Frailty Index Based on Common Laboratory Tests for Patients Starting Home-Based Medical Care.

OBJECTIVES: To determine whether a Frailty Index based on laboratory tests (FI-lab) is associated with clinical outcomes independently of a standard nonlaboratory Frailty Index (FI-clinical) in older patients starting home-based medical care. DESIGN: Secondary analysis of data from a multicenter prospective cohort study. SETTING AND PARTICIPANTS: Patients aged ≥65 years who were starting home-based medical care services provided by doctors and nurses at Nagoya, Japan. METHODS: We calculated FI-lab (proportion of abnormal results out of 25 commonly tested laboratory parameters) and FI-clinical using 42 items based on data obtained at enrollment. The primary outcome was mortality within 2 years after starting home-based medical care. A sensitivity analysis was also conducted with 1-year mortality as the outcome. Other outcomes included hospitalization and nursing home admission within 2 years. RESULTS: In total, 188 patients (mean age 79.9 ± 10.2 years, 57.5% male) were included. The median FI-lab was 0.40 [interquartile range (IQR) 0.29-0.50] and the median FI-clinical was 0.32 (IQR 0.24-0.43). Sixty-nine patients (36.7%) died within 2 years of starting home-based medical care. A Cox proportional hazards regression analysis including age, sex, FI-lab, and FI-clinical as independent variables revealed that FI-lab was associated with 2-year mortality independently of FI-clinical [FI-lab per 0.1 unit, odds ratio (OR) 1.49, 95% CI 1.25-1.77; FI-clinical per 0.1 unit, OR 1.13, 95% CI 0.90-1.41]. The sensitivity analysis showed similar results for 1-year mortality. Neither FI-lab nor FI-clinical was associated with hospitalization or nursing home admission within 2 years. CONCLUSIONS AND IMPLICATIONS: FI-lab was associated with 2-year mortality in patients starting home-based medical care, independently of FI-clinical, and may be useful for risk assessment in this population. Studies with larger sample sizes are needed.

Outcome-based analytical performance specifications: current status and future challenges.

Analytical performance specifications (APS) based on outcomes refer to how 'good' the analytical performance of a test needs to be to do more good than harm to the patient. Analytical performance of a measurand affects its clinical performance. Without first setting clinical performance requirements, it is difficult to define how good analytically the test needs to be to meet medical needs. As testing is indirectly linked to health outcomes through clinical decisions on patient management, often simulation-based studies are used to assess the impact of analytical performance on the probability of clinical outcomes which is then translated to Model 1b APS according to the Milan consensus. This paper discusses the related key definitions, concepts and considerations that should assist in finding the most appropriate methods for deriving Model 1b APS. We review the advantages and limitations of published methods and discuss the criteria for transferability of Model 1b APS to different settings. We consider that the definition of the clinically acceptable misclassification rate is central to Model 1b APS. We provide some examples and guidance on a more systematic approach for first defining the clinical performance requirements for tests and we also highlight a few ideas to tackle the future challenges associated with providing outcome-based APS for laboratory testing.

Plasma D-asparagine and the D/L-serine ratio reflect chronic kidney diseases in children regardless of physique.

Biomarkers that accurately reflect renal function are essential in management of chronic kidney diseases (CKD). However, in children, age/physique and medication often alter established renal biomarkers. We studied whether amino acid enantiomers in body fluids correlate with renal function and whether they are influenced by physique or steroid medication during development. We conducted a prospective study of children 2 to 18 years old with and without CKD. We analyzed associations of serine/asparagine enantiomers in body fluids with major biochemical parameters as well as physique. To study consequences of kidney dysfunction and steroids on serine/asparagine enantiomers, we generated juvenile mice with uninephrectomy, ischemic reperfusion injury, or dexamethasone treatment. We obtained samples from 27 children, of which 12 had CKD due to congenital (n = 7) and perinatal (n = 5) causes. Plasma D-asparagine and the D/L-serine ratio had robust, positive linear associations with serum creatinine and cystatin C, and detected CKD with high sensitivity and specificity, uninfluenced by body size or biochemical parameters. In the animal study, kidney dysfunction increased plasma D-asparagine and the D/L-serine ratio, but dexamethasone treatment did not. Thus, plasma D-asparagine and the D/L-serine ratio can be useful markers for renal function in children.

Facilitators of and Barriers to the Use of a Digital Self-Management Service for Diagnostic Testing: Focus Group Study With Potential Users.

BACKGROUND: Health care lags in digital transformation, despite the potential of technology to improve the well-being of individuals. The COVID-19 pandemic has accelerated the uptake of technology in health care and increased individuals' willingness to perform self-management using technology. A web-based service, Directlab Online, provides consumers with direct digital access to diagnostic test packages, which can digitally support the self-management of health. OBJECTIVE: This study aims to identify the facilitators, barriers, and needs of Directlab Online, a self-management service for web-based access to diagnostic testing. METHODS: A qualitative method was used from a potential user's perspective. The needs and future needs for, facilitators of, and barriers to the use of Directlab Online were evaluated. Semistructured focus group meetings were conducted in 2022. Two focus groups were focused on sexually transmitted infection test packages and 2 were focused on prevention test packages. Data analysis was performed according to the principles of the Framework Method. The Consolidated Framework for Implementation Research was used to categorize the facilitators and barriers. RESULTS: In total, 19 participants, with a mean age of 34.32 (SD 14.70) years, participated in the focus groups. Important barriers were a lack of privacy information, too much and difficult information, and a commercial appearance. Important facilitators were the right amount of information, the right kind of tests, and the involvement of a health care professional. The need for a service such as Directlab Online was to ensure its availability for users' health and to maintain their health. CONCLUSIONS: According to the participants, facilitators and barriers were comprehension of the information, the goal of the website, and the overall appearance of the service. Although the service was developed in cocreation with health care professionals and users, the needs did not align. The users preferred understandable and adequate, but not excessive, information. In addition, they preferred other types of tests to be available on the service. For future research, it would be beneficial to focus on cocreation between the involved medical professionals and users to develop, improve, and implement a service such as Directlab Online.

The 2023 WSES guidelines on the management of trauma in elderly and frail patients.

BACKGROUND: The trauma mortality rate is higher in the elderly compared with younger patients. Ageing is associated with physiological changes in multiple systems and correlated with frailty. Frailty is a risk factor for mortality in elderly trauma patients. We aim to provide evidence-based guidelines for the management of geriatric trauma patients to improve it and reduce futile procedures. METHODS: Six working groups of expert acute care and trauma surgeons reviewed extensively the literature according to the topic and the PICO question assigned. Statements and recommendations were assessed according to the GRADE methodology and approved by a consensus of experts in the field at the 10th international congress of the WSES in 2023. RESULTS: The management of elderly trauma patients requires knowledge of ageing physiology, a focused triage, including drug history, frailty assessment, nutritional status, and early activation of trauma protocol to improve outcomes. Acute trauma pain in the elderly has to be managed in a multimodal analgesic approach, to avoid side effects of opioid use. Antibiotic prophylaxis is recommended in penetrating (abdominal, thoracic) trauma, in severely burned and in open fractures elderly patients to decrease septic complications. Antibiotics are not recommended in blunt trauma in the absence of signs of sepsis and septic shock. Venous thromboembolism prophylaxis with LMWH or UFH should be administrated as soon as possible in high and moderate-risk elderly trauma patients according to the renal function, weight of the patient and bleeding risk. A palliative care team should be involved as soon as possible to discuss the end of life in a multidisciplinary approach considering the patient's directives, family feelings and representatives' desires, and all decisions should be shared. CONCLUSIONS: The management of elderly trauma patients requires knowledge of ageing physiology, a focused triage based on assessing frailty and early activation of trauma protocol to improve outcomes. Geriatric Intensive Care Units are needed to care for elderly and frail trauma patients in a multidisciplinary approach to decrease mortality and improve outcomes.

Quality of Answers of Generative Large Language Models Versus Peer Users for Interpreting Laboratory Test Results for Lay Patients: Evaluation Study.

BACKGROUND: Although patients have easy access to their electronic health records and laboratory test result data through patient portals, laboratory test results are often confusing and hard to understand. Many patients turn to web-based forums or question-and-answer (Q&A) sites to seek advice from their peers. The quality of answers from social Q&A sites on health-related questions varies significantly, and not all responses are accurate or reliable. Large language models (LLMs) such as ChatGPT have opened a promising avenue for patients to have their questions answered. OBJECTIVE: We aimed to assess the feasibility of using LLMs to generate relevant, accurate, helpful, and unharmful responses to laboratory test-related questions asked by patients and identify potential issues that can be mitigated using augmentation approaches. METHODS: We collected laboratory test result-related Q&A data from Yahoo! Answers and selected 53 Q&A pairs for this study. Using the LangChain framework and ChatGPT web portal, we generated responses to the 53 questions from 5 LLMs: GPT-4, GPT-3.5, LLaMA 2, MedAlpaca, and ORCA_mini. We assessed the similarity of their answers using standard Q&A similarity-based evaluation metrics, including Recall-Oriented Understudy for Gisting Evaluation, Bilingual Evaluation Understudy, Metric for Evaluation of Translation With Explicit Ordering, and Bidirectional Encoder Representations from Transformers Score. We used an LLM-based evaluator to judge whether a target model had higher quality in terms of relevance, correctness, helpfulness, and safety than the baseline model. We performed a manual evaluation with medical experts for all the responses to 7 selected questions on the same 4 aspects. RESULTS: Regarding the similarity of the responses from 4 LLMs; the GPT-4 output was used as the reference answer, the responses from GPT-3.5 were the most similar, followed by those from LLaMA 2, ORCA_mini, and MedAlpaca. Human answers from Yahoo data were scored the lowest and, thus, as the least similar to GPT-4-generated answers. The results of the win rate and medical expert evaluation both showed that GPT-4's responses achieved better scores than all the other LLM responses and human responses on all 4 aspects (relevance, correctness, helpfulness, and safety). LLM responses occasionally also suffered from lack of interpretation in one's medical context, incorrect statements, and lack of references. CONCLUSIONS: By evaluating LLMs in generating responses to patients' laboratory test result-related questions, we found that, compared to other 4 LLMs and human answers from a Q&A website, GPT-4's responses were more accurate, helpful, relevant, and safer. There were cases in which GPT-4 responses were inaccurate and not individualized. We identified a number of ways to improve the quality of LLM responses, including prompt engineering, prompt augmentation, retrieval-augmented generation, and response evaluation.

At-home testing for respiratory viruses: a minireview of the current landscape.

The landscape of at-home testing using over-the-counter (OTC) tests has been evolving over the last decade. The United States Food and Drug Administration Emergency Use Authorization rule has been in effect since the early 2000s, and it was widely employed during the severe acute respiratory syndrome coronavirus 2 pandemic to authorize antigen and nucleic acid detection tests for use in central laboratories as well as OTC. During the pandemic, the first at-home tests for respiratory viruses became available for consumer use, which opened the door for additional respiratory virus OTC tests. Concerns may exist regarding the public's ability to properly collect samples, perform testing, interpret results, and report results to public health authorities. However, favorable comparison studies between OTC testing and centralized laboratory test results suggest that OTC testing may have a place in healthcare, and it is likely here to stay. This mini-review of OTC tests for viral respiratory diseases will briefly cover the regulatory and reimbursement environment, current OTC test availability, as well as the advantages and limitations of OTC tests.

Advances in sepsis biomarkers.

Sepsis, a dysregulated host immune response to an infectious agent, significantly increases morbidity and mortality for hospitalized patients worldwide. This chapter reviews (1) the basic principles of infectious diseases, pathophysiology and current definition of sepsis, (2) established sepsis biomarkers such lactate, procalcitonin and C-reactive protein, (3) novel, newly regulatory-cleared/approved biomarkers, such as assays that evaluate white blood cell properties and immune response molecules, and (4) emerging biomarkers and biomarker panels to highlight future directions and opportunities in the diagnosis and management of sepsis.

Sludge-based candidate reference materials for enhanced quality control of particulate processes in total organic carbon analysis for wastewater1.

Accurate analyses of total organic carbon (TOC) encompassing particulate organic carbon in wastewater are key for evaluating the behavior of particulate organic contaminants and maintaining the carbon mass balance throughout the wastewater treatment process. This study was conducted to develop candidate reference materials of environmental origin from excess sludge collected from wastewater treatment facilities, primarily receiving industrial wastewater and livestock manure as the main sources. Homogeneity and stability assessments for total carbon (TC) and TOC were conducted in the particle samples following the standardized procedures of ISO Guide 35 and ISO 13258. The results showed that high inorganic carbon (IC) content in particles, such as YJ(500) (IC: 29%), rendered them unsuitable for TOC quality control (QC), as they increased uncertainty in both homogeneity and stability assessments. Additionally, a13C NMR analysis revealed that samples with a high (O-alkyl)/(C-H-alkyl) ratio in their carbon structures exhibited relatively low stability. Through the homogeneity and stability assessments, a particle sample, YJ(100), was selected as the reference material (RM); the assigned values were as follows: 30.78% for TC and 27.94% for TOC, with uncertainties of 0.01% and 1.1%, respectively. Furthermore, considering sample transportation conditions, the safe storage period for the RM particles was determined to be 2 weeks under harsh conditions (at 40 °C). In our inter-laboratory test (n = 8) using the particle samples, we confirmed that the particle samples can effectively enhance particle processing QC and validate a proposed suspended solids pretreatment method. This study showcases valuable environmental particle sample production and evaluation, offering potential advancements in the QC of TOC analysis for wastewater samples.

Integrated Machine Learning Approach for the Early Prediction of Pressure Ulcers in Spinal Cord Injury Patients.

(1) Background: Pressure ulcers (PUs) substantially impact the quality of life of spinal cord injury (SCI) patients and require prompt intervention. This study used machine learning (ML) techniques to develop advanced predictive models for the occurrence of PUs in patients with SCI. (2) Methods: By analyzing the medical records of 539 patients with SCI, we observed a 35% incidence of PUs during hospitalization. Our analysis included 139 variables, including baseline characteristics, neurological status (International Standards for Neurological Classification of Spinal Cord Injury [ISNCSCI]), functional ability (Korean version of the Modified Barthel Index [K-MBI] and Functional Independence Measure [FIM]), and laboratory data. We used a variety of ML methods-a graph neural network (GNN), a deep neural network (DNN), a linear support vector machine (SVM_linear), a support vector machine with radial basis function kernel (SVM_RBF), K-nearest neighbors (KNN), a random forest (RF), and logistic regression (LR)-focusing on an integrative analysis of laboratory, neurological, and functional data. (3) Results: The SVM_linear algorithm using these composite data showed superior predictive ability (area under the receiver operating characteristic curve (AUC) = 0.904, accuracy = 0.944), as demonstrated by a 5-fold cross-validation. The critical discriminators of PU development were identified based on limb functional status and laboratory markers of inflammation. External validation highlighted the challenges of model generalization and provided a direction for future research. (4) Conclusions: Our study highlights the importance of a comprehensive, multidimensional data approach for the effective prediction of PUs in patients with SCI, especially in the acute and subacute phases. The proposed ML models show potential for the early detection and prevention of PUs, thus contributing substantially to improving patient care in clinical settings.

Deep Learning Prediction of Cervical Spine Surgery Revision Outcomes Using Standard Laboratory and Operative Variables.

BACKGROUND: Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art model of revision prediction of cervical spine surgery using laboratory and operative variables. METHODS: Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016 and 2022 were identified (N = 3151), and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and time frame. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables. RESULTS: Red blood cell count, hemoglobin, hematocrit, mean corpuscular hemoglobin concentration, red blood cell distribution width, platelet count, carbon dioxide, anion gap, and calcium all were significantly associated with ≥1 revision cohorts. For the prediction of 3-month revision, the deep neural network achieved an area under the receiver operating characteristic curve of 0.833. The model demonstrated increased performance for anterior versus posterior and arthrodesis versus decompression procedures. CONCLUSIONS: Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables in a cervical spine surgery cohort. This work used standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of one-size-fits-all risk scores for spine procedures.

Statistical considerations for some issues in clinical bridging studies evaluating companion diagnostic devices.

An in vitro diagnostic device (IVD) that is essential for the safe and effective use of a corresponding therapeutic product is commonly referred to as companion diagnostic device. Clinical trials using companion diagnostic devices (tests) together with therapies can yield the information necessary to address whether both products are safe and effective. A clinical trial ideally assesses safety and effectiveness of a therapy, where the clinical trial enrolls subjects based on the final market ready companion diagnostic test (CDx). However, such a requirement may be difficult to accomplish or impractical to achieve at the time of the clinical trial enrollment, due to unavailability of the CDx. Instead, clinical trial assay(s) (CTA), which are not the final marketable product, are often used in enrollment of patients in a clinical trial. When CTA is used for subject enrollment, a clinical bridging study provides a mechanism to bridge the clinical efficacy of the therapeutic product from CTA to CDx. This manuscript reviews some issues and challenges commonly associated with clinical bridging studies, including missing data, use of local tests for enrollment, prescreening before enrollment, and evaluation of CDx for low positive rate biomarkers, with particular focus on clinical trials using a binary endpoint and provide alternative statistical methodologies to assess effectiveness of CDx.

Rigorous evaluation of genetic and epigenetic effects on clinical laboratory measurements using Japanese monozygotic twins.

The investigation of environmental effects on clinical measurements using individual samples is challenging because their genetic and environmental factors are different. However, using monozygotic twins (MZ) makes it possible to investigate the influence of environmental factors as they have the same genetic factors within pairs because the difference in the clinical traits within the MZ mostly reflect the influence of environmental factors. We hypothesized that the within-pair differences in the traits that are strongly affected by genetic factors become larger after genetic risk score (GRS) correction. Using 278 Japanese MZ pairs, we compared the change in within-pair differences in each of the 45 normalized clinical measurements before and after GRS correction, and we also attempted to correct for the effects of genetic factors to identify Cytosine-phosphodiester-Guanine (CpG) sites in DNA sequences with epigenetic effects that are regulated by genetic factors. Five traits were classified into the high heritability group, which was strongly affected by genetic factors. CpG sites could be classified into three groups: regulated only by environmental factors, regulated by environmental factors masked by genetic factors, and regulated only by genetic factors. Our method has the potential to identify trait-related methylation sites that have not yet been discovered.

Using machine learning to develop smart reflex testing protocols.

OBJECTIVE: Reflex testing protocols allow clinical laboratories to perform second line diagnostic tests on existing specimens based on the results of initially ordered tests. Reflex testing can support optimal clinical laboratory test ordering and diagnosis. In current clinical practice, reflex testing typically relies on simple "if-then" rules; however, this limits the opportunities for reflex testing since most test ordering decisions involve more complexity than traditional rule-based approaches would allow. Here, using the analyte ferritin as an example, we propose an alternative machine learning-based approach to "smart" reflex testing. METHODS: Using deidentified patient data, we developed a machine learning model to predict whether a patient getting CBC testing will also have ferritin testing ordered. We evaluate applications of this model to reflex testing by assessing its performance in comparison to possible rule-based approaches. RESULTS: Our underlying machine learning models performed moderately well in predicting ferritin test ordering (AUC=0.731 in reference to actual ordering) and demonstrated promising potential to underlie key clinical applications. In contrast, none of the many traditionally framed, rule-based, hypothetical reflex protocols we evaluated offered sufficient agreement with actual ordering to be clinically feasible. Using chart review, we further demonstrated that the strategic deployment of our model could avoid important ferritin test ordering errors. CONCLUSIONS: Machine learning may provide a foundation for new types of reflex testing with enhanced benefits for clinical diagnosis.

Cognitive factors impacting patient understanding of laboratory test information.

Laboratory testing can provide information useful to promote patient health literacy and ultimately patient well-being. The human state of mind involves not only cognition but also emotion and motivation factors when receiving, processing, and acting upon information. The cognitive load for patients acquiring and processing new information is high. Modes of distribution can affect both attention to and receipt of information. Implicit unconscious biases can affect whom and what patients believe. Positive wording and framing of information with salience for patients can evoke positive emotions. Providing patients with the gist, or essential meaning, of information can positively influence decision-making. What laboratorians provide as information helps to combat mis- and disinformation. Laboratorians can actively participate in measures to improve the patient experience in health care by developing and contributing to high-quality information to enable timely, meaningful communication and interpretation of test results.

Clinical Decision Support System in laboratory medicine.

Clinical Decision Support Systems (CDSS) have been implemented in almost all healthcare settings. Laboratory medicine (LM), is one of the most important structured health data stores, but efforts are still needed to clarify the use and scope of these tools, especially in the laboratory setting. The aim is to clarify CDSS concept in LM, in the last decade. There is no consensus on the definition of CDSS in LM. A theoretical definition of CDSS in LM should capture the aim of driving significant improvements in LM mission, prevention, diagnosis, monitoring, and disease treatment. We identified the types, workflow and data sources of CDSS. The main applications of CDSS in LM were diagnostic support and clinical management, patient safety, workflow improvements, and cost containment. Laboratory professionals, with their expertise in quality improvement and quality assurance, have a chance to be leaders in CDSS.

Comprehensive improvements in the emergency laboratory test process based on information technology.

OBJECTIVE: To explore the application effects of information technology (IT) on emergency laboratory testing procedures. METHODS: In this study, IT-based optimisation of the emergency laboratory testing process was implemented between October and December 2021. Thus, the emergency laboratory test reports from January to September 2021 were placed into the pre-optimised group, while those from January to September 2022 were categorised into the post-optimised group. Besides, the emergency laboratory test report time, emergency laboratory test report time limit coincidence rate, error rate, and employee and patient satisfaction levels in individual months and across the whole period were described. Moreover, changes in the above indicators before and after the implementation of IT-based optimisation were explored and the application effects of IT-based optimisation were also evaluated. RESULTS: The emergency laboratory test report times after the implementation of IT-based optimisation were shorter than those before IT-based optimisation (P < 0.05). The total number of laboratory test items before and after information optimization amounted to 222,139 and 259,651, respectively. Also, IT-based optimisation led to an increase in the emergency laboratory test report time limit coincidence rate from 98.77% to 99.03% (P < 0.05), while the emergency laboratory test report error rate fell from 0.77‱ to 0.15‱ (P < 0.05). Additionally, IT-based optimisation resulted in increases in both employee satisfaction, from 80.65% to 93.55% (N = 31, P > 0.05), and patient satisfaction, from 93.06% to 98.44% (P < 0.05). CONCLUSION: The automation and IT-based optimisation of the emergency laboratory testing process significantly reduces the emergency laboratory test report time and error rate. Additionally, IT-driven optimization enhances the alignment of emergency laboratory test report deadlines and enhances the overall quality and safety of emergency laboratory testing.

Systematically analysis of decompensated cirrhotic patients with spontaneous bacterial peritonitis to identify diagnostic and prognostic indexes.

BACKGROUND: Spontaneous bacterial peritonitis (SBP) is a common complication in patients with cirrhosis. The diagnosis of SBP is still mostly based on ascites cultures and absolute ascites polymorphonuclear (PMN) cell count, which restricts the widely application in clinical settings. This study aimed to identify reliable and easy-to-use biomarkers for both diagnosis and prognosis of cirrhotic patients with SBP. METHODS: We conducted a retrospective study including 413 cirrhotic patients from March 2013 to July 2022 in the First Affiliated Hospital of Guangxi Medical University. Patients' clinical characteristics and laboratory indices were collected and analyzed. Two machine learning methods (Xgboost and LASSO algorithms) and a logistic regression analysis were adopted to screen and validate the indices associated with the risk of SBP. A predictive model was constructed and validated using the estimated area under curve (AUC). The indices related to the survival of cirrhotic patients were also analyzed. RESULTS: A total of 413 cirrhotic patients were enrolled in the study, of whom 329 were decompensated and 84 were compensated. 52 patients complicated and patients with SBP had a poorer Child-Pugh score (P < 0.05). Patients with SBP had a greater proportion of malignancies than those without SBP(P < 0.05). The majority of laboratory test indicators differed significantly between patients with and without SBP (P < 0.05). Albumin, neutrophil-to-lymphocyte ratio (NLR), and ferritin-to-neutrophil ratio (FNR) were found to be independently associated with SBP in decompensated cirrhotic patients using LASSO algorithms, and logistic regression analysis. The model established by the three indices showed a high predictive value with an AUC of 0.808. Furthermore, increased neutrophils, ALP, and C-reactive protein-to-albumin ratio (CAR) were associated with the shorter survival time of patients with decompensated cirrhosis, and the combination of these indices showed a greater predictive value for cirrhotic patients. CONCLUSIONS: The present study identified FNR as a novel index in the diagnosis of SBP in decompensated patients with cirrhosis. A model based on neutrophils, ALP and CAR showed high performance in predicting the prognosis of patients with decompensated cirrhosis.

Short-term All-cause In-hospital Mortality Prediction by Machine Learning Using Numeric Laboratory Results.

Introduction: A critical value (or panic value) is a laboratory test result that significantly deviates from the normal value and represents a potentially life-threatening condition requiring immediate action. Although notification of critical values by critical value list (CVL) is a well-established method, their contribution to mortality prediction is unclear. Methods: A total of 335,430 clinical laboratory results from 92,673 patients from July 2018 to December 2019 were used. Data in the first 12 months were divided into two datasets at a ratio of 70:30, and a 7-day mortality prediction model by machine learning (eXtreme Gradient Boosting [XGB] decision tree) was created using stratified random undersampling data of the 70% dataset. Mortality predictions by the CVL and XGB model were validated using the remaining 30% of the data, as well as different 6-month datasets from July to December 2019. Results: The true results which were the sum of correct predictions by the XGB model and CVL using the remaining 30% data were 61,535 and 61,024 tests, and the false results which were the sum of incorrect predictions were 5,492 and 6,003, respectively. Furthermore, the true results with the different datasets were 105,956 and 102,061 tests, and the false results were 6,052 and 9,947, respectively. The XGB model was significantly better than CVL (p < 0.001) in both datasets.The receiver operating characteristic-area under the curve values for the 30% and validation data by XGB were 0.9807 and 0.9646, respectively, which were significantly higher than those by CVL (0.7549 and 0.7172, respectively). Conclusions: Mortality prediction within 7 days by machine learning using numeric laboratory results was significantly better than that by conventional CVL. The results indicate that machine learning enables timely notification to healthcare providers and may be safer than prediction by conventional CVL.

Evaluation of Laboratory Findings of Patients with Coronavirus Disease 2019 in Kerman, Iran.

Background & Objective: Since December 2019 in Wuhan, China there is a new form of pneumonia and after expansion in other countries, World Health Organization (WHO) called it Coronavirus Disease 2019 (COVID-19). Since the clinical laboratory findings have played an important role in the progression of the disease, this study aimed to evaluate the laboratory findings in COVID-19 patients (before vaccination). Methods: In this case-control study that was conducted from February to August 2020; the laboratory test status in 101 positive COVID-19 patients was evaluated and compared with 101 healthy individuals. Results: The results of our study showed that 21% of patients had low WBC, 24.75% low RBC, 37.62%, low Hb, 18.81% with low HCT, 29.7%, low Plt, 41.58% had High PT, 71.29% high CRP, 17.82% high urea, 11.88% high CR, 15.84% high LDH, 10.89% low sodium, 14.75% low potassium (K). The quantitative examination of blood factors showed that lymph%, mixed%, PLT, HCT, Hb, and RBC were higher in the control group than in the case group. While Neu%, WBC, PTT, CRP, UREA, LDH, K in the patient group were higher than in the control group. Conclusion: According to the results of the study, it can be concluded that in the clinical treatment of COVID-19 patients, much attention should be paid to the laboratory indicators to identify and intervene early in critically ill patients.