A Diagnostic Tool for Identification of Etiologies of Fever of Unknown Origin in Adult Patients

Neutrophil-to-ferritin ratio can predict hematological causes of fever of unknown origin

Despite advancements in diagnostic modalities, delineating the etiology of fever of unknown origin (FUO) remains a significant challenge for clinicians. Notably, cases with hematological malignancies often have a poor prognosis due to delayed diagnosis. This study investigated the potential of readily obtainable laboratory markers to differentiate hematological causes from other etiologies during the early stages of FUO. A retrospective analysis was conducted on the medical records of 100 patients who fulfilled the modified FUO criteria between January 2010 and April 2023. Hematological etiologies were identified in 26 of the 100 patients. Peripheral blood neutrophil, lymphocyte, platelet counts, and the systemic immune inflammation (SII) index, were significantly lower in the hematological group compared to the non-hematological group. Conversely, serum ferritin levels were demonstrably higher in the hematological group. ROC analysis identified a neutrophil-to-ferritin ratio (NFR) cutoff value of < 8.53 as optimal for predicting hematological etiology. Subsequent multivariate analysis demonstrated that the NFR was the sole independent predictor of hematological etiology (p = 0.013).This study proposes a novel approach for early diagnosis of a potentially life-threatening subset of FUO patients. The NFR presents as an inexpensive and readily available marker for predicting hematological etiology in FUO cases.

Integrating Medical Domain Knowledge for Early Diagnosis of Fever of Unknown Origin: An Interpretable Hierarchical Multimodal Neural Network Approach

Accurate and interpretable differential diagnostic technologies are crucial for supporting clinicians in decision-making and treatment-planning for patients with fever of unknown origin (FUO). Existing solutions commonly address the diagnosis of FUO by transforming it into a multi-classification task. However, after the emergence of COVID-19 pandemic, clinicians have recognized the heightened significance of early diagnosis in patients with FUO, particularly for practical needs such as early triage. This has resulted in increased demands for identifying a wider range of etiologies, shorter observation windows, and better model interpretability. In this article, we propose an interpretable hierarchical multimodal neural network framework (iHMNNF) to facilitate early diagnosis of FUO by incorporating medical domain knowledge and leveraging multimodal clinical data. The iHMNNF comprises a top-down hierarchical reasoning framework (Td-HRF) built on the class hierarchy of FUO etiologies, five local attention-based multimodal neural networks (La-MNNs) trained for each parent node of the class hierarchy, and an interpretable module based on layer-wise relevance propagation (LRP) and attention mechanism. Experimental datasets were collected from electronic health records (EHRs) at a large-scale tertiary grade-A hospital in China, comprising 34,051 hospital admissions of 30,794 FUO patients from January 2011 to October 2020. Our proposed La-MNNs achieved area under the receiver operating characteristic curve (AUROC) values ranging from 0.7809 to 0.9035 across all five decomposed tasks, surpassing competing machine learning (ML) and single-modality deep learning (DL) methods while also providing enhanced interpretability. Furthermore, we explored the feasibility of identifying FUO etiologies using only the first N-hour time series data obtained after admission.

Differential diagnosis of lymphoma with 18F-FDG PET/CT in patients with fever of unknown origin accompanied by lymphadenopathy

PURPOSE

To investigate the value of 18F-fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the differential diagnosis of lymphoma in patients with fever of unknown origin (FUO) accompanied by lymphadenopathy and to develop a simple scoring system to distinguish lymphoma from other etiologies.

METHODS

A prospective study was conducted on patients with classic FUO accompanied by lymphadenopathy. After standard diagnostic procedures, including PET/CT scan and lymph-node biopsy, 163 patients were enrolled and divided into lymphoma and benign groups according to the etiology. The diagnostic utility of PET/CT imaging was evaluated, and beneficial parameters that could improve diagnostic effectiveness were identified.

RESULTS

The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of PET/CT in diagnosing lymphoma in patients with FUO accompanied by lymphadenopathy were 81.0, 47.6, 59.3, and 72.7%, respectively. The lymphoma prediction model combining high SUVmax of the "hottest" lesion, high SUVmax of the retroperitoneal lymph nodes, old age, low platelet count, and low ESR had an area under the curve of 0.93 (0.89-0.97), a sensitivity of 84.8%, a specificity of 92.9%, a PPV of 91.8%, and an NPV of 86.7%. There was a lower probability of lymphoma for patients with a score < 4 points.

CONCLUSIONS

PET/CT scans show moderate sensitivity and low specificity in diagnosing lymphoma in patients with FUO accompanied by lymphadenopathy. The scoring system based on PET/CT and clinical parameters performs well in differentiating lymphoma and benign causes and can be used as a reliable noninvasive tool.

REGISTRATION NUMBER

This study on FUO was registered on http://www.

CLINICALTRIALS

gov on January 14, 2014, with registration number NCT02035670.

Diagnostic models for fever of unknown origin based on 18F-FDG PET/CT: a prospective study in China

Background

This study aims to analyze the 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) characteristics of different causes of fever of unknown origin (FUO) and identify independent predictors to develop a suitable diagnostic model for distinguishing between these causes. A total of 524 patients with classical FUO who underwent standard diagnostic procedures and PET/CT were prospectively studied. The diagnostic performance of PET/CT imaging was analyzed, and relevant clinical parameters that could improve diagnostic efficacy were identified. The model was established using the data of 369 patients and the other 155 patients comprised the validation cohort for verifying the diagnostic performance of the model.

Results

The metabolic characteristics of the “hottest” lesion, the spleen, bone marrow, and lymph nodes varied for various causes. PET/CT combined with clinical parameters achieved better discrimination in the differential diagnosis of FUO. The etiological diagnostic models included the following factors: multisite metabolic characteristics, blood cell counts, inflammatory indicators (erythrocyte sedimentation rate, C-reactive protein, serum ferritin, and lactate dehydrogenase), immunological indicators (interferon gamma release assay, antinuclear antibody, and anti-neutrophil cytoplasm antibody), specific signs (weight loss, rash, and splenomegaly), and age. In the testing cohort, the AUCs of the infection prediction model, the malignancy diagnostic model, and the noninfectious inflammatory disease prediction model were 0.89 (95% CI 0.86–0.92), 0.94 (95% CI 0.92–0.97), and 0.95 (95% CI 0.93–0.97), respectively. The corresponding AUCs for the validation cohort were 0.88 (95% CI 0.82–0.93), 0.93 (95% CI 0.89–0.98), and 0.95 (95% CI 0.92–0.99), respectively.

Conclusions

18F-FDG PET/CT has a certain level of sensitivity and accuracy in diagnosing FUO, which can be further improved by combining it with clinical parameters. Diagnostic models based on PET/CT show excellent performance and can be used as reliable tools to discriminate the cause of FUO.

Trial registration This study (a two-step method apparently improved the physicians’ level of diagnosis decision-making for adult patients with FUO) was registered on the website http://www.clinical-trials.gov on January 14, 2014, with registration number NCT02035670.

Rheumatic disorders among patients with fever of unknown origin: A systematic review and meta-analysis

OBJECTIVES

To conduct a systematic literature review and meta-analysis to estimate the proportion of fever of unknown origin (FUO) and inflammation of unknown origin (IUO) cases that are due to rheumatic disorders and the relative frequency of specific entities associated with FUO/IUO.

METHODS

We searched PubMed and EMBASE between January 1, 2002, and December 31, 2021, for studies with ≥50 patients reporting on causes of FUO/IUO. The primary outcome was the proportion of FUO/IUO patients with rheumatic disease. Secondary outcomes include the association between study and patient characteristics and the proportion of rheumatic disease in addition to the relative frequency of rheumatic disorders within this group. Proportion estimates were calculated using random-effects models.

RESULTS

The included studies represented 16884 patients with FUO/IUO. Rheumatic disease explained 22.2% (95%CI 19.6 - 25.0%) of cases. Adult-onset Still's disease (22.8% [95%CI 18.4-27.9%]), giant cell arteritis (11.4% [95%CI 8.0-16.3%]), and systemic lupus erythematosus (11.1% [95%CI 9.0-13.8%]) were the most frequent disorders. The proportion of rheumatic disorders was significantly higher in high-income countries (25.9% [95%CI 21.5 - 30.8%]) versus middle-income countries (19.5% [95%CI 16.7 - 22.7%]) and in prospective studies (27.0% [95%CI 21.9-32.8%]) versus retrospective studies (20.6% [95%CI 18.1-24.0%]). Multivariable meta-regression analysis demonstrated that rheumatic disease was associated with the fever duration (0.011 [95%CI 0.003-0.021]; P=0.01) and with the fraction of patients with IUO (1.05 [95%CI 0.41-1.68]; P=0.002).

CONCLUSION

Rheumatic disorders are a common cause of FUO/IUO. The care of patients with FUO/IUO should involve physicians who are familiar with the diagnostic workup of rheumatic disease.

Application of Machine Learning for the Prediction of Etiological Types of Classic Fever of Unknown Origin

Background: The etiology of fever of unknown origin (FUO) is complex and remains a major challenge for clinicians. This study aims to investigate the distribution of the etiology of classic FUO and the differences in clinical indicators in patients with different etiologies of classic FUO and to establish a machine learning (ML) model based on clinical data. Methods: The clinical data and final diagnosis results of 527 patients with classic FUO admitted to 7 medical institutions in Chongqing from January 2012 to August 2021 and who met the classic FUO diagnostic criteria were collected. Three hundred seventy-three patients with final diagnosis were divided into 4 groups according to 4 different etiological types of classical FUO, and statistical analysis was carried out to screen out the indicators with statistical differences under different etiological types. On the basis of these indicators, five kinds of ML models, i.e., random forest (RF), support vector machine (SVM), Light Gradient Boosting Machine (LightGBM), artificial neural network (ANN), and naive Bayes (NB) models, were used to evaluate all datasets using 5-fold cross-validation, and the performance of the models were evaluated using micro-F1 scores. Results: The 373 patients were divided into the infectious disease group (n = 277), non-infectious inflammatory disease group (n = 51), neoplastic disease group (n = 31), and other diseases group (n = 14) according to 4 different etiological types. Another 154 patients were classified as undetermined group because the cause of fever was still unclear at discharge. There were significant differences in gender, age, and 18 other indicators among the four groups of patients with classic FUO with different etiological types (P < 0.05). The micro-F1 score for LightGBM was 75.8%, which was higher than that for the other four ML models, and the LightGBM prediction model had the best performance. Conclusions: Infectious diseases are still the main etiological type of classic FUO. Based on 18 statistically significant clinical indicators such as gender and age, we constructed and evaluated five ML models. LightGBM model has a good effect on predicting the etiological type of classic FUO, which will play a good auxiliary decision-making function.

An Experimental and Theoretical Approach to Understand Fever, DENF & its Cure

Fever is a response of a human body, due to an increase in the temperature, against certain stimuli. It may be associated with several reasons and one of the major causes of fever is a mosquito bite. Fever due to dengue virus (DENV) infection is being paid most attention out of several other fever types because of a large number of deaths reported worldwide. Dengue virus is transmitted by biting of the mosquitoes, Aedes aegypti and Aedes albopictus. DENV1, DENV2, DENV3 and DENV4 are the four serotypes of dengue virus and these serotypes have 65% similarities in their genomic structure. The genome of DENV is composed of single-stranded RNA and it encodes for the polyprotein. Structural and non-structural proteins (nsP) are the two major parts of polyprotein. Researchers have paid high attention to the non-structural protease (nsP) of DENV like nsP1, nsP2A, nsP2B, nsP3, nsP4A, nsP4B and nsP5. The NS2B-NS3 protease of DENV is the prime target of the researchers as it is responsible for the catalytic activity. In the present time, Dengvaxia (vaccine) is being recommended to patients suffering severely from DENV infection in few countries only. Till date, neither a vaccine nor an effective medicine is available to combat all four serotypes. This review describes the fever, its causes, and studies to cure the infection due to DENV using theoretical and experimental approaches.

Combined clinical parameters improve the diagnostic efficacy of 18F-FDG PET/CT in patients with fever of unknown origin (FUO) and inflammation of unknown origin (IUO): A prospective study in China

OBJECTIVES

To improve the diagnostic efficacy of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) for Chinese patients with fever of unknown origin (FUO) and inflammation of unknown origin (IUO), with combined clinical parameters.

MATERIALS AND METHODS

FUO/IUO patients who underwent a standard diagnostic work-up and ¹⁸F-FDG PET/CT scanning were enrolled and divided into a local uptake lesion subgroup and a non-specific abnormal uptake subgroup. Beneficial clinical parameters for improving the diagnostic efficacy of PET/CT were identified.

RESULTS

From January 2014 to January 2019, 253 FUO/IUO patients were studied. In total, 147 patients had local uptake lesions and 106 patients had non-specific abnormal uptake. In the local uptake lesion group, the positioning accuracy of PET/CT was 37.2% in grades 1 and 2, and 66.3% in grades 3 and 4. With the following combination of clinical parameters, the positioning accuracy increased to 75.0% and 90.0%, respectively: time from admission to performing PET/CT scanning <6.5 days and C-reactive protein level >95 mg/l. In the non-specific abnormal uptake group, the combination of sex (male), bicytopenia, and lactic dehydrogenase improved the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for diagnosing malignancy from 64.3%, 69%, 60%, and 72.7%, respectively, to 83.3%, 81%, 81.4%, and 82.9%, respectively. With the combination of sex (male), white blood count, serum ferritin level, and hepatosplenomegaly, the infection prediction model had a sensitivity, specificity, PPV, and NPV of 78%, 76.2%, 76.6%, and 77.6%, respectively.

CONCLUSIONS

Combined clinical parameters improved the localization diagnostic value of ¹⁸F-FDG PET/CT in the local uptake lesion subgroup and the etiological diagnostic value in the non-specific abnormal uptake subgroup.