Enhancing pneumonia prognosis in the emergency department: a novel machine learning approach using complete blood count and differential leukocyte count combined with CURB-65 score.

BACKGROUND: Pneumonia poses a major global health challenge, necessitating accurate severity assessment tools. However, conventional scoring systems such as CURB-65 have inherent limitations. Machine learning (ML) offers a promising approach for prediction. We previously introduced the Blood Culture Prediction Index (BCPI) model, leveraging solely on complete blood count (CBC) and differential leukocyte count (DC), demonstrating its effectiveness in predicting bacteremia. Nevertheless, its potential in assessing pneumonia remains unexplored. Therefore, this study aims to compare the effectiveness of BCPI and CURB-65 in assessing pneumonia severity in an emergency department (ED) setting and develop an integrated ML model to enhance efficiency. METHODS: This retrospective study was conducted at a 3400-bed tertiary medical center in Taiwan. Data from 9,352 patients with pneumonia in the ED between 2019 and 2021 were analyzed in this study. We utilized the BCPI model, which was trained on CBC/DC data, and computed CURB-65 scores for each patient to compare their prognosis prediction capabilities. Subsequently, we developed a novel Cox regression model to predict in-hospital mortality, integrating the BCPI model and CURB-65 scores, aiming to assess whether this integration enhances predictive performance. RESULTS: The predictive performance of the BCPI model and CURB-65 score for the 30-day mortality rate in ED patients and the in-hospital mortality rate among admitted patients was comparable across all risk categories. However, the Cox regression model demonstrated an improved area under the ROC curve (AUC) of 0.713 than that of CURB-65 (0.668) for in-hospital mortality (p<0.001). In the lowest risk group (CURB-65=0), the Cox regression model outperformed CURB-65, with a significantly lower mortality rate (2.9% vs. 7.7%, p<0.001). CONCLUSIONS: The BCPI model, constructed using CBC/DC data and ML techniques, performs comparably to the widely utilized CURB-65 in predicting outcomes for patients with pneumonia in the ED. Furthermore, by integrating the CURB-65 score and BCPI model into a Cox regression model, we demonstrated improved prediction capabilities, particularly for low-risk patients. Given its simple parameters and easy training process, the Cox regression model may be a more effective prediction tool for classifying patients with pneumonia in the emergency room.

Bacteremia detection from complete blood count and differential leukocyte count with machine learning: complementary and competitive with C-reactive protein and procalcitonin tests.

BACKGROUND: Biomarkers, such as leukocyte count, C-reactive protein (CRP), and procalcitonin (PCT), have been commonly used to predict the occurrence of life-threatening bacteremia and provide prognostic information, given the need for prompt intervention. However, such diagnosis methods require much time and money. Therefore, we propose a method with a high prediction capability using machine learning (ML) models based on complete blood count (CBC) and differential leukocyte count (DC) and compare its performance with traditional CRP or PCT biomarker methods and those of models incorporating CRP or PCT biomarkers. METHODS: We collected 366,586 daily blood culture (BC) results, of which 350,775 (93.2%), 308,803 (82.1%), and 23,912 (6.4%) cases were issued CBC/DC (CBC/DC group), CRP with CBC/DC (CRP&CBC/DC group), and PCT with CBC/DC (PCT&CBC/DC group), respectively. For the ML methods, conventional logistic regression and random forest models were selected, trained, applied, and validated for each group. Fivefold validation and prediction capability were also evaluated and reported. RESULTS: Overall, the ML methods, such as the random forest model, demonstrated promising performances. When trained with CBC/DC data, it achieved an area under the ROC curve (AUC) of 0.802, which is superior to the prediction conventionally made with CRP/PCT levels (0.699/0.731). Upon evaluating the performance enhanced by incorporating CRP or PCT biomarkers, it reported no substantial AUC increase with the addition of either CRP or PCT to CBC/DC data, which suggests the predicting power and applicability of using only CBC/DC data. Moreover, it showed competitive prognostic capability compared to the PCT test with similar all-cause in-hospital mortality (45.10% vs. 47.40%) and overall median survival time (27 vs. 25 days). CONCLUSIONS: The ML models using only CBC/DC data yielded more accurate bacteremia predictions compared to those by methods using CRP and PCT data and reached similar prognostic performance as by PCT data. Thus, such models are potentially complementary and competitive with traditional CRP and PCT biomarkers for conducting and guiding antibiotic usage.

Predicting 2-Day Mortality of Thrombocytopenic Patients Based on Clinical Laboratory Data Using Machine Learning.

BACKGROUND: Clinical laboratories have traditionally used a single critical value for thrombocytopenic events. This system, however, could lead to inaccuracies and inefficiencies, causing alarm fatigue and compromised patient safety. OBJECTIVES: This study shows how machine learning (ML) models can provide auxiliary information for more accurate identification of critical thrombocytopenic patients when compared with the traditional notification system. RESEARCH DESIGN: A total of 50,505 patients' platelet count and other 26 additional laboratory datasets of each thrombocytopenic event were used to build prediction models. Conventional logistic regression and ML methods, including random forest (RF), artificial neural network, stochastic gradient descent (SGD), naive Bayes, support vector machine, and decision tree, were applied to build different models and evaluated. RESULTS: Models using logistic regression [area under the curve (AUC)=0.842], RF (AUC=0.859), artificial neural network (AUC=0.867), or SGD (AUC=0.826) achieved the desired average AUC>0.80. The highest positive predictive value was obtained by the SGD model in the testing data (72.2%), whereas overall, the RF model showed higher sensitivity and total positive predictions in both the training and testing data and outperformed other models. The positive 2-day mortality predictive rate of RF methods is as high as 46.1%-significantly higher than using the traditional notification system at only 14.8% [χ2(1)=81.66, P<0.001]. CONCLUSIONS: This study demonstrates a data-driven ML approach showing a significantly more accurate 2-day mortality prediction after a critical thrombocytopenic event, which can reinforce the accuracy of the traditional notification system.

Incorporating Statistical Test and Machine Intelligence Into Strain Typing of Staphylococcus haemolyticus Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry.

Staphylococcus haemolyticus is one of the most significant coagulase-negative staphylococci, and it often causes severe infections. Rapid strain typing of pathogenic S. haemolyticus is indispensable in modern public health infectious disease control, facilitating the identification of the origin of infections to prevent further infectious outbreak. Rapid identification enables the effective control of pathogenic infections, which is tremendously beneficial to critically ill patients. However, the existing strain typing methods, such as multi-locus sequencing, are of relatively high cost and comparatively time-consuming. A practical method for the rapid strain typing of pathogens, suitable for routine use in clinics and hospitals, is still not available. Matrix-assisted laser desorption ionization-time of flight mass spectrometry combined with machine learning approaches is a promising method to carry out rapid strain typing. In this study, we developed a statistical test-based method to determine the reference spectrum when dealing with alignment of mass spectra datasets, and constructed machine learning-based classifiers for categorizing different strains of S. haemolyticus. The area under the receiver operating characteristic curve and accuracy of multi-class predictions were 0.848 and 0.866, respectively. Additionally, we employed a variety of statistical tests and feature-selection strategies to identify the discriminative peaks that can substantially contribute to strain typing. This study not only incorporates statistical test-based methods to manage the alignment of mass spectra datasets but also provides a practical means to accomplish rapid strain typing of S. haemolyticus.

Application of a MALDI-TOF analysis platform (ClinProTools) for rapid and preliminary report of MRSA sequence types in Taiwan.

BACKGROUND: The accurate and rapid preliminarily identification of the types of methicillin-resistant Staphylococcus aureus (MRSA) is crucial for infection control. Currently, however, expensive, time-consuming, and labor-intensive methods are used for MRSA typing. By contrast, matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a potential tool for preliminary lineage typing. The approach has not been standardized, and its performance has not been analyzed in some regions with geographic barriers (e.g., Taiwan Island). METHODS: The mass spectra of 306 MRSA isolates were obtained from multiple reference hospitals in Taiwan. The multilocus sequence types (MLST) of the isolates were determined. The spectra were analyzed for the selection of characteristic peaks by using the ClinProTools software. Furthermore, various machine learning (ML) algorithms were used to generate binary and multiclass models for classifying the major MLST types (ST5, ST59, and ST239) of MRSA. RESULTS: A total of 10 peaks with the highest discriminatory power (m/z range: 2,082-6,594) were identified and evaluated. All the single peaks revealed significant discriminatory power during MLST typing. Moreover, the binary and multiclass ML models achieved sufficient accuracy (82.80-94.40% for binary models and >81.00% for multiclass models) in classifying the major MLST types. CONCLUSIONS: A combination of MALDI-TOF MS analysis and ML models is a potentially accurate, objective, and efficient tool for infection control and outbreak investigation.

Duration of electroencephalographic recordings in patients with epilepsy.

PURPOSE: Previous studies have demonstrated different diagnostic yields with electroencephalography (EEG). Due to the small sample sizes or different patient populations (outpatients or inpatients only) in these previous studies, the clinical use of routine EEG and outpatient/inpatient video-EEG monitoring (VEM) needs further clarification. In this study, we investigated EEGs obtained from patients referred by epileptologists; by comparing the results of different EEG methods, we sought to determine the optimal durations and specific types of EEG recordings for different clinical situations. METHODS: The data from 335 routine EEGs, 281 3 h outpatient VEMs, and 247 inpatient VEMs (>48 h) were reviewed. We analyzed the latency to the first epileptiform discharge or clinical event. RESULTS: In patients undergoing outpatient VEMs, 48% of the first epileptiform discharges appeared within 20 min, and 64% appeared within 30 min. In patients undergoing inpatient VEMs, 21.2% had their first attack within 3h. The second peak of event occurrence was during the 33rd-36th h. Only 3.5% of the seizures were recorded after 57 h. The detection rate of epileptiform discharges was higher for 3h outpatient VEM than for routine EEG (54.1% versus 16.4%, p<0.01). Epileptic and/or nonepileptic events were recorded in 45.8% of the inpatient VEMs, the diagnostic yield of which was higher than for outpatient VEMs (p<0.01). Since the patients in this study had been selected to limit the bias between each group, the diagnostic yield of EEGs in this study are likely to have been higher than those found in routine practice. Patients with generalized epilepsy had a shorter latency to the first epileptiform discharge compared to patients with localization-related epilepsy (mean, 22.1 min versus 33.9 min, p<0.05). CONCLUSIONS: Two-thirds of epileptiform discharges were detected within 30 min of VEM. A 30-min recording is recommended for routine EEG examinations that aim to detect epileptiform discharges. A 3h outpatient VEM is a reasonable option when a routine EEG fails to detect epileptiform discharges. The latency to the first epileptiform discharge was shorter in patients with generalized epilepsy than in patients with localization-related epilepsy. 48 h of inpatient VEM might be adequate for detecting the target events.