Clinical knowledge-guided deep reinforcement learning for sepsis antibiotic dosing recommendations.

Sepsis is the third leading cause of death worldwide. Antibiotics are an important component in the treatment of sepsis. The use of antibiotics is currently facing the challenge of increasing antibiotic resistance (Evans et al., 2021). Sepsis medication prediction can be modeled as a Markov decision process, but existing methods fail to integrate with medical knowledge, making the decision process potentially deviate from medical common sense and leading to underperformance. (Wang et al., 2021). In this paper, we use Deep Q-Network (DQN) to construct a Sepsis Anti-infection DQN (SAI-DQN) model to address the challenge of determining the optimal combination and duration of antibiotics in sepsis treatment. By setting sepsis clinical knowledge as reward functions to guide DQN complying with medical guidelines, we formed personalized treatment recommendations for antibiotic combinations. The results showed that our model had a higher average value for decision-making than clinical decisions. For the test set of patients, our model predicts that 79.07% of patients will achieve a favorable prognosis with the recommended combination of antibiotics. By statistically analyzing decision trajectories and drug action selection, our model was able to provide reasonable medication recommendations that comply with clinical practices. Our model was able to improve patient outcomes by recommending appropriate antibiotic combinations in line with certain clinical knowledge.

Gastrointestinal manifestations of critical ill heatstroke patients and their associations with outcomes: A multicentre, retrospective, observational study.

BACKGROUND: Extreme heat exposure is a growing health problem, and the effects of heat on the gastrointestinal (GI) tract is unknown. This study aimed to assess the incidence of GI symptoms associated with heatstroke and its impact on outcomes. AIM: To assess the incidence of GI symptoms associated with heatstroke and its impact on outcomes. METHODS: Patients admitted to the intensive care unit (ICU) due to heatstroke were included from 83 centres. Patient history, laboratory results, and clinically relevant outcomes were recorded at ICU admission and daily until up to day 15, ICU discharge, or death. GI symptoms, including nausea/vomiting, diarrhoea, flatulence, and bloody stools, were recorded. The characteristics of patients with heatstroke concomitant with GI symptoms were described. Multivariable regression analyses were performed to determine significant predictors of GI symptoms. RESULTS: A total of 713 patients were included in the final analysis, of whom 132 (18.5%) patients had at least one GI symptom during their ICU stay, while 26 (3.6%) suffered from more than one symptom. Patients with GI symptoms had a significantly higher ICU stay compared with those without. The mortality of patients who had two or more GI symptoms simultaneously was significantly higher than that in those with one GI symptom. Multivariable logistic regression analysis revealed that older patients with a lower GCS score on admission were more likely to experience GI symptoms. CONCLUSION: The GI manifestations of heatstroke are common and appear to impact clinically relevant hospitalization outcomes.

Prediction of prokinetic agents in critically ill patients with feeding intolerance: a prospective observational clinical study.

Background: Prokinetic agents are currently considered the first-line therapy to improve gastric emptying when feeding intolerance occurred in critically ill adults. In this study, we developed a technique to assess the feasibility of predicting prokinetic agent efficacy in critically ill patients. Methods: The first images of each patient were obtained after EFI had occurred but before the first dose of prokinetic agents was administered and additional images were obtained every morning until the seventh day. The gastric antrum echodensity was recorded based on grayscale values (50th percentile, ED50; 85th percentile, ED85; mean, EDmean) and daily energy and protein intake was collected as the judgment for effective and ineffective group. A receiver operating characteristic curve was analyzed to distinguish the thresholds between the two groups and thus determine the ability of the gastric antrum echodensity to predict the efficacy of prokinetic agents. Results: In total, 83 patients were analyzed. Patients in the ineffective group had a higher ED50 (58.13 ± 14.48 vs. 49.88 ± 13.78, p < 0.001, difference 95% CI: 5.68, 10.82), ED85 (74.81 ± 16.41 vs. 65.70 ± 16.05, p < 0.001, difference 95% CI:6.16, 12.05), and EDmean (60.18 ± 14.31 vs. 51.76 ± 14.08, p < 0.001, difference 95% CI: 5.85, 11.00) than those in the effective group. Patients in the effective group more easily reached the target energy 16.21 ± 7.98 kcal/kg vs. 9.17 ± 6.43 kcal/kg (p < 0.001), 0.72 ± 0.38 g/kg vs. 0.42 ± 0.31 g/kg (p < 0.001) than in the ineffective group intake by day. Conclusion: The gastric antrum echodensity might serve as a tool for judging the efficacy of prokinetic agents, helping clinicians to decide whether to use prokinetic agents or place a post-pyloric tube when feeding intolerance occurs in critically ill patients.Clinical trial registration:http://www.chictr.org.cn/addproject2.aspx, ChiCTR2200058373. Registered 7 April 2022.

Disparities between randomized clinical trial participants and sepsis patients in real-world.

BACKGROUND: The external validity or "generalizability" of randomized controlled trials (RCTs) often needs be considered when making treatment decisions. We evaluate whether participants in large multicenter RCTs investigating sepsis were similar in age, disease severity, comorbidities, and mortality to the general population of sepsis patients. METHODS: Using MEDLINE, PubMed, and the Cochrane Central Register of Controlled Trials, RCTs that enrolled 100 or more adult sepsis patients from two or more sites published from 01 January 2000 to 04 August 2019 were identified. The weighted mean age of trial participants was calculated as the main variable, and it was compared with the mean ages of the overall populations derived from the MIMIC database and the EICU database. Two researchers independently screened all abstracts and performed data extraction, then aggregated the data using a random effects model. Multiple linear regression was used to determine whether any factors were significantly associated with age disparities. RESULTS: The mean age of the 60,577 participants in the 94 trials included in the analysis was significantly lower than those of the patients in the MIMIC and EICU databases (weighted mean age 62.28 years vs. 64.47 years for MIMIC and 65.20 years for EICU; both p < 0.001). Trial participants were less likely to have known comorbidities such as diabetes (13.96% vs. 30.64% for MIMIC and 35.75% for EICU; both p < 0.001). The weighted mortality rate in trial participants was higher than that in patients in the MIMIC and EICU databases (29.33% vs. 20.72% for MIMIC and 17.53% for EICU; both p < 0.001). Differences in age, severity score, and comorbidities remained statistically significant in sensitivity analyses. Multivariable regression suggested that commercially supported trials were more likely to include patients with higher severity scores (p = 0.002), but after adjustment for study region and sepsis diagnosis inclusion in such trials was not significantly associated with age. CONCLUSIONS: On average, trial participants were younger than the general sepsis patient population. Commercial support influenced patient selection. Efforts to understand and address the above-described patient disparities are necessary to improve the generalizability of RCT results. TRIAL REGISTRATION: PROSPERO CRD42019145692.

Sepsis-induced Coagulopathy Subphenotype Identification by Latent Class Analysis

Background: Recent studies have shown that anticoagulant therapy has heterogeneous treatment effects on patients with sepsis-induced coagulopathy (SIC). Aims: To identify the latent phenotypes of patients with SIC. Study design: Retrospective cohort study. Methods: We obtained data of patients with SIC from the Medical Information Mart for Intensive Care IV database. SIC subphenotypes were identified by latent class analysis (LCA) and K-means clustering. Clinical and laboratory variables were obtained in patients who met the diagnostic criteria for SIC. The baseline characteristics of the patients and the association between the heterogeneity of anticoagulant therapy and clinical outcomes (28-day and in-hospital mortality) were compared between the subphenotypes. Results: We identified 4,993 patients with SIC. The LCA and K-means clustering analysis robustly identified three subphenotypes of SIC. Class 1 patients (n = 1,808) had the lowest blood cell counts (leukocytes, erythrocytes, and platelets). Class 2 patients (n = 1,157) had severe coagulopathy with a high prothrombin time and international normalized ratio, multiple-organ dysfunction, high lactate, sequential organ failure assessment score, and mortality. Class 3 (n = 2,028) were older, had more comorbidities, a higher fibrinogen concentration, and lower plasma and platelet infusion rates. After variable adjustments, heparin therapy reduced the 28-day mortality (odds ratio [OR] 0.39, 0.30-0.49, p < 0.001) and in-hospital mortality (OR 0.42, 0.33-0.53, p < 0.001) only in class 2. Conclusion: Three SIC subphenotypes were defined using clinical findings and laboratory variables. The effects of heparin treatment differ between the subphenotypes. This finding will facilitate the identification of target patients with SIC who should receive anticoagulant therapy.

Chinese experts' consensus on the application of intensive care big data.

The development of intensive care medicine is inseparable from the diversified monitoring data. Intensive care medicine has been closely integrated with data since its birth. Critical care research requires an integrative approach that embraces the complexity of critical illness and the computational technology and algorithms that can make it possible. Considering the need of standardization of application of big data in intensive care, Intensive Care Medicine Branch of China Health Information and Health Care Big Data Society, Standard Committee has convened expert group, secretary group and the external audit expert group to formulate Chinese Experts' Consensus on the Application of Intensive Care Big Data (2022). This consensus makes 29 recommendations on the following five parts: Concept of intensive care big data, Important scientific issues, Standards and principles of database, Methodology in solving big data problems, Clinical application and safety consideration of intensive care big data. The consensus group believes this consensus is the starting step of application big data in the field of intensive care. More explorations and big data based retrospective research should be carried out in order to enhance safety and reliability of big data based models of critical care field.

Increased diaphragm echodensity correlates with postoperative pulmonary complications in patients after major abdominal surgery: a prospective observational study.

BACKGROUND: Associated with increased morbidity and mortality, postoperative pulmonary complications (PPCs) often occur after major abdominal surgery. Diaphragmatic dysfunction is suggested to play an important role in the development of PPCs and diaphragm echodensity can be used as an indicator of diaphragm function. This study aimed to determine whether diaphragm echodensity could predict the occurrence of PPCs in patients after major abdominal surgery. METHODS: Diaphragm ultrasound images of patients after major abdominal surgery were collected during spontaneous breathing trials. Echodensity was quantified based on the right-skewed distribution of grayscale values (50th percentile, ED50; 85th percentile, ED85; mean, EDmean). Intra- and inter-analyzer measurement reproducibility was determined. Outcomes including occurrence of PPCs, reintubation rate, duration of ventilation, and length of ICU stay were recorded. RESULTS: Diaphragm echodensity was measured serially in 117 patients. Patients who developed PPCs exhibited a higher ED50 (35.00 vs. 26.00, p < 0.001), higher ED85 (64.00 vs. 55.00, p < 0.001) and higher EDmean (39.32 vs. 33.98, p < 0.001). In ROC curve analysis, the area under the curve of ED50 for predicting PPCs was 0.611. The optimal ED50 cutoff value for predicting the occurrence of PPCs was 36. According to this optimal ED50 cutoff value, patients were further divided into a high-risk group (ED50 > 36, n = 35) and low-risk group (ED50 ≤ 36, n = 82). Compared with the low-risk group, the high-risk group had a higher incidence of PPCs (unadjusted p = 0.003; multivariate-adjusted p < 0.001). CONCLUSION: Diaphragm echodensity can be feasibly and reproducibly measured in mechanically ventilated patients. The increase in diaphragm echodensity during spontaneous breathing trials was related to an increased risk of PPCs in patients after major abdominal surgery.

Association between early elevated phosphate and mortality among critically ill elderly patients: a retrospective cohort study.

BACKGROUND: Phosphate disturbances are relatively common in hospitalized patients, especially in critically ill patients. The abnormal phosphate levels may indicate an abnormal body condition. However, little is known about the association between elevated serum phosphate and outcome in critically ill elderly patients. Therefore, the purpose of the present study was to investigate the association between early elevated phosphate and mortality in critically ill elderly patients. METHODS: The present study was a retrospective cohort study based on the medical information mart for intensive care IV (MIMIC-IV) database. Patients with age ≥60 years old were enrolled in the present study. The primary outcome in the present study was ICU mortality. Univariate and multivariate Cox proportional hazard regression analyses were used to evaluate the association between early elevated phosphate and ICU mortality in critically ill elderly patients. RESULTS: Twenty-four thousand two hundred eighty-nine patients were involved in this analysis and 2,417 patients died in ICU. The median age of involved patients was 78.4 (67.5, 82.9) years old. The median level of serum phosphate in the survivor group was 3.6 (3.0, 4.3) mg/dL, and the median level of serum phosphate in the non-survivor group was 4.4 (3.4, 5.8) mg/dL. The level of serum phosphate in the non-survivor group was significantly higher than the survivor group (4.4 vs. 3.6, P<0.001). The multivariate Cox proportional hazard regression demonstrated that elevated phosphate was an independent risk factor for ICU mortality, after adjustment for other covariates (HR=1.056, 95%CI: 1.028-1.085, P<0.001). CONCLUSIONS: In critically ill elderly patients, early elevated phosphate was significantly associated with increased ICU mortality.

Association of Gastric Antrum Echodensity and Acute Gastrointestinal Injury in Critically Ill Patients.

(1) Background: Acute muscle inflammation leads to increased sonographic echodensity. We developed a technique to characterize the echodensity of the gastric antrum wall and assess its feasibility in evaluating the severity of acute gastrointestinal injury (AGI); (2) Methods: The B-mode images of the gastric antrum of each enrolled patient were obtained daily by point-of-care ultrasound (POCUS). The 50th percentile, 85th percentile, and mean value of the grayscale distribution according to histogram analysis (ED50, ED85, and EDmean, respectively) were used to characterize the gastric antrum echodensity. Consistency and correlation analyses were performed to evaluate the feasibility and reproducibility of gastric antrum echodensity measurement. The association of gastric antrum echodensity with the severity of AGI and its ability to predict feeding intolerance (FI) were analyzed; (3) Results: In total, 206 POCUS images of 43 patients were analyzed. The gastric antrum echodensity measurements had sufficient intra- and inter-investigator reliabilities (intraclass correlation coefficient >0.9 for all parameters). The ED50 showed a significant upward trend as AGI severity increased, as well as ED85 and EDmean (p for trend <0.001, respectively). Patients who experienced FI had a higher ED50 (67.8 vs. 56.1, p = 0.02), ED85 (85.6 vs. 71.2, p = 0.01), and EDmean (70.3 vs. 57.6, p = 0.01) upon enteral feeding initiation; (4) Conclusions: Measurement of gastric antrum echodensity was technically feasible and reproducible in ventilated patients. Increased gastric antrum echodensity was associated with greater severity of AGI. Patients with higher gastric antrum echodensity upon enteral nutrition initiation via a nasogastric tube were more likely to develop FI.

Mean arterial pressure/norepinephrine equivalent dose index as an early measure of initiation time for enteral nutrition in patients with shock: A prospective observational study.

OBJECTIVES: The aim of this study was to compare the predictive ability of the norepinephrine dose (NE), norepinephrine equivalent dose (NEQ), and mean arterial pressure (MAP)/NEQ index to predict the optimal time to initiate enteral nutrition in patients with shock on vasopressors. METHODS: We prospectively enrolled patients with shock who were receiving vasopressors and followed them for ≤28 d after enrollment. Patients who developed feeding intolerance (FI) during the follow-up period were allocated to the FI group and the remaining patients were allocated to the non-feeding intolerance (non-FI) group. The primary outcome was FI occurrence. The receiving operating characteristic curve (ROC) was used to evaluate the thresholds and predictive ability of NE, NEQ, and the MAP/NEQ index to predict FI. RESULTS: Of the 66 patients enrolled, 47 developed FI. The MAP/NEQ index showed good predictive ability 6 h before EN initiation. The threshold of the MAP/NEQ index for predicting FI was 417 mmHg·µg·kg·min-1 (specificity: 52.9%, sensitivity: 81%) with an area under the ROC curve (AUC) of 70.3% (95% confidence interval [CI], 55.1-85.5; P = 0.015). The threshold for the NE was 0.2 µg·kg/min-1 (specificity: 47.1%, sensitivity: 88.1%), with an AUC of 65.3% (95% CI, 48.2-82.5; P = 0.067), and that for the NEQ was 0.2 µg·kg/min-1 (specificity: 47.1%, sensitivity: 88.1%), with an AUC of 66.2% (95% CI, 49.3-83; P = 0.053). CONCLUSIONS: Compared with the NE and NEQ, it could be possible with the MAP/NEQ index to distinguish earlier whether patients with shock receiving vasopressors were suitable for initiation of EN, thereby avoiding FI.

Association Between Serum Osmolality and Acute Kidney Injury in Critically Ill Patients: A Retrospective Cohort Study.

Purposes: Acute kidney injury (AKI) is a common complication in critically ill patients and is usually associated with poor outcomes. Serum osmolality has been validated in predicting critically ill patient mortality. However, data about the association between serum osmolality and AKI is still lacking in ICU. Therefore, the purpose of the present study was to investigate the association between early serum osmolality and the development of AKI in critically ill patients. Methods: The present study was a retrospective cohort analysis based on the medical information mart for intensive care III (MIMIC-III) database. 20,160 patients were involved in this study and divided into six subgroups according to causes for ICU admission. The primary outcome was the incidence of AKI after ICU admission. The association between early serum osmolality and AKI was explored using univariate and multivariate logistic regression analyses. Results: The normal range of serum osmolality was 285-300 mmol/L. High serum osmolality was defined as serum osmolality >300 mmol/L and low serum osmolality was defined as serum osmolality <285 mmol/L. Multivariate logistic regression indicated that high serum osmolality was independently associated with increased development of AKI with OR = 1.198 (95% CL = 1.199-1.479, P < 0.001) and low serum osmolality was also independently associated with increased development of AKI with OR = 1.332 (95% CL = 1.199-1.479, P < 0.001), compared with normal serum osmolality, respectively. Conclusions: In critically ill patients, early high serum osmolality and low serum osmolality were both independently associated with an increased risk of development of AKI.

Using Machine Learning Algorithms to Predict Hospital Acquired Thrombocytopenia after Operation in the Intensive Care Unit: A Retrospective Cohort Study.

Hospital acquired thrombocytopenia (HAT) is a common hematological complication after surgery. This research aimed to develop and compare the performance of seven machine learning (ML) algorithms for predicting patients that are at risk of HAT after surgery. We conducted a retrospective cohort study which enrolled adult patients transferred to the intensive care unit (ICU) after surgery in West China Hospital of Sichuan University from January 2016 to December 2018. All subjects were randomly divided into a derivation set (70%) and test set (30%). ten-fold cross-validation was used to estimate the hyperparameters of ML algorithms during the training process in the derivation set. After ML models were developed, the sensitivity, specificity, area under the curve (AUC), and net benefit (decision analysis curve, DCA) were calculated to evaluate the performances of ML models in the test set. A total of 10,369 patients were included and in 1354 (13.1%) HAT occurred. The AUC of all seven ML models exceeded 0.7, the two highest were Gradient Boosting (GB) (0.834, 0.814-0.853, p < 0.001) and Random Forest (RF) (0.828, 0.807-0.848, p < 0.001). There was no difference between GB and RF (0.834 vs. 0.828, p = 0.293); however, these two were better than the remaining five models (p < 0.001). The DCA revealed that all ML models had high net benefits with a threshold probability approximately less than 0.6. In conclusion, we found that ML models constructed by multiple preoperative variables can predict HAT in patients transferred to ICU after surgery, which can improve risk stratification and guide management in clinical practice.

Association between Domperidone Administered via Feeding Tube and Feeding Success in Critically Ill Patients with Enteral Feeding Intolerance.

One nutritional challenge in critically ill patients is enteral feeding intolerance (EFI), but current prokinetic agents have uncertain efficacy and safety profiles. We conducted a longitudinal, single-center, retrospective study to evaluate the efficacy and safety of domperidone administered via the feeding tube versus intravenous (IV) metoclopramide among adult patients with EFI. The primary outcome was feeding success, defined as the proportion of patients with average percentage of daily protein prescription >80% of the target dose. The secondary outcomes were safety endpoints. Among 28,814 intensive care unit (ICU) admissions, 552 patients with EFI were included, 38 receiving IV metoclopramide and 514 receiving tube feeding domperidone. The proportion of feeding success in patients receiving tube feeding domperidone and IV metoclopramide was 42.02% and 21.05%, respectively. After 1:2 matching (IV metoclopramide to tube feeding domperidone), the proportion of feeding success was 40.79% in patients receiving tube feeding domperidone. Basically, after matching, there were no differences in any safety endpoints (mortality and length of stay during ICU and hospitalization, organ-support-treatment free days) or adverse events (recurrence of EFI, electrolyte disturbance, abdominal and other symptoms) between the two groups (p > 0.05). A logistic regression analysis in the matched cohort indicated that domperidone administered via the feeding tube was independently associated with feeding success. We found that tube feeding domperidone was efficient in increasing enteral nutrition delivery performance among critically ill adult patients with EFI.

Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method.

The purpose of this study was to determine whether a deep-learning-based assessment system could facilitate preoperative grading of meningioma. This was a retrospective study conducted at two institutions covering 643 patients. The system, designed with a cascade network structure, was developed using deep-learning technology for automatic tumor detection, visual assessment, and grading prediction. Specifically, a modified U-Net convolutional neural network was first established to segment tumor images. Subsequently, the segmentations were introduced into rendering algorithms for spatial reconstruction and another DenseNet convolutional neural network for grading prediction. The trained models were integrated as a system, and the robustness was tested based on its performance on an external dataset from the second institution involving different magnetic resonance imaging platforms. The results showed that the segment model represented a noteworthy performance with dice coefficients of 0.920 ± 0.009 in the validation group. With accurate segmented tumor images, the rendering model delicately reconstructed the tumor body and clearly displayed the important intracranial vessels. The DenseNet model also achieved high accuracy with an area under the curve of 0.918 ± 0.006 and accuracy of 0.901 ± 0.039 when classifying tumors into low-grade and high-grade meningiomas. Moreover, the system exhibited good performance on the external validation dataset.

Development and internal validation of a simple prognostic score for early sepsis risk stratification in the emergency department.

OBJECTIVES: No validated, simple, powerful and continuously monitorable risk prediction tools are available for patients with sepsis during the early phases in the emergency department (ED). We sought to derive a novel Simple Sepsis Early Prognostic Score (SSEPS) composed of physiological indicators that do not depend on laboratory tests and that can be used by emergency clinicians in predicting outcomes in patients with sepsis. DESIGN: Retrospective cohort analysis of a collected data source. PARTICIPANTS: Patients with sepsis admitted to the ED of the West China Hospital of Sichuan University between July 2015 and June 2016 were included. We excluded patients who were pregnant, those with cardiac or respiratory arrest, and those using vasoactive drugs before admission to the ED. PRIMARY OUTCOME MEASURES: 28-day all-cause mortality. RESULTS: The SSEPS consisted of age, heart rate, respiratory rate and altered consciousness. Patients in the development cohort with higher SSEPS had a significantly higher mortality (first tertile vs second tertile vs third tertile: 12.5% vs 28.6% vs 53.5%, p<0.001). The area under the receiver operating characteristic curve for SSEPS was 0.762 (95% CI 0.686 to 0.838), which was similar to Sequential Organ Failure Assessment (SOFA) (area under the curve: 0.745, 95% CI 0.692 to 0.798) and Acute Physiology and Chronic Health Evaluation (APACHE II) (area under the curve: 0.750, 95% CI 0.681 to 0.819). Moreover, the decision curve analysis showed that the net benefit of SSEPS was higher than SOFA and APACHE II at any probability threshold. CONCLUSION: The SSEPS is simple and useful for clinicians in stratifying high-risk patients with sepsis at the early phase of ED admission.

Early risk stratification of acute myocardial infarction using a simple physiological prognostic scoring system: insights from the REACP study.

BACKGROUND: A more accurate and simpler scoring systems for early risk stratification of acute myocardial infarction at admission can accelerate and improve decision-making. AIM: To develop and validate a simple physiological prognostic scoring system for early risk stratification in patients with acute myocardial infarction. METHODS: Easily accessible physiological vital signs and demographic characteristics of patients with acute myocardial infarction at the time of presentation in the multicentre Retrospective Evaluation of Acute Chest Pain study were used to develop a multivariate logistic regression model predicting 12 and 24-month mortality. The study population consisted of 2619 patients from seven hospitals and was divided into a 70% sample for model derivation and a 30% sample for model validation. A nomogram was created to enable prospective risk stratification for clinical care. RESULTS: The simple physiological prognostic scoring system consisted of age, heart rate, body mass index and Killip class. The area under the receiver operating characteristic curve of the simple physiological prognostic scoring system was superior to that of several risk scoring systems in clinical use. Net reclassification improvement, integrated discrimination improvement and decision curve analysis of the derivation set also revealed superior performance to the Global Registry of Acute Coronary Events score, and the Hosmer-Lemeshow test indicated good calibration for predicting mortality in patient with acute myocardial infarction in the validation set (P = 0.612). CONCLUSION: This simple physiological prognostic scoring system may be a useful risk stratification tool for early assessment of patients with acute myocardial infarction.