Diagnosis Capability Research Articles

Ai-corona: Radiologist-assistant deep learning framework for COVID-19 diagnosis in chest CT scans.

The development of medical assisting tools based on artificial intelligence advances is essential in the global fight against COVID-19 outbreak and the future of medical systems. In this study, we introduce ai-corona, a radiologist-assistant deep learning framework for COVID-19 infection diagnosis using chest CT scans. Our framework incorporates an EfficientNetB3-based feature extractor. We employed three datasets; the CC-CCII set, the MasihDaneshvari Hospital (MDH) cohort, and the MosMedData cohort. Overall, these datasets constitute 7184 scans from 5693 subjects and include the COVID-19, non-COVID abnormal (NCA), common pneumonia (CP), non-pneumonia, and Normal classes. We evaluate ai-corona on test sets from the CC-CCII set, MDH cohort, and the entirety of the MosMedData cohort, for which it gained AUC scores of 0.997, 0.989, and 0.954, respectively. Our results indicates ai-corona outperforms all the alternative models. Lastly, our framework's diagnosis capabilities were evaluated as assistant to several experts. Accordingly, We observed an increase in both speed and accuracy of expert diagnosis when incorporating ai-corona's assistance.

Comprehensive microbiota alterations in IBD and improved diagnostic accuracy for IBD using multi‐kingdom microbial features

Background Inflammatory bowel disease(IBD),including Crohn's Disease(CD) and ulcerative colitis (UC), is closely linked with altered gut microbiota.Roles of bacteria in IBD have been widely investigated, whereas other microbial kingdoms, fungi, archaea, virus, are less explored. Here, we aim to investigate the multi-kingdom microbial alterations and their capabilities for IBD diagnosis. Methods A total of 968 stool samples (292 CD, 305 UC and 371 controls) of untreated patients from iHMP were collected. Differential microorganisms were identified via wilcoxon test followed by adjustment for confounders. Inter-kingdom co-occurrence interactions analysis was performed by SparCC then microorganism modules were clustered by “MCODE”. Subsequently, neural networks algorithm was used to build diagnostic models for CD or UC with single- or multi-kingdom microbial features and the best panel of biomarkers was further identified by recursive feature elimination. Moreover, diagnostic models were validated in additional independent cohorts. Differential microbial pathways were analyzed to further explore functional alterations in CD and UC. Results In CD and UC, the microbial compositional change was identified in different kingdoms. Compared to controls, we identified 41 bacteria, 37 fungi, 40 archaea and 50 viruses with differential abundance in CD. Similarly, 63 bacteria, 52 fungi, 58 archaea and 39 viruses with differential abundance were detected in UC. Moreover, inter-kingdom interactions were more complex in IBD than controls, especially the interactions between fungal Aspergillusand BeAn 58058 virus. Notably, the diagnostic models constructed with multi-kingdom microbial features performed better (AUC of 0.90 in CD and 0.91 in UC) than that with single kingdom microbial features. The diagnostic models also showed reliable accuracy in independent cohorts with an average AUC of 0.93 (CD) and 0.74 (UC), respectively. Among these biomarkers, bacterial Bacteroidesand fungalAspergillusare the main contributors to the distinguishing ability in both CD and UC diagnostic models. In addition, pathways related to lipid and terpenoids metabolism and immune response were altered in CD and UC, such as glycosphingolipid biosynthesis, carotenoid biosynthesis and IL-17 signaling pathway. Conclusions Our study investigated comprehensivepathogenic microbiota of IBD, which encompasses bacteria, fungi, virus and archaea. And the combination of multi-kingdom microbial biomarkers may serve as effective tools for CD and UC diagnosis, which outperforms single kingdom biomarkers. The alterations of microbial inter-kingdom interactions and cross-kingdom functional changes provide new insight in understanding pathological mechanisms of IBD.

PIVKA-II serves as a potential biomarker that complements AFP for the diagnosis of hepatocellular carcinoma

BackgroundHepatocellular carcinoma (HCC) is one of the most common malignant tumors of the digestive system and has high morbidity and mortality rates. It is essential to search new biomarkers to improve the accuracy of early HCC diagnosis. Therefore, we evaluated the diagnostic value of prothrombin induced by vitamin K deficiency or antagonist- II (PIVKA-II) as a potential biomarker that complements α-fetoprotein (AFP) in HCC by detecting the serum PIVKA-II levels.MethodsSerum PIVKA-II levels were compared in 168 HCC patients, 150 benign liver disease patients and 153 healthy controls to investigate the PIVKA-II potential to be a HCC biomarker. Receiver operating characteristic curve (ROC) analysis was used to evaluate the value of PIVKA-II in the diagnosis of HCC and its complementary role of AFP. The correlation between serum PIVKA-II levels and clinicopathological characteristics was analyzed to study the value of PIVKA-II in assessing HCC progression and prognosis. Finally, the ability of PIVKA-II in assessing the surgical treatment effects of HCC was studied by comparing the pre- and post-operative serum PIVKA-II levels in 89 HCC patients.ResultsSerum PIVKA-II levels in HCC patients were significantly higher than that in patients with benign liver disease and healthy controls. The PIVKA-II performance in the diagnosing HCC as an individual biomarker was remarkable. The combined detection of PIVKA-II and AFP improved the diagnostic efficiency of HCC. PIVKA-II retained significant diagnosis capabilities for AFP-negative HCC patients. Significant correlations were found between PIVKA-II expression levels and some clinicopathological characteristics, including tumor size, tumor stage, tumor metastasis, differentiation degree and complications. PIVKA-II expression obviously decreased after surgical resection.ConclusionsPIVKA-II is a promising serum biomarker for the HCC diagnosis that can be used as a supplement for AFP. The combined diagnosis of the two markers greatly improved the diagnostic efficiency of HCC. The PIVKA-II levels in HCC patients were widely associated with clinicopathological characteristics representing tumor cell dissemination and/or poor prognosis. PIVKA-II can be used to evaluate the curative effects of HCC resection.

Bearing Fault Feature Extraction and Fault Diagnosis Method Based on Feature Fusion

Bearing is one of the most important parts of rotating machinery with high failure rate, and its working state directly affects the performance of the entire equipment. Hence, it is of great significance to diagnose bearing faults, which can contribute to guaranteeing running stability and maintenance, thus promoting production efficiency and economic benefits. Usually, the bearing fault features are difficult to extract effectively, which results in low diagnosis performance. To solve the problem, this paper proposes a bearing fault feature extraction method and it establishes a bearing fault diagnosis method that is based on feature fusion. The basic idea of the method is as follows: firstly, the time-frequency feature of the bearing signal is extracted through Wavelet Packet Transform (WPT) to form the time-frequency characteristic matrix of the signal; secondly, the Multi-Weight Singular Value Decomposition (MWSVD) is constructed by singular value contribution rate and entropy weight. The features of the time-frequency feature matrix obtained by WPT are further extracted, and the features that are sensitive to fault in the time-frequency feature matrix are retained while the insensitive features are removed; finally, the extracted feature matrix is used as the input of the Support Vector Machine (SVM) classifier for bearing fault diagnosis. The proposed method is validated by data sets from the time-varying bearing data from the University of Ottawa and Case Western Reserve University Bearing Data Center. The results show that the algorithm can effectively diagnose the bearing under the steady-state and unsteady state. This paper proposes that the algorithm has better fault diagnosis capabilities and feature extraction capabilities when compared with methods that aree based on traditional feature technology.

Research on Structure Data Link Detection Method Based on Internet of Things System

In order to improve the fault diagnosis and analysis capabilities of the cyber-physical system in the Internet of Things, it is necessary to detect and identify the vicious data chain of the cyber-physical system in the Internet of Things. Moreover, to realize the detection and identification of the vicious data link in the cyber-physical system in the Internet of Things, a fast extraction algorithm for the vicious data link of the cyber-physical system in the Internet of Things is proposed in the paper to collect vicious data from the cyber-physical system in the Internet of Things. In addition, the malignant data generated during the factor adjustment of the Internet of Things can be divided into periodic structure and non-periodic structure in structure, and the malignant data sensor network model of the cyber-physical system in the Internet of Things is constructed. Therefore, through simulation experiment analysis, the method proposed in the paper has superior performance in the detection and identification of vicious data links in the cyber-physical system of the Internet of Things.

Multifunctional Liquid Crystal Nanoparticles for Cancer Therapy

Cancer is the second foremost reason for worldwide death, affecting every country of the globe. However, 70% of cancer-related death was reported from low- and middle-income nations. Delay in the detection and intervention of therapeutic agents in cancer patients also promoted a cancer-related mortality index. Currently, numerous nanomedicines are under development for advancing tumor diagnosis and therapeutic capability. Recently, liquid crystalline nanoparticles (LCNPs) have emerged as an attractive drug delivery system for both intravenous and non-intravenous applications. The widely explored LCNPs for cancer therapy include cubosomes and hexosomes. They have significant advantages over other drug delivery system, which includes, high internal surface area, unique solubilization properties and sustained release of entrapped drug molecules and co-loading of imaging and therapeutic agents in a single system. In this review, we have briefly discussed the advantages of LCNPs, preparation methods, and their multifunctional role in treating various cancers.

An Examination of Prospective Uses and Future Directions of Neuralink: The Brain-Machine Interface.

The human brain is one of the most mystifying biological structures in nature. Overwhelming research, technology, and innovations in neuroscience have augmented clinical assessments, diagnosis, and treatment capabilities. Nonetheless, there is still much to be discovered about nervous system disorders and defects. Neuralink, a neurotechnology company, is advancing the field of neuroscience and neuroengineering. The company’s initial aim is to develop an implantable brain-machine interface device that will enhance the lives of people with severe brain and spinal cord injuries. Here, we provide insight into Neuralink’s design, early testing, and future applications in neurosurgery. While early testing with small and large animals show promising results, no clinical trials have been conducted to date. Additionally, a term search for “Neuralink” was performed in PubMed. The literature search yielded only 28 references, of which most indirectly mentioned the device but not in direct testing. In order to conclude the safety and viability of the Neuralink device, further research studies are needed to move forward beyond speculation.

Differential X-ray diagnosis of pseudotuberculous scenario of pulmonary abscess with tuberculous cavities

Background. Recent decades in Ukraine have been characterized by a significant increase in the number of tuberculosis patients, often with forming cavities of destruction. X-ray diagnosis of lung cavitary lesions is one of the current issues of modern pulmonology and thoracic surgery. Pulmonary abscesses resemble other diseases with destruction and cavities substantiating the need for differential diagnosis with tuberculosis. 
 Purpose – specifying particular scenarios of X-ray presentation of lung abscess and determining the capability of differential diagnosis of pseudotuberculosis with cavities of tuberculosis etiology.
 Materials and methods. The paper deals with the analysis of X-ray examination of thoracic viscera provided for 252 patients with lung abscess, aged 18 and up to 78. X-ray radiography in two projections, linear and computed tomography (56 patients involved) were performed. All patients underwent a study over time.
 Results. Almost in most lung abscess cases, there is a need for differential diagnosis with a range of medical entities. The obtained data have made it possible to suggest a classification of X-ray scenarios of lung abscess. The scenarios of X-ray presentation of acute pulmonary abscess are typical and atypical, among those: cystoid, pseudotuberculous, affected 38 patients (15 %), and pulmonary-pleural. The peculiarities of X-ray presentation of pseudotuberculous scenario along with the differences and signs allowing to make an accurate diagnosis have been specified.
 Conclusions. X-ray study remains an essential in diagnosing purulent-destructive diseases. Being familiar with the scenarios mentioned above and pseudotuberculous one, in particular, will make it possible to significantly improve diagnosis as well as differential diagnosis of pulmonary abscess.

Artificial intelligence in OCT angiography.

Optical coherence tomographic angiography (OCTA) is a non-invasive imaging modality that provides three-dimensional, information-rich vascular images. With numerous studies demonstrating unique capabilities in biomarker quantification, diagnosis, and monitoring, OCTA technology has seen rapid adoption in research and clinical settings. The value of OCTA imaging is significantly enhanced by image analysis tools that provide rapid and accurate quantification of vascular features and pathology. Today, the most powerful image analysis methods are based on artificial intelligence (AI). While AI encompasses a large variety of techniques, machine-learning-based, and especially deep-learning-based, image analysis provides accurate measurements in a variety of contexts, including different diseases and regions of the eye. Here, we discuss the principles of both OCTA and AI that make their combination capable of answering new questions. We also review contemporary applications of AI in OCTA, which include accurate detection of pathologies such as choroidal neovascularization, precise quantification of retinal perfusion, and reliable disease diagnosis.

Microprocessor Error Diagnosis by Trace Monitoring Under Laser Testing

This work explores the diagnosis capabilities of the enriched information provided by microprocessors trace subsystem combined with laser fault injection. Laser fault injection campaigns with delimited architectural regions have been accomplished on an ARM Cortex-A9 device. Experimental results demonstrate the capability of the presented technique to provide additional information of the various error mechanisms that can happen in a microprocessor. A comparison with radiation campaigns presented in previous work is also discussed, showing that laser fault injection results are in good agreement with neutron and proton radiation results.

Panel-to-Substring Differential Power Processing Converter With Embedded Electrical Diagnosis Capability for Photovoltaic Panels Under Partial Shading

Various kinds of differential power processing (DPP) converters have been developed to improve the energy yield of partially-shaded photovoltaic (PV) panels by precluding partial shading issues, such as the reduction in power generation and the occurrence of multiple maximum power points. Meanwhile, PV systems require fault diagnosis tools to detect premature deterioration and malfunctions that lead to a reduction in power generation of the system as a whole and, in the worst case, hazardous situations, such as a fire. This article proposes a novel DPP converter as well as an electrical diagnosis technique using the DPP converter. The proposed DPP converter not only addresses the partial shading issues but also provides the electrical diagnosis capability. In the diagnosis mode, the DPP converter injects ac currents to a panel, and an ac impedance of the panel can be calculated from the voltage response to the injected ac currents. The detailed operation analysis and experimental verification tests using a prototype were performed. The results demonstrated the improved power yield from partially shaded PV panels and the electrical diagnosis capability of the proposed DPP converter.

Heterogeneous graph reasoning for knowledge-grounded medical dialogue system

Beyond the common difficulties faced in task-oriented dialogue system, medical dialogue has recently attracted increasing attention due to its huge application potential while posing more challenges in reasoning over medical domain knowledge and logic. Existing works resort to neural language models for dialogue embedding and neglect the explicit logical reasoning, leading to poor explainable and generalization ability. In this work, we propose an explainable Heterogeneous Graph Reasoning (HGR) model to unify the relational dialogue context understanding and entity-correlation reasoning into a heterogeneous graph structure. HGR encodes entity context according to the corresponding utterance and deduces next response after fusing the underlying medical knowledge with entity context by attentional graph propagation. To push forward the future research on expert-sensitive task-oriented dialogue system, we first release a large-scale Medical Dialogue Consultant benchmark (MDG-C) with 16 Gastrointestinal diseases for evaluating consultant capability and a Medical Dialogue Diagnosis benchmark (MDG-D) with 6 diseases for measuring diagnosis capability of models, respectively. Extensive experiments on both MDG-C and MDG-D benchmarks demonstrate the superiority of our HGR over state-of-the-art knowledge grounded approaches in general fields of medical dialogue system.

A Combined Approach for Model-Based PV Power Plant Failure Detection and Diagnostic

Photovoltaic (PV) technology allows large-scale investments in a renewable power-generating system at a competitive levelized cost of electricity (LCOE) and with a low environmental impact. Large-scale PV installations operate in a highly competitive market environment where even small performance losses have a high impact on profit margins. Therefore, operation at maximum performance is the key for long-term profitability. This can be achieved by advanced performance monitoring and instant or gradual failure detection methodologies. We present in this paper a combined approach on model-based fault detection by means of physical and statistical models and failure diagnosis based on physics of failure. Both approaches contribute to optimized PV plant operation and maintenance based on typically available supervisory control and data acquisition (SCADA) data. The failure detection and diagnosis capabilities were demonstrated in a case study based on six years of SCADA data from a PV plant in Slovenia. In this case study, underperforming values of the inverters of the PV plant were reliably detected and possible root causes were identified. Our work has led us to conclude that the combined approach can contribute to an efficient and long-term operation of photovoltaic power plants with a maximum energy yield and can be applied to the monitoring of photovoltaic plants.

Aptamer Conjugated Gold Nanostar-Based Distance-Dependent Nanoparticle Surface Energy Transfer Spectroscopy for Ultrasensitive Detection and Inactivation of Corona Virus.

The ongoing outbreak of the coronavirus infection has killed more than 2 million people. Herein, we demonstrate that Rhodamine 6G (Rh-6G) dye conjugated DNA aptamer-attached gold nanostar (GNS)-based distance-dependent nanoparticle surface energy transfer (NSET) spectroscopy has the capability of rapid diagnosis of specific SARS-CoV-2 spike recombinant antigen or SARS-CoV-2 spike protein pseudotyped baculovirus within 10 min. Because Rh-6G-attached single-stand DNA aptamer wrapped the GNS, 99% dye fluorescence was quenched because of the NSET process. In the presence of spike antigen or virus, the fluorescence signal persists because of the aptamer–spike protein binding. Specifically, the limit of detection for the NSET assay has been determined to be 130 fg/mL for antigen and 8 particles/mL for virus. Finally, we have demonstrated that DNA aptamer-attached GNSs can stop virus infection by blocking the angiotensin-converting enzyme 2 (ACE2) receptor binding capability and destroying the lipid membrane of the virus.

A Multi-Input and Multi-Task Convolutional Neural Network for Fault Diagnosis Based on Bearing Vibration Signal

Bearing fault diagnosis is essential for the safe and stable operation of rotating machinery. Existing methods use signals from a single dimension, limiting diagnostic generality and accuracy. To address these limitations and make improved use of signal features from multiple dimensions, a novel convolutional neural network model with multi-dimensional signal inputs and multi-dimensional task outputs called MIMTNet is proposed. First, frequency domain signals and a time frequency graph are obtained by using the short-time Fourier transform and a wavelet transform to process original time domain signals simultaneously. Then, the time domain signals, the frequency domain signals, and the time frequency graph are fed into the model and a special aggregation is performed after extracting features from the three corresponding branches. Finally, the outputs of the three-dimensional tasks are acquired by different full connection layers to process the aggregated features of bearing position, damage location within the bearing, and the damage size. Two common bearing vibration signal datasets are used to verify the generalization ability of our proposed method. And experimental results show that the proposed method effectively improves the bearing diagnosis capability of the deep learning model.

Multi-annual performance evaluation of laboratories in post-mortem diagnosis of animal rabies: Which techniques lead to the most reliable results in practice?

Rabies diagnosis proficiency tests on animal specimens using four techniques (FAT, RTCIT, conventional RT-PCR and real-time RT-PCR) were organised over 10 years (2009–2019). Seventy-three laboratories, of which 59% were from Europe, took part. As the panels were prepared with experimentally-infected samples, the error rate of laboratories on positive and negative samples was accurately estimated. Based on fitted values produced by mixed modelling including the variable “laboratory” as a random variable to take into account the longitudinal design of our dataset, the technique that provided the most concordant results was conventional RT-PCR (99.3%; 95% CI 99.0–99.6), closely followed by FAT (99.1%; 95% CI 98.7–99.4), real-time RT-PCR (98.7%; 95% CI 98.1–99.3) and then RTCIT (96.8%; 95% CI 95.8–97.7). We also found that conventional RT-PCR provided a better diagnostic sensitivity level (99.3% ±4.4%) than FAT (98.7% ±1.6%), real-time RT-PCR (97.9% ±0.8%) and RTCIT (95.3% ±5.1%). Regarding diagnostic specificity, RTCIT was the most specific technique (96.4% ±3.9%) followed closely by FAT (95.6% ±3.8%), real-time RT-PCR (95.0% ±1.8%) and conventional RT-PCR (92.9% ±0.5%). Due to multiple testing of the samples with different techniques, the overall diagnostic conclusion was also evaluated, and found to reach an inter-laboratory concordance level of 99.3%. The concordance for diagnostic sensitivity was 99.6% ±2.0% and for diagnostic specificity, 98.0% ±8.5%. Molecular biology techniques were, however, found to be less specific than expected. The potential reasons for such findings are discussed herein. The regular organisation of performance tests has contributed to an increase in the performance of participating laboratories over time, demonstrating the benefits of such testing. Maintaining a high-quality rabies diagnosis capability on a global scale is key to achieving the goal of eliminating dog-mediated human rabies deaths. The regular organisation of exercises on each continent using selected local strains to be tested according to the local epidemiological situation is one factor that could help increase reliable diagnosis worldwide. Rabies diagnosis capabilities could indeed be enhanced by providing adequate and sustainable proficiency testing on a large scale and in the long term

Cloud Computing-Based Framework for Breast Cancer Diagnosis Using Extreme Learning Machine.

Globally, breast cancer is one of the most significant causes of death among women. Early detection accompanied by prompt treatment can reduce the risk of death due to breast cancer. Currently, machine learning in cloud computing plays a pivotal role in disease diagnosis, but predominantly among the people living in remote areas where medical facilities are scarce. Diagnosis systems based on machine learning act as secondary readers and assist radiologists in the proper diagnosis of diseases, whereas cloud-based systems can support telehealth services and remote diagnostics. Techniques based on artificial neural networks (ANN) have attracted many researchers to explore their capability for disease diagnosis. Extreme learning machine (ELM) is one of the variants of ANN that has a huge potential for solving various classification problems. The framework proposed in this paper amalgamates three research domains: Firstly, ELM is applied for the diagnosis of breast cancer. Secondly, to eliminate insignificant features, the gain ratio feature selection method is employed. Lastly, a cloud computing-based system for remote diagnosis of breast cancer using ELM is proposed. The performance of the cloud-based ELM is compared with some state-of-the-art technologies for disease diagnosis. The results achieved on the Wisconsin Diagnostic Breast Cancer (WBCD) dataset indicate that the cloud-based ELM technique outperforms other results. The best performance results of ELM were found for both the standalone and cloud environments, which were compared. The important findings of the experimental results indicate that the accuracy achieved is 0.9868, the recall is 0.9130, the precision is 0.9054, and the F1-score is 0.8129.

Contrast-Enhanced Ultrasound of the Pleural Cavity: A Method to Locate Pleural Catheters and Identify Fibrous Septa

We aimed to explore the value of contrast-enhanced ultrasound (CEUS) of the pleural cavity in locating catheters and identifying fibrous septa and to compare CEUS with multiple existing methods. We included 304 participants whose pleural effusion could not continue to be drained and compared the catheter-localization capabilities of empirical diagnosis, B-mode ultrasound with normal saline and CEUS, with computed tomography as the reference standard. CEUS performed the best (accuracy, 100%; sensitivity, 100%; specificity, 100%), followed by B-mode ultrasound with normal saline (accuracy, 77.78%; sensitivity, 62.5%; specificity, 100%), and finally empirical diagnosis (accuracy, 54.17%; sensitivity, 66.67%; specificity, 33.33%). The capabilities of CEUS and computed tomography to identify fibrous septa were evaluated, with B-mode ultrasound as the reference, and CEUS (accuracy, 100%; sensitivity, 100%; specificity, 100%) was superior to computed tomography (accuracy, 82.41%; sensitivity, 26.09%; specificity, 97.65%). Overall, CEUS can accurately locate catheters and identify fibrous septa, with performance superior to existing methods.

Strain-resilient electrical functionality in thin-film metal electrodes using two-dimensional interlayers.

Flexible electrodes that allow electrical conductance to be maintained during mechanical deformation are required for the development of wearable electronics. However, flexible electrodes based on metal thin-films on elastomeric substrates can suffer from complete and unexpected electrical disconnection after the onset of mechanical fracture across the metal. Here we show that the strain-resilient electrical performance of thin-film metal electrodes under multimodal deformation can be enhanced by using a two-dimensional (2D) interlayer. Insertion of atomically-thin interlayers — graphene, molybdenum disulfide, or hexagonal boron nitride — induce continuous in-plane crack deflection in thin-film metal electrodes. This leads to unique electrical characteristics (termed electrical ductility) in which electrical resistance gradually increases with strain, creating extended regions of stable resistance. Our 2D-interlayer electrodes can maintain a low electrical resistance beyond a strain in which conventional metal electrodes would completely disconnect. We use the approach to create a flexible electroluminescent light emitting device with an augmented strain-resilient electrical functionality and an early-damage diagnosis capability.

Wastewater COD characterization: RBCOD and SBCOD characterization analysis methods

Wastewater characterization is the basis for process design and operation optimization of wastewater treatment plants (WWTPs). In this work, a comprehensive study of the respirometry method has been performed to evaluate the biodegradable organic matters of wastewater. First, the optimal initial substrate to biomass ratio (S0/X0) was confirmed. Second, under the optimal S0/X0, the degradation curves of wastewater carbon oxygen demand (COD) components rapidly biodegradable COD (RBCOD) and slowly biodegradable COD (SBCOD) were obtained. Third, the Mann–Kendall test was performed to confirm the time point (t2) when endogenous respiration levels were reached, and the hydrolysis model was used to determine the time point (t1) of the SBCOD degradation stage. Considering the results, an adequate wastewater COD characterization method for RBCOD and SBCOD has been proposed. This study provides strong support to carry out effective and feasible process design, process diagnosis and optimization capability, can help achieve refined and stable operational management of WWTPs.