Utilidad del modelo 5MPB-Toledo para predecir bacteriemia en el paciente con infección del tracto urinario en el servicio de urgencias

Julián-Jiménez, Agustín; Rubio-Díaz, Rafael; Castillo, Juan González del; García‐Lamberechts, Eric Jorge; Sanz, Itziar Huarte; Bustos, Carmen Navarro; González, Francisco Javier Candel

doi:10.1016/j.acuro.2022.04.003

Cited by 5 publications

(31 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tras el análisis de regresión logística por el método de introducción, el modelo asignó una puntuación a cada variable de forma que cada paciente podría obtener de 0 a 10 puntos: PCT ≥ 0,51 ng/ml (4 puntos); Tª>38,3°C (1 punto); índice de Charlson ≥3 (1 punto); FR ≥22 respiraciones por minuto (1 punto); leucocitos >12.000/mm 3 (1 punto); existencia de tiritona/escalofríos (1 punto) y recuento de plaquetas < 150.000/ mm 3 (1 punto). El modelo consigue un excelente ABC-COR en la cohorte de derivación de 0,924 (IC 95%:0,914-0,934) y en la de validación de 0,926 (IC 95%: 0,910-0,942), superior a las publicadas anteriormente [ 35 , 36 ] y solo comparables a las del MPB-Toledo [ 52 , 53 , 55 , 56 ]. En este sentido, el MPB-INFURG-SEMES se compara por sus autores con el modelo de Shapiro en la muestra total obteniéndose un ABC-COR de 0,752 (IC 95%: 0.731-0.733) para los criterios de Shapiro (similar a la comunicada en los estudios de validación de dicho modelo) [ 26 , 27 ].…”

Section: Nuevos Modelos Predictivosunclassified

“…Aunque se han publicado recientemente distintos mode-los predictivos de bacteriemia en pacientes con NAC, ninguno consigue el rendimiento del MPB-Toledo [ 52 , 55 ] o el MPB-INFURG-SEMES [ 59 ] en estos pacientes valorados en los SUH. Así, uno de ellos de Kim et al [ 71 ]., realizado en 8 SUH clasificó a los enfermos en grupos de bajo (1,2% de BV), moderado (7,2% de BV) y alto riesgo (31,5% de BV).…”

Section: Situaciones Clínicas De Especial Interésunclassified

“…En los últimos años se han propuesto distintos modelos predictivos para los SUH de distinta complejidad [26][27][28][29][30][31][32][33][34][35][36][52][53][54][55][56][57][58][59]. En ellos, ha adquirido una gran relevancia el papel que pueden jugar los BMRII [35,36], y en especial la PCT [35,36,[52][53][54][55][56][57][58][59], como factores predictores independientes de bacteriemia. Se ha demostrado que su capacidad pronóstica puede igualar, e incluso superar, la que consiguen distintos modelos que no la incluyen [35,36].…”

Section: Nuevos Modelos Predictivosunclassified

“…Entre ellos, por sus resultados y disponibilidad en los SUH españoles, destacan la proteína C reactiva (PCR), las interleucinas (IL) 6 y 8, el lactato, la proadrenomedulina (proADM), la presepsina, el dímero D y el receptor soluble del activador del plasminógeno de tipo uroquinasa (su-PAR) [35,36,[44][45][46][47][48][49][50][51]. Pero, entre todos los BMRII, la procalcitonina (PCT) obtiene el mejor rendimiento predictivo sobre el resto para predecir bacteriemia y a su vez poder orientar hacia el patógeno causante de la infección, su evolución clínica (a sepsis grave y shock séptico) y la mortalidad [2, 35,36,[52][53][54][55][56][57][58][59]. De ahí que se han propuesto, desarrollado y validado diferentes modelos predictivos que incluyen, como una de sus variables con mayor peso, la PCT [52][53][54][55][56][57][58][59].…”

Section: Introductionunclassified

“…Pero, entre todos los BMRII, la procalcitonina (PCT) obtiene el mejor rendimiento predictivo sobre el resto para predecir bacteriemia y a su vez poder orientar hacia el patógeno causante de la infección, su evolución clínica (a sepsis grave y shock séptico) y la mortalidad [2, 35,36,[52][53][54][55][56][57][58][59]. De ahí que se han propuesto, desarrollado y validado diferentes modelos predictivos que incluyen, como una de sus variables con mayor peso, la PCT [52][53][54][55][56][57][58][59]. Además, un aspecto muy relevante hoy en día es que ya en el 89% de los SUH españoles existe disponibilidad para su uso, convirtiéndose en una herramienta útil y disponible de forma universal [60].…”

Section: Introductionunclassified

See 4 more Smart Citations

New predictive models of bacteremia in the emergency department: a step forward

Julián-Jiménez¹,

Rubio-Díaz²,

Castillo³

et al. 2022

Rev Esp Quimioter

View full text Add to dashboard Cite

The care of patients with a suspected infectious process in hospital emergency department (ED) has increased in the last decade to account for around 15-20% of all daily care. In the initial evaluation of these patients, samples are taken for the different microbiological studies in 45% of the cases, where obtaining blood cultures (BC) predominates, in 14.6% of all of them. The diagnostic yield of these BC is highly variable (2-20%). The most frequent suspected or confirmed foci or infectious processes of true bacteremia (TB) in the ED are urinary tract infection (45%) and respiratory infection (25%). For all these reasons, the suspicion and confirmation of TB has a relevant diagnostic and prognostic significance and requires changing some of the most important decisions to be made in the ED. Among others, indicate discharge or admission, extract BC and administer the appropriate and early antimicrobial. The intention of this review is to highlight the scientific evidence published in the last five years, clarify the current controversies and compare the ability to predict bacteremia of the latest predictive models published since 2017 with those already existing on that date, year in which a review was published that left open the proposal to continue searching for a model with adequate performance for ED. And so, based on it, generate different recommendations that help define the role that these models or scales can have in improving the indication for obtaining BC, as well as in the immediate making of other diagnostic-therapeutic decisions (administration early and appropriate antibiotic treatment, request for complementary tudies and other microbiological samples, intensity of hemodynamic support, need for admission, etc.)

show abstract

Section: Nuevos Modelos Predictivosunclassified

Section: Situaciones Clínicas De Especial Interésunclassified

Section: Nuevos Modelos Predictivosunclassified

Section: Introductionunclassified

See 3 more Smart Citations

New predictive models of bacteremia in the emergency department: a step forward

Julián-Jiménez¹,

Rubio-Díaz²,

Castillo³

et al. 2022

Rev Esp Quimioter

View full text Add to dashboard Cite

show abstract

Combination of machine learning algorithms with natural language processing may increase the probability of bacteremia detection in the emergency department: A retrospective, big-data analysis of 94,482 patients

Ben-Haim,

Yosef,

Rowand

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

Background Prompt diagnosis of bacteremia in the emergency department (ED) is of utmost importance. Nevertheless, the average time to first clinical laboratory finding range from 1 to 3 days. Alongside a myriad of scoring systems for occult bacteremia prediction, efforts for applying artificial intelligence (AI) in this realm are still preliminary. In the current study we combined an AI algorithm with a Natural Language Processing (NLP) algorithm that would potentially increase the yield extracted from clinical ED data. Methods This study involved adult patients who visited our emergency department and at least one blood culture was taken to rule out bacteremia. Using both tabular and free text data, we built an ensemble model that leverages XGBoost for structured data, and logistic regression (LR) on a word-analysis technique called bag-of-words (BOW) Term Frequency-Inverse Document Frequency (TF-IDF), for textual data. All algorithms were designed in order to predict the risk for bacteremia with ED patients whose blood cultures were sent to the laboratory. Results The study cohort comprised 94,482 individuals, of whom 52% were males. The prevalence of bacteremia in the entire cohort was 9.7%. The model trained on the tabular data yielded an area under the curve (AUC) of 73.7% for XGBoost, while the LR that was trained on the free text achieved an AUC of 71.3%. After checking a range of weights, the best combination was for 55% weight on the XGBoost prediction and 45% weight on the LR prediction. The final model prediction yielded an AUC of 75.6%. Conclusion Harnessing artificial intelligence to the task of bacteremia surveillance in the ED settings by a combination of both free text and tabular data analysis improved predictive performance compared to using tabular data alone. We recommend that future AI applications based on our findings should be assimilated into the clinical routines of ED physicians.

show abstract

Diagnostic accuracy of procalcitonin for bacteremia in the emergency department: a systematic review

Julián-Jiménez,

Eduardo García,

Merinos-Sánchez

et al. 2023

Rev Esp Quimioter

View full text Add to dashboard Cite

Introduction. Obtaining blood cultures (HC) is performed in 15% of the patients treated with suspicion of infection in the Hospital Emergency Services (ED) with a variable diagnostic yield (2-20%). The 30-day mortality of patients with bacteremia is two or three times higher than the rest with the same process. Procalcitonin (PCT) is a biomarker that has been used as a tool to help predict bacteremia in HEDs. The main objective of this systematic review is to investigate the diagnostic accuracy of PCT in predicting true bacteraemia in adult patients treated with clinical suspicion of infection in the ED, as well as to identify a specific PCT value as the most relevant from the clinical decision diagnostic point of view that can be recommended for decision making Method. A systematic review was performed following the PRISMA guidelines in the PubMed, Web of Science, EMBASE, Lilacs, Cochrane, Epistemonikos, Tripdatabase and ClinicalTrials.gov databases from January 2010 to May 31, 2023 without language restrictions and using a combination of MESH terms: “Bacteremia/ Bacteraemia/ Blood Stream Infection”, “Procalcitonin”, “Emergencies/ Emergency/ Emergency Department” and “Adults”. Observational cohort studies and partially an systematic review were included. No meta-analysis techniques were performed, but the results were compared narratively. Results. A total of 1,372 articles were identified, of which 20 that met the inclusion criteria were finally analyzed. The included studies represent a total of 18,120 processed HC with 2,877 bacteraemias (15.88%). Ten studies were rated as high, 9 moderate and 1 low quality. The AUC-COR of all the studies ranges from 0.68 (95% CI: 0.59-0.77) to 0.98 (95% CI: 0.97-0.99). The PCT value >0.5 ng/ml is the most widely used and proposed in up to ten of the works included in this systematic review, whose estimated mean yield is an AUC-COR of 0.833. If only the results of the 6 high-quality studies using a cut-off point (PC) >0.5 ng/mL PCT are taken into account, the estimated mean AUC-COR result is 0.89 with Se of 77.6% and It is 78%. Conclusions. PCT has a considerable diagnostic accuracy of bacteraemia in patients treated in EDs for different infectious processes. The CP>0.5 ng/ml has been positioned as the most suitable for predicting the existence of bacteraemia and can be used to reasonably rule it out.

show abstract

Utilidad del modelo 5MPB-Toledo para predecir bacteriemia en el paciente con infección del tracto urinario en el servicio de urgencias

Cited by 5 publications

References 21 publications

New predictive models of bacteremia in the emergency department: a step forward

New predictive models of bacteremia in the emergency department: a step forward

Combination of machine learning algorithms with natural language processing may increase the probability of bacteremia detection in the emergency department: A retrospective, big-data analysis of 94,482 patients

Diagnostic accuracy of procalcitonin for bacteremia in the emergency department: a systematic review

Contact Info

Product

Resources

About