and Emergency Response for Inpatient Optimization [DETERIO]) based on a consensus definition of deterioration (the Adult Inpatient Decompensation Event [AIDE] criteria) and that approaches deterioration as a state "value-estimation" problem outperform a commercially available deterioration score? DERIVATION COHORT: The derivation cohort contained retrospective patient data collected from both inpatient services (inpatient) and emergency departments (EDs) of two hospitals within the University of California San Diego Health System. There were 330,729 total patients; 71,735 were inpatient and 258,994 were ED. Of these data, 20% were randomly sampled as a retrospective "testing set." VALIDATION COHORT: The validation cohort contained temporal patient data. There were 65,898 total patients; 13,750 were inpatient and 52,148 were ED. PREDICTION MODEL: DETERIO was developed and validated on these data, using the AIDE criteria to generate a composite score. DETERIO's architecture builds upon previous work. DETERIO's prediction performance up to 12 hours before T0 was compared against Epic Deterioration Index (EDI). RESULTS: In the retrospective testing set, DETERIO's area under the receiver operating characteristic curve (AUC) was 0.797 and 0.874 for inpatient and ED subsets, respectively. In the temporal validation cohort, the corresponding AUC were 0.775 and 0.856, respectively. DETERIO outperformed EDI in the inpatient validation cohort (AUC, 0.775 vs. 0.721; p < 0.01) while maintaining superior sensitivity and a comparable rate of false alarms (sensitivity, 45.50% vs. 30.00%; positive predictive value, 20.50% vs. 16.11%). CONCLUSIONS: DETERIO demonstrates promise in the viability of a state value-estimation approach for predicting adult physiologic deterioration. It may outperform EDI while offering additional clinical utility in triage and clinician interaction with prediction confidence and explanations. Additional studies are needed to assess generalizability and real-world clinical impact.
Asunto(s)
Aprendizaje Profundo , Servicio de Urgencia en Hospital , Humanos , Estudios Retrospectivos , Masculino , Femenino , Persona de Mediana Edad , Anciano , Deterioro Clínico , Triaje/métodos , Adulto , Estudios de Cohortes , Pacientes InternosRESUMEN
Amelogenesis imperfecta (AI) is a genetic disease characterized by poor formation of tooth enamel. AI occurs due to mutations, especially in AMEL, ENAM, KLK4, MMP20, and FAM83H, associated with changes in matrix proteins, matrix proteases, cell-matrix adhesion proteins, and transport proteins of enamel. Due to the wide variety of phenotypes, the diagnosis of AI is complex, requiring a genetic test to characterize it better. Thus, there is a demand for developing low-cost, noninvasive, and accurate platforms for AI diagnostics. This case-control pilot study aimed to test salivary vibrational modes obtained in attenuated total reflection fourier-transformed infrared (ATR-FTIR) together with machine learning algorithms: linear discriminant analysis (LDA), random forest, and support vector machine (SVM) could be used to discriminate AI from control subjects due to changes in salivary components. The best-performing SVM algorithm discriminates AI better than matched-control subjects with a sensitivity of 100%, specificity of 79%, and accuracy of 88%. The five main vibrational modes with higher feature importance in the Shapley Additive Explanations (SHAP) were 1010 cm-1, 1013 cm-1, 1002 cm-1, 1004 cm-1, and 1011 cm-1 in these best-performing SVM algorithms, suggesting these vibrational modes as a pre-validated salivary infrared spectral area as a potential biomarker for AI screening. In summary, ATR-FTIR spectroscopy and machine learning algorithms can be used on saliva samples to discriminate AI and are further explored as a screening tool.
Asunto(s)
Amelogénesis Imperfecta , Aprendizaje Automático , Saliva , Humanos , Amelogénesis Imperfecta/diagnóstico , Amelogénesis Imperfecta/genética , Amelogénesis Imperfecta/metabolismo , Saliva/metabolismo , Saliva/química , Espectroscopía Infrarroja por Transformada de Fourier/métodos , Femenino , Estudios de Casos y Controles , Masculino , Algoritmos , Adulto , Máquina de Vectores de Soporte , Proyectos Piloto , Análisis Discriminante , Biomarcadores , Triaje/métodos , Adolescente , Adulto JovenRESUMEN
OBJECTIVE: To describe the adherence to the sepsis protocol by obstetric nurses in the obstetric triage of a high-risk maternity reference center. METHODS: This was a quantitative, documental, and retrospective study involving 105 pregnant women treated in obstetric triage under sepsis criteria. Data were collected through electronic medical records using structured forms and were organized into tables employing descriptive statistics. This research adhered to ethical principles concerning human studies. RESULTS: Of the checklists for initiating the SEPSIS protocol by obstetric nurses, 105 were identified. Regarding the protocol steps performed, lactate was collected in 97.1% of cases and blood cultures in 98.1%, antibiotic therapy was administered in 94.3%, and hydration was carried out in 51.4% of the cases. CONCLUSION: The initiation of the sepsis protocol for all women meeting the criteria was confirmed. However, the steps were not fully implemented as recommended by the institutional protocol, and the recommended broad-spectrum antibiotic was not administered.
Asunto(s)
Adhesión a Directriz , Sepsis , Humanos , Femenino , Estudios Retrospectivos , Embarazo , Sepsis/tratamiento farmacológico , Adulto , Adhesión a Directriz/estadística & datos numéricos , Adhesión a Directriz/normas , Triaje/métodos , Triaje/normas , Triaje/éticaAsunto(s)
COVID-19 , Participación de la Comunidad , Pandemias , Triaje , Humanos , COVID-19/epidemiología , COVID-19/prevención & control , Triaje/métodos , SARS-CoV-2RESUMEN
BACKGROUND: In Germany, the telephone patient service 116,117 for callers with non-life-threatening health issues is available 24/7. Based on structured initial assessment, urgency and placement of suitable medical care offer have been offered since 2020. The service has been in increasing demand for several years: Depending on time and residence, this can result in longer waiting times. METHODS: Prospective, two-armed cohort study with two intervention groups and one control group, alternating between blinding and unblinding for employees of 116,117 regarding prioritization status. Two interventions based on automated voice dialogues (1: Simple self-rating tool, 2: Automated brief query of emergency symptoms). In case of high level of urgency, callers are prioritized. Validation of urgency and need for care is carried out routinely based on structured initial assessment. DISCUSSION: By creating and providing a largely reproducible documentation of the implemented solutions for a waiting queue management, the developed approach would be available for comparable projects in the German health care system or in the European context. This potentially leads to a reduction in the use of resources in the development of comparable technical solutions based on automated voice dialogs. TRIAL REGISTRATION: DRKS00031235, registered on 10th November 2023, https://drks.de/search/de/trial/DRKS00031235 .
Asunto(s)
Teléfono , Humanos , Estudios Prospectivos , Alemania , Urgencias Médicas , Listas de Espera , Triaje/métodos , Líneas DirectasRESUMEN
AIM: Quantitative faecal haemoglobin (fHb) measurement by faecal immunochemical test (FIT) is a powerful biomarker for colorectal cancer (CRC) and is incorporated in referral, prioritisation and triage protocols for symptomatic cases in other countries. We report our use of FIT to prioritise new patient symptomatic cases referred for colorectal investigation. METHOD: Cases referred for investigation of new colorectal symptoms who were aged ≥50 years (≥40 years Maori/Pacific peoples), who would otherwise be triaged to non-urgent colonoscopy, were asked to provide a stool sample for FIT. Following FIT testing, cases were re-triaged to either urgent colonoscopy, non-urgent colonoscopy or computed tomography colonography (CTC) depending on fHb concentration (measured in micrograms haemoglobin per gram of stool [mcg/g]) and incorporating clinical judgement. At pathway initiation, cases already waiting for colonoscopy on the non-urgent new patient waiting list were approached first, and then new patient (NP) referrals for colonoscopy could be triaged to the pathway at the discretion of the triaging consultant. RESULTS: Out of 739 cases, 715 (97%) returned FIT samples, and 691 cases completed colorectal investigations. Overall FIT positivity ≥10mcg/g was 17.1%. Fifteen colorectal cancers (CRC) were detected (2.2%). The sensitivity and specificity of FIT ≥10mcg/g for CRC were 80.0% (54.0-93.7%) and 84.3 (81.4-86.9%) respectively. A total of 432 cases (62.5%) completed the pathway without recourse to colonoscopy, and the median time to CRC diagnosis for NP from referral was 25 days. CONCLUSION: FIT based prioritisation of cases referred with symptoms concerning for CRC is feasible and reduces time to CRC diagnosis.
Asunto(s)
Colonoscopía , Neoplasias Colorrectales , Detección Precoz del Cáncer , Sangre Oculta , Derivación y Consulta , Triaje , Humanos , Neoplasias Colorrectales/diagnóstico , Persona de Mediana Edad , Femenino , Masculino , Anciano , Detección Precoz del Cáncer/métodos , Triaje/métodos , Hemoglobinas/análisis , Nueva Zelanda , Colonografía Tomográfica Computarizada , Heces/químicaRESUMEN
Establishing reliable noninvasive tools to precisely diagnose clinically significant liver fibrosis (SF, ≥F2) remains an unmet need. We aimed to build a combined radiomics-clinic (CoRC) model for triaging SF and explore the additive value of the CoRC model to transient elastography-based liver stiffness measurement (FibroScan, TE-LSM). This retrospective study recruited 595 patients with biopsy-proven liver fibrosis at two centers between January 2015 and December 2021. At Center 1, the patients before December 2018 were randomly split into training (276) and internal test (118) sets, the remaining were time-independent as a temporal test set (96). Another data set (105) from Center 2 was collected for external testing. Radiomics scores were built with selected features from Deep learning-based (ResUNet) automated whole liver segmentations on MRI (T2FS and delayed enhanced-T1WI). The CoRC model incorporated radiomics scores and relevant clinical variables with logistic regression, comparing routine approaches. Diagnostic performance was evaluated by the area under the receiver operating characteristic curve (AUC). The additive value of the CoRC model to TE-LSM was investigated, considering necroinflammation. The CoRC model achieved AUCs of 0.79 (0.70, 0.86), 0.82 (0.73, 0.89), and 0.81 (0.72-0.91), outperformed FIB-4, APRI (all p < 0.05) in the internal, temporal, and external test sets and maintained the discriminatory power in G0-1 subgroups (AUCs range, 0.85-0.86; all p < 0.05). The AUCs of joint CoRC-LSM model were 0.86 (0.79-0.94), and 0.81 (0.72-0.90) in the internal and temporal sets (p = 0.01). The CoRC model was useful for triaging SF, and may add value to TE-LSM.
Asunto(s)
Diagnóstico por Imagen de Elasticidad , Cirrosis Hepática , Hígado , Imagen por Resonancia Magnética , Humanos , Cirrosis Hepática/diagnóstico por imagen , Cirrosis Hepática/diagnóstico , Masculino , Femenino , Persona de Mediana Edad , Estudios Retrospectivos , Imagen por Resonancia Magnética/métodos , Adulto , Diagnóstico por Imagen de Elasticidad/métodos , Hígado/patología , Hígado/diagnóstico por imagen , Curva ROC , Aprendizaje Profundo , Anciano , Triaje/métodosRESUMEN
BACKGROUND: This study aims to facilitate parental identification of designated emergency facilities for expeditious pediatric care within the framework of Taiwan's newly implemented "regional joint defense" approach to pediatric emergency services. The research seeks to elucidate the mechanisms by which this novel system can enhance timely access to appropriate emergency care for children, potentially improving health outcomes and resource utilization in acute pediatric situations. METHODS: Factor analysis (FA) and triangular entropy matrix (TEM) analyzed the appearance, breathing and skin of pediatric assessment triangle (ABC of PAT), three types of prehospital pediatric emergence condition (PPEC), five levels of Taiwan's pediatric emergency triage (TPET), and applied the social learning theory (SLT) in educational doctrine, using experts' weighted questionnaires. RESULTS: Firstly, to address deficiencies in Taiwan's pediatric prehospital emergency medicine (PEM) system, integrating emergency medical knowledge (EMK) and pediatric life support (PLS) into medical education, staff training, and the national handbook for new parents is crucial. This equips parents to manage children's illnesses and prevent emergencies. Then, in life-threatening situations, immediate emergency room (ER) transport is vital for symptoms like whitish or purple lips, cold limbs, mottled skin, cold sweat, convulsions, dyspnea, chest dimples, weak consciousness, and oxygen saturation below 94%. Finally, for non-life-threatening emergencies, seek medical evaluation if symptoms include wheezing, chest tightness, chest pain, persistent high fever over 39 degrees with convulsions, chills, cold sweats, not eating or urinating for over 12 hours, or fever lasting more than 48 hours. CONCLUSION: Parents must remain calm and provide their baby with a sense of security while observing the development of physical symptoms. This approach enables them to effectively determine the most appropriate time to take their children to the emergency room, thereby avoiding life-threatening emergencies. Prompt and proper measures and treatments not only alleviate various discomforts caused by illness or medical emergencies but also reduce systemic distress, life-threatening situations, and unfortunate incidents before hospitalization.
Asunto(s)
Servicios Médicos de Urgencia , Humanos , Taiwán/epidemiología , Niño , Medicina de Emergencia/educación , Medicina de Emergencia/organización & administración , Cuidados para Prolongación de la Vida/métodos , Pediatría/métodos , Pediatría/organización & administración , Triaje/métodos , Medicina de Urgencia Pediátrica/métodos , Medicina de Urgencia Pediátrica/estadística & datos numéricos , Preescolar , Encuestas y Cuestionarios , LactanteRESUMEN
Although paediatric patients with gastrointestinal (GI) foreign bodies require multiple resources, they often present with few or no discernible symptoms and are typically assigned a low acuity level during triage. We compared the predictive accuracy of the revised Korean Triage and Acuity Scale (rKTAS), which elevates acuity by one step in relation to anticipated resource utilization, with that of the conventional KTAS for clinical outcomes. This was a retrospective study of National Emergency Department Information System data. Data on patient and ED characteristics, resources used, and clinical outcomes were collected from January 2018 to December 2021 for patients with GI foreign bodies aged under 19. The primary outcome was rKTAS accuracy in predicting hospitalization, ICU admission, operating room (OR) use, and ED length of stay (EDLOS). The AUROC was used to evaluate the performance via of the KTAS and rKTAS. In total, 25,324 paediatric patients visited the ED for GI tract foreign bodies. The mean age was 3.8 years, and 51% (12,923) were between 1 and 4 year old. Although most (23,658; 93.4%) were discharged, 4.9% required hospitalization. Two or more resources were utilized in 2514 (9.9%) cases, and 3,514 individuals had their triage levels increased by one step. Compared with those of the KTAS, the AUROCs of the rKTAS for predicting overall hospitalization (p < 0.05), admission to general wards (p < 0.05), ICU admission (p = 0.01), and admission via the OR (p < 0.05)were higher than KTAS. Compared with that with the KTAS, the EDLOS with the rKTAS was longer at levels 1, 2, and 3. The adjusted rKTAS is a better predictor of clinical outcomes for paediatric patients with GI tract foreign bodies than the KTAS.
Asunto(s)
Servicio de Urgencia en Hospital , Cuerpos Extraños , Tracto Gastrointestinal , Hospitalización , Triaje , Humanos , Triaje/métodos , Preescolar , Masculino , Cuerpos Extraños/diagnóstico , Femenino , Niño , Lactante , República de Corea , Estudios Retrospectivos , Adolescente , Tiempo de Internación , Recién NacidoRESUMEN
BACKGROUND: Pediatric cervical spine injuries (CSIs) from blunt trauma carry a high risk of neurological damage. Accurate diagnosis is vital for preventing harm and aiding recovery, yet the diagnostic accuracy of clinical decision rules (CDRs) remains unclear. OBJECTIVE: To assess the effectiveness of triage tools for detecting CSI in pediatric trauma patients. METHODS: A summary of the Cochrane Review by Tavender et al. (2024), with comments from a rehabilitation perspective. RESULTS: Five studies with 21,379 participants assessed seven CDRs. Direct comparisons showed high sensitivity but low specificity across different CDRs. Indirect comparison studies also demonstrated varying sensitivities and specificities. CONCLUSIONS: Insufficient evidence exists to determine the best tools for deciding if imaging is necessary for diagnosing potential CSI in children. Better quality studies are needed to assess the accuracy of CDRs for cervical spine clearance in this population.
Asunto(s)
Vértebras Cervicales , Traumatismos Vertebrales , Triaje , Humanos , Triaje/métodos , Vértebras Cervicales/lesiones , Vértebras Cervicales/diagnóstico por imagen , Niño , Traumatismos Vertebrales/diagnóstico , Traumatismos Vertebrales/diagnóstico por imagen , Reglas de Decisión ClínicaRESUMEN
INTRODUCTION: The urgency and complexity of emergency room (ER) settings require precise and swift decision-making processes for patient care. Ensuring the timely execution of critical examinations and interventions is vital for reducing diagnostic errors, but the literature highlights a need for innovative approaches to optimize diagnostic accuracy and patient outcomes. In response, our study endeavors to create predictive models for timely examinations and interventions by leveraging the patient's symptoms and vital signs recorded during triage, and in so doing, augment traditional diagnostic methodologies. METHODS: Focusing on four key areas-medication dispensing, vital interventions, laboratory testing, and emergency radiology exams, the study employed Natural Language Processing (NLP) and seven advanced machine learning techniques. The research was centered around the innovative use of BioClinicalBERT, a state-of-the-art NLP framework. RESULTS: BioClinicalBERT emerged as the superior model, outperforming others in predictive accuracy. The integration of physiological data with patient narrative symptoms demonstrated greater effectiveness compared to models based solely on textual data. The robustness of our approach was confirmed by an Area Under the Receiver Operating Characteristic curve (AUROC) score of 0.9. CONCLUSION: The findings of our study underscore the feasibility of establishing a decision support system for emergency patients, targeting timely interventions and examinations based on a nuanced analysis of symptoms. By using an advanced natural language processing technique, our approach shows promise for enhancing diagnostic accuracy. However, the current model is not yet fully mature for direct implementation into daily clinical practice. Recognizing the imperative nature of precision in the ER environment, future research endeavors must focus on refining and expanding predictive models to include detailed timely examinations and interventions. Although the progress achieved in this study represents an encouraging step towards a more innovative and technology-driven paradigm in emergency care, full clinical integration warrants further exploration and validation.
Asunto(s)
Servicio de Urgencia en Hospital , Aprendizaje Automático , Procesamiento de Lenguaje Natural , Humanos , Triaje/métodos , Sistemas de Apoyo a Decisiones Clínicas , NarraciónRESUMEN
BACKGROUND: Emergency departments (EDs) are frequently overcrowded and increasingly used by nonurgent patients. Symptom checkers (SCs) offer on-demand access to disease suggestions and recommended actions, potentially improving overall patient flow. Contrary to the increasing use of SCs, there is a lack of supporting evidence based on direct patient use. OBJECTIVE: This study aimed to compare the diagnostic accuracy, safety, usability, and acceptance of 2 SCs, Ada and Symptoma. METHODS: A randomized, crossover, head-to-head, double-blinded study including consecutive adult patients presenting to the ED at University Hospital Erlangen. Patients completed both SCs, Ada and Symptoma. The primary outcome was the diagnostic accuracy of SCs. In total, 6 blinded independent expert raters classified diagnostic concordance of SC suggestions with the final discharge diagnosis as (1) identical, (2) plausible, or (3) diagnostically different. SC suggestions per patient were additionally classified as safe or potentially life-threatening, and the concordance of Ada's and physician-based triage category was assessed. Secondary outcomes were SC usability (5-point Likert-scale: 1=very easy to use to 5=very difficult to use) and SC acceptance net promoter score (NPS). RESULTS: A total of 450 patients completed the study between April and November 2021. The most common chief complaint was chest pain (160/437, 37%). The identical diagnosis was ranked first (or within the top 5 diagnoses) by Ada and Symptoma in 14% (59/437; 27%, 117/437) and 4% (16/437; 13%, 55/437) of patients, respectively. An identical or plausible diagnosis was ranked first (or within the top 5 diagnoses) by Ada and Symptoma in 58% (253/437; 75%, 329/437) and 38% (164/437; 64%, 281/437) of patients, respectively. Ada and Symptoma did not suggest potentially life-threatening diagnoses in 13% (56/437) and 14% (61/437) of patients, respectively. Ada correctly triaged, undertriaged, and overtriaged 34% (149/437), 13% (58/437), and 53% (230/437) of patients, respectively. A total of 88% (385/437) and 78% (342/437) of participants rated Ada and Symptoma as very easy or easy to use, respectively. Ada's NPS was -34 (55% [239/437] detractors; 21% [93/437] promoters) and Symptoma's NPS was -47 (63% [275/437] detractors and 16% [70/437]) promoters. CONCLUSIONS: Ada demonstrated a higher diagnostic accuracy than Symptoma, and substantially more patients would recommend Ada and assessed Ada as easy to use. The high number of unrecognized potentially life-threatening diagnoses by both SCs and inappropriate triage advice by Ada was alarming. Overall, the trustworthiness of SC recommendations appears questionable. SC authorization should necessitate rigorous clinical evaluation studies to prevent misdiagnoses, fatal triage advice, and misuse of scarce medical resources. TRIAL REGISTRATION: German Register of Clinical Trials DRKS00024830; https://drks.de/search/en/trial/DRKS00024830.
Asunto(s)
Estudios Cruzados , Servicio de Urgencia en Hospital , Humanos , Servicio de Urgencia en Hospital/estadística & datos numéricos , Método Doble Ciego , Masculino , Femenino , Persona de Mediana Edad , Adulto , Anciano , Triaje/métodosRESUMEN
BACKGROUND: Emergency triage, which involves complex decision-making under stress and time constraints, may suffer from inaccuracies due to workplace distractions. A serious game was developed to simulate the triage process and environment. A pilot study was undertaken to collect preliminary data on the effects of distractors on emergency nurse triage accuracy. METHOD: A 2 × 2 factorial randomized controlled trial (RCT) was designed for the study. A sample of 70 emergency room nurses was randomly assigned to three experimental groups exposed to different distractors (noise, task interruptions, and both) and one control group. Nurses had two hours to complete a series of 20 clinical vignettes, in which they had to establish a chief complaint and assign an emergency level. RESULTS: Fifty-five nurses completed approximately 15 vignettes each during the allotted time. No intergroup differences emerged in terms of triage performance. Nurses had a very favorable appreciation of the serious game focusing on triage. CONCLUSION: The results show that both the structure of our study and the serious game can be used to carry out a future RCT on a larger scale. The lack of a distractor effect raises questions about the frequency and intensity required to find a significant impact on triage performance.
Asunto(s)
Servicio de Urgencia en Hospital , Triaje , Humanos , Proyectos Piloto , Triaje/métodos , Femenino , Masculino , Adulto , Enfermeras y Enfermeros/psicología , Persona de Mediana Edad , Estudios de Factibilidad , Enfermería de UrgenciaRESUMEN
OBJECTIVES: In this study, we aimed to validate the performance of the PAX1 and JAM3 methylation (PAX1m/JAM3m) test as a triage tool for detecting cervical intraepithelial neoplasia grade 3 or worse (CIN3 +) in non-16/18 high-risk human papillomavirus-positive patients (non-16/18 hrHPV +). METHODS: The triage performance of liquid-based cytology (LBC) and the PAX1m/JAM3m test for detecting CIN3 + were compared. RESULTS: In total, 1851 participants had cervical histological outcomes and were included in the analysis. The sensitivity/specificity of the LBC test results with atypical squamous cells of undetermined significance or worse (LBC ≥ ASCUS) and the PAX1m/JAM3m test were 90.1%/26.7% and 84.8%/88.5%, respectively. PAX1m/JAM3m( +) had the highest diagnostic AUC (0.866, 95% confidence interval (CI) 0.837-0.896) in the whole cohort. All cancers (n = 20) were detected by PAX1m/JAM3m(+). Compared with LBC ≥ ASCUS, PAX1m/JAM3m(+) reduced the number of patients who needed referral for colposcopy by 57.21% (74.66% vs. 17.45%). The odds ratios for detecting CIN3 + by LBC ≥ ASCUS and PAX1m/JAM3m(+) were 3.3 (95% CI 2.0-5.9) and 42.6 (27.1-69.6), respectively (p < 0.001). The combination of LBC ≥ ASCUS or PAX1m/JAM3m(+) slightly increased the diagnostic sensitivity (98.0%, 95% CI: 95.8-100%) and referral rate (77.09%) but reduced the diagnostic specificity (24.8%, 22.7-26.8%). CONCLUSIONS: In non-16/18 hrHPV(+) women, PAX1m/JAM3m was superior to cytology for detecting CIN3 + . Compared with LBC ≥ ASCUS, PAX1m/JAM3m(+) reduced the number of significant referrals to colposcopy without compromising diagnostic sensitivity.
Asunto(s)
Detección Precoz del Cáncer , Virus del Papiloma Humano , Factores de Transcripción Paired Box , Infecciones por Papillomavirus , Triaje , Displasia del Cuello del Útero , Neoplasias del Cuello Uterino , Femenino , Humanos , China , Metilación de ADN/genética , Detección Precoz del Cáncer/métodos , Detección Precoz del Cáncer/estadística & datos numéricos , Virus del Papiloma Humano/aislamiento & purificación , Factores de Transcripción Paired Box/genética , Infecciones por Papillomavirus/diagnóstico , Estudios Prospectivos , Sensibilidad y Especificidad , Triaje/métodos , Displasia del Cuello del Útero/diagnóstico , Displasia del Cuello del Útero/virología , Neoplasias del Cuello Uterino/diagnóstico , Neoplasias del Cuello Uterino/virologíaRESUMEN
The prompt initiation of stroke treatment significantly influences patient outcomes, highlighting the crucial role of prehospital triage. This study aimed to assess the implementation of the 7-Item Japan Urgent Stroke Triage (JUST-7) score by emergency medical services (EMS) in our region and its effect on emergency transportation for suspected stroke patients. Data were collected from patients suspected of having an acute stroke with a Cincinnati Prehospital Stroke Scale (CPSS) score of 1 or more who were transferred by ambulance within 24 h of symptom onset. Two prehospital stroke scales were employed during different periods: period 1 with CPSS alone (January to December 2020) and period 2 with both CPSS and JUST-7 (January 2021 to March 2023). On-scene time data were obtained from the EMS crews, and data regarding the final diagnosis of patients and their outcomes were obtained from the respective hospitals to which the patients were transferred. These data were compared between periods 1 and 2 and between the CPSS and JUST-7. The results revealed that additional evaluation with JUST-7 did not affect ambulance transport time. The CPSS+JUST-7 approach demonstrated higher specificity in identifying stroke and major artery occlusion than with the CPSS alone; however, an appropriate cut-off value needs to be considered. The JUST-7 achieved a diagnostic concordance rate of 35.9% for the most likely stroke type and 64.0% for the first two most likely types. This research emphasizes the potential of JUST-7 as a valuable addition to prehospital stroke diagnosis protocols. Its flexibility in adapting cut-off values based on regional factors and available medical resources optimizes its utility in diverse healthcare settings. The JUST-7 score is a promising tool for improving patient outcomes through prompt and accurate prehospital assessments.
Asunto(s)
Servicios Médicos de Urgencia , Accidente Cerebrovascular , Triaje , Humanos , Triaje/métodos , Japón , Accidente Cerebrovascular/diagnóstico , Accidente Cerebrovascular/terapia , Anciano , Masculino , Femenino , Persona de Mediana Edad , Anciano de 80 o más Años , Ambulancias , Factores de TiempoRESUMEN
A critical problem that Emergency Departments (EDs) must address is overcrowding, as it causes extended waiting times and increased patient dissatisfaction, both of which are immediately linked to a greater number of patients who leave the ED early, without any evaluation by a healthcare provider (Leave Without Being Seen, LWBS). This has an impact on the hospital in terms of missing income from lost opportunities to offer treatment and, in general, of negative outcomes from the ED process. Consequently, healthcare managers must be able to forecast and control patients who leave the ED without being evaluated in advance. This study is a retrospective analysis of patients registered at the ED of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital of Salerno (Italy) during the years 2014-2021. The goal was firstly to analyze factors that lead to patients abandoning the ED without being examined, taking into account the features related to patient characteristics such as age, gender, arrival mode, triage color, day of week of arrival, time of arrival, waiting time for take-over and year. These factors were used as process measures to perform a correlation analysis with the LWBS status. Then, Machine Learning (ML) techniques are exploited to develop and compare several LWBS prediction algorithms, with the purpose of providing a useful support model for the administration and management of EDs in the healthcare institutions. During the examined period, 688,870 patients were registered and 39188 (5.68%) left without being seen. Of the total LWBS patients, 59.6% were male and 40.4% were female. Moreover, from the statistical analysis emerged that the parameter that most influence the abandonment rate is the waiting time for take-over. The final ML classification model achieved an Area Under the Curve (AUC) of 0.97, indicating high performance in estimating LWBS for the years considered in this study. Various patient and ED process characteristics are related to patients who LWBS. The possibility of predicting LWBS rates in advance could be a valid tool quickly identifying and addressing "bottlenecks" in the hospital organization, thereby improving efficiency.