Optimal cisplatin cycles in locally advanced cervical carcinoma patients treated with concurrent chemoradiotherapy

Purpose To analyze the effect of cisplatin cycles on the clinical outcomes of patients with locally advanced cervical cancer (LACC) treated with concurrent chemoradiotherapy (CCRT). Methods This study included 749 patients with LACC treated with CCRT between January 2011 and December 2015. A receiver operating characteristic (ROC) curve was used to analyze the optimal cut-off of cisplatin cycles in predicting clinical outcomes. Clinicopathological features of the patients were compared using the Chi-square test. Prognosis was assessed using log-rank tests and Cox proportional hazard models. Toxicities were compared among different cisplatin cycle groups. Results Based on the ROC curve, the optimal cut-off of the cisplatin cycles was 4.5 (sensitivity, 64.3%; specificity, 54.3%). The 3-year overall, disease-free, loco-regional relapse-free, and distant metastasis-free survival for patients with low-cycles (cisplatin cycles < 5) and high-cycles (≥ 5) were 81.5% and 89.0% (P < 0.001), 73.4% and 80.1% (P = 0.024), 83.0% and 90.8% (P = 0.005), and 84.9% and 86.8% (P = 0.271), respectively. In multivariate analysis, cisplatin cycles were an independent prognostic factor for overall survival. In the subgroup analysis of high-cycle patients, patients who received over five cisplatin cycles had similar overall, disease-free, loco-regional relapse-free, and distant metastasis-free survival to patients treated with five cycles. Acute and late toxicities were not different between the two groups. Conclusion Cisplatin cycles were associated with overall, disease-free, and loco-regional relapse-free survival in LACC patients who received CCRT. Five cycles appeared to be the optimal number of cisplatin cycles during CCRT (AU)

Improving the diagnosis of myelodysplastic syndrome by red blood cell parameters

Purpose To investigate the value of red blood cell parameters in Myelodysplastic syndrome (MDS) diagnosis and their relations to MDS subtypes and risk groups. Methods The red blood cell parameter [mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC) and red cell distribution width (RDW)] levels [203 MDS, 99 aplastic anemia (AA), 145 megaloblastic anemia (MA)] were collected from a single-center retrospective cohort. The cut-off values, area under the receiver operating characteristic curve (ROC) curve (AUC), sensitivity and specificity of the four parameters were calculated from the ROC. Furthermore, Kruskal–Wallis test and Dunn’s Test were performed to determine erythrocyte parameters in different subtypes and prognostic risks MDS. Results There are significant statistic differences in RDW (P < 0.001), MCH (P = 0.036) and MCHC (P < 0.001) (MDS vs AA); RDW (P = 0.009), MCV (P < 0.001), MCH (P < 0.001) and MCHC (P = 0.001) (MDS vs MA); MCV (P = 0.011) and MCH (P = 0.008) (higher-risk MDS vs lower-risk MDS). Between MDS and MA, the area under the receiver operating characteristic curve (ROC) curve (AUC) values of MCV, MCH, MCHC, RDW were 0.846, 0.855, 0.617, and 0.593. Between MDS and AA, the AUC values of MCH, MCHC, RDW were 0.609, 0.671, and 0.662, respectively. Conclusions The red blood cell parameters contribute to the differential diagnosis of MDS, AA and MA and are related to MDS subtypes and risk groups (AU)

Diminished prefrontal hemodynamic response in adult attention deficit hyperactivity disorder: a multi-channel functional near-infrared spectroscopy study

Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder. Adult ADHD is currently diagnosed based only on subjective clinical and scoring measures, which inevitably lead to a low correct diagnosis rate. Hence, an effective auxiliary examination with higher sensitivity is needed. Method Twenty healthy controls (HC) subjects and 20 adults with ADHD were included in this study. The functional near-infrared spectroscopy (fNIRS) under verbal fluency test (VFT) was performed to detect cerebral cortex hemodynamics. Correlation and Receiver operating characteristic (ROC) curve analysis were employed to reveal the relationship between differences in hemodynamic response and clinical characteristics. Results The HbO response of adult ADHD in the prefrontal cortex (PFC) was significantly smaller than that of HC. HbO concentration changes in the corresponding channels were negatively correlated with the ASRS-inattention score. HbO concentration changes of channels 16 and 26 corresponding to the medial PFC might be helpful for the diagnosis of adult ADHD. Conclusion Adult ADHD patients have low activation of the PFC, changes of whose corresponding channels were significantly associated with attention deficit, indicating that fNIRS under VFT may be an effective auxiliary examination for adult ADHD. (AU)

Nutritional indicators' performance in malnutrition diagnosis of hospitalized elderly patients.

BACKGROUND: Several nutritional diagnosis methods and their relationship with clinical outcomes have been described. This study investigated malnutrition in hospitalized elderly patients (HEP) using different nutritional indicators and determined criteria to identify malnutrition and explore the variables that discriminate the risk of malnutrition. METHOD: Cross-sectional study with 500 HEP; different methods of nutritional diagnosis, their relationship with clinical outcomes and criteria for defining malnutrition were investigated. The GLIM criteria for the diagnosis of malnutrition was applied in this study. In the statistical analysis, the Chi-square test, Fisher's exact test, Mann-Whitney test, univariate and multiple logistic regression and the ROC curve were used. RESULTS: Patients aged 65-79 years, at nutritional risk or with malnutrition, had longer hospital stays (p = 0.0099; OR = 1.047; 95% CI = 1.011; 1.084) and lower body mass index (BMI) (p < 0.0001; OR = 0.867 (1153)); 95% CI = 0.813; 0.924 (1085; 1225). Patients aged ≥80 years had a lower BMI (p = 0.0053; OR = 0.779 (1284); 95% CI = 0.653; 0.928 (1078; 1531)). Accuracy was significant in both age groups for BMI (p < 0.0001; 65-79 years and p = 0.001; ≥80 years); for the lymphocyte count (p = 0.0167; 65-79 years and p = 0.0028; ≥80 years), and for the calf circumference (CC) (p < 0.0001; 65-79 years and p = 0.001; ≥80 years). Using the GLIM criteria, 27.78% of patients were considered malnourished. CC showed good accuracy, good specificity, but low sensitivity while BMI was more accurate to detect malnutrition in both age groups. CONCLUSION: CC showed good accuracy, good specificity, but low sensitivity to detect malnutrition. BMI was more accurate in both age groups to detect malnutrition.

Application of machine learning approaches in predicting clinical outcomes in older adults - a systematic review and meta-analysis.

BACKGROUND: Machine learning-based prediction models have the potential to have a considerable positive impact on geriatric care. DESIGN: Systematic review and meta-analyses. PARTICIPANTS: Older adults (≥ 65 years) in any setting. INTERVENTION: Machine learning models for predicting clinical outcomes in older adults were evaluated. A random-effects meta-analysis was conducted in two grouped cohorts, where the predictive models were compared based on their performance in predicting mortality i) under and including 6 months ii) over 6 months. OUTCOME MEASURES: Studies were grouped into two groups by the clinical outcome, and the models were compared based on the area under the receiver operating characteristic curve metric. RESULTS: Thirty-seven studies that satisfied the systematic review criteria were appraised, and eight studies predicting a mortality outcome were included in the meta-analyses. We could only pool studies by mortality as there were inconsistent definitions and sparse data to pool studies for other clinical outcomes. The area under the receiver operating characteristic curve from the meta-analysis yielded a summary estimate of 0.80 (95% CI: 0.76 - 0.84) for mortality within 6 months and 0.81 (95% CI: 0.76 - 0.86) for mortality over 6 months, signifying good discriminatory power. CONCLUSION: The meta-analysis indicates that machine learning models display good discriminatory power in predicting mortality. However, more large-scale validation studies are necessary. As electronic healthcare databases grow larger and more comprehensive, the available computational power increases and machine learning models become more sophisticated; there should be an effort to integrate these models into a larger research setting to predict various clinical outcomes.

Prediction of diabetes disease using an ensemble of machine learning multi-classifier models.

BACKGROUND AND OBJECTIVE: Diabetes is a life-threatening chronic disease with a growing global prevalence, necessitating early diagnosis and treatment to prevent severe complications. Machine learning has emerged as a promising approach for diabetes diagnosis, but challenges such as limited labeled data, frequent missing values, and dataset imbalance hinder the development of accurate prediction models. Therefore, a novel framework is required to address these challenges and improve performance. METHODS: In this study, we propose an innovative pipeline-based multi-classification framework to predict diabetes in three classes: diabetic, non-diabetic, and prediabetes, using the imbalanced Iraqi Patient Dataset of Diabetes. Our framework incorporates various pre-processing techniques, including duplicate sample removal, attribute conversion, missing value imputation, data normalization and standardization, feature selection, and k-fold cross-validation. Furthermore, we implement multiple machine learning models, such as k-NN, SVM, DT, RF, AdaBoost, and GNB, and introduce a weighted ensemble approach based on the Area Under the Receiver Operating Characteristic Curve (AUC) to address dataset imbalance. Performance optimization is achieved through grid search and Bayesian optimization for hyper-parameter tuning. RESULTS: Our proposed model outperforms other machine learning models, including k-NN, SVM, DT, RF, AdaBoost, and GNB, in predicting diabetes. The model achieves high average accuracy, precision, recall, F1-score, and AUC values of 0.9887, 0.9861, 0.9792, 0.9851, and 0.999, respectively. CONCLUSION: Our pipeline-based multi-classification framework demonstrates promising results in accurately predicting diabetes using an imbalanced dataset of Iraqi diabetic patients. The proposed framework addresses the challenges associated with limited labeled data, missing values, and dataset imbalance, leading to improved prediction performance. This study highlights the potential of machine learning techniques in diabetes diagnosis and management, and the proposed framework can serve as a valuable tool for accurate prediction and improved patient care. Further research can build upon our work to refine and optimize the framework and explore its applicability in diverse datasets and populations.

Development and validation of nomograms to predict survival of primary adrenal lymphoma: a population-based retrospective study.

While it is known that accurate evaluation of overall survival (OS) and disease-specific survival (DSS) for patients with primary adrenal lymphoma (PAL) can affect their prognosis, no stable and effective prediction model exists. This study aimed to develop prediction models to evaluate survival. This study enrolled 5448 patients with adrenal masses from the SEER Program. The influencing factors were selected using the least absolute shrinkage and selection operator regression model (LASSO) and Fine and Gray model (FGM). In addition, nomograms were constructed. Receiver operating characteristic curves and bootstrap self-sampling methods were used to verify the discrimination and consistency of the nomograms. The independent influencing factors for PAL survival were selected by LASSO and FGM, and three models were built: the OS, DSS, and FGS (DSS analysis by FGM) model. The areas under the curve and decision curve analyses indicated that the models were valid. This study developed survival prediction models to predict OS and DSS of patients with PAL. The FGS model was more accurate than the DSS model in the short term. Above all, these models should offer benefits to patients with PAL in terms of the treatment modality choice and survival evaluation.

Development of a Bispectral index score prediction model based on an interpretable deep learning algorithm.

BACKGROUND: Proper maintenance of hypnosis is crucial for ensuring the safety of patients undergoing surgery. Accordingly, indicators, such as the Bispectral index (BIS), have been developed to monitor hypnotic levels. However, the black-box nature of the algorithm coupled with the hardware makes it challenging to understand the underlying mechanisms of the algorithms and integrate them with other monitoring systems, thereby limiting their use. OBJECTIVE: We propose an interpretable deep learning model that forecasts BIS values 25 s in advance using 30 s electroencephalogram (EEG) data. MATERIAL AND METHODS: The proposed model utilized EEG data as a predictor, which is then decomposed into amplitude and phase components using fast Fourier Transform. An attention mechanism was applied to interpret the importance of these components in predicting BIS. The predictability of the model was evaluated on both regression and binary classification tasks, where the former involved predicting a continuous BIS value, and the latter involved classifying a dichotomous status at a BIS value of 60. To evaluate the interpretability of the model, we analyzed the attention values expressed in the amplitude and phase components according to five ranges of BIS values. The proposed model was trained and evaluated using datasets collected from two separate medical institutions. RESULTS AND CONCLUSION: The proposed model achieved excellent performance on both the internal and external validation datasets. The model achieved a root-mean-square error of 6.614 for the regression task, and an area under the receiver operating characteristic curve of 0.937 for the binary classification task. Interpretability analysis provided insight into the relationship between EEG frequency components and BIS values. Specifically, the attention mechanism revealed that higher BIS values were associated with increased amplitude attention values in high-frequency bands and increased phase attention values in various frequency bands. This finding is expected to facilitate a more profound understanding of the BIS prediction mechanism, thereby contributing to the advancement of anesthesia technologies.

Meta analysis of the diagnostic value of circulating miRNA in benign and malignant pulmonary nodules.

OBJECTIVE: A meta-analysis was conducted to assess the impact of miRNAs in circulation on diagnosing benign and malignant pulmonary nodules (BPNs and MPNs). METHODS: Electronic databases such as Embase, PubMed, Web of Science, and The Cochrane Library were utilized for diagnostic tests of circulating miRNAs to diagnose BPNs and MPNs from the library creation to February 2023. Meta-analysis of the included literature was performed using Stata 16, Meta-Disc 1.4, and Review Manager 5.4 software. This study determined the combined sensitivity, specificity, diagnostic ratio (DOR), positive/negative likelihood ratios (PLR/NLR), as well as value of area under the receiver operating characteristic (ROC) curve. RESULTS: This meta-analysis included 14 publications and 17 studies. According to our findings, the pooled sensitivity for miRNA in diagnosing benign and malignant pulmonary nodules was 0.82 [95% CI (0.74, 0.88)], specificity was 0.84 [95% CI (0.79, 0.88)], whereas the DOR was 22.69 [95% CI (13.87, 37.13)], PLR was 5.00 [95% CI (3.87, 6.46)], NLR was 0.22 [95% CI (0.15, 0.32)], and the area under the working characteristic curve (AUC) of the subject was 0.89 [95% CI (0.86, 0.91)]. CONCLUSION: Circulating miRNAs could be used with sensitivity, specificity, DOR, PLR, NLR, and AUC as biomarkers to diagnose pulmonary nodules (PNs). However, more research is needed to determine the optimum miRNA combinations for diagnosing PNs due to the significant heterogeneity on previous studies.

Predicting the outcomes of hepatocellular carcinoma downstaging with the use of clinical and radiomics features.

BACKGROUND: Downstaging of hepatocellular carcinoma (HCC) makes it possible for patients beyond the criteria to have the chance of liver transplantation (LT) and improved outcomes. Thus, a procedure to predict the prognosis of the treatment is an urgent requisite. The present study aimed to construct a comprehensive framework with clinical information and radiomics features to accurately predict the prognosis of downstaging treatment. METHODS: Specifically, three-dimensional (3D) tumor segmentation from contrast-enhanced computed tomography (CT) is employed to extract spatial information of the lesions. Then, the radiomics features within the segmented region are calculated. Combining radiomics features and clinical data prompts the development of feature selection to enhance the robustness and generalizability of the model. Finally, we adopt the support vector machine (SVM) algorithm to establish a classification model for predicting HCC downstaging outcomes. RESULTS: Herein, a comparative study was conducted on three different models: a radiomics features-based model (R model), a clinical features-based model (C model), and a joint radiomics clinical features-based model (R-C model). The average accuracy of the three models was 0.712, 0.792, and 0.844, and the average area under the receiver-operating characteristic (AUROC) of the three models was 0.775, 0.804, and 0.877, respectively. CONCLUSIONS: The novel and practical R-C model accurately predicted the downstaging outcomes, which could be utilized to guide the HCC downstaging toward LT treatment.

Scattering and absorption properties modification of optically cleared skeletal muscles: an ex vivo study.

Optical clearing is a relatively new approach to enhancing the optical transparency of biological tissues by reducing their scattering properties. The optical clearing effect is achievable via various chemical, physical, and photo-thermal techniques. The present work studied optical parameters of bovine skeletal muscles under different clearing protocols: immersion optical clearing in 99% glycerol and photo-thermal optical clearing via exposure to IR laser irradiation. Moreover, the two techniques were combined with different immersion time intervals after multiple exposure periods to get optimum results. The muscle samples' diffuse reflectance and total transmittance were measured using a single integrating sphere and introduced to the Kubleka-Munk mathematical model to determine the absorption and reduced scattering coefficients. Results revealed a 6% scattering reduction after irradiating the sample for 10 min and immersing it in glycerol for 18 min and 8% after 20 min of laser irradiation and 18 min of immersion. Moreover, increases of 6.5% and 7.5% in penetration depth were prominent for the total treatment times of 28 min and 38 min, respectively. Furthermore, the measurements' accuracy and sensitivity were analyzed and evaluated using the receiver operating characteristic method. The accuracy ranged from 0.93 to 0.98, with sensitivity from 0.93 to 0.99 for each clearing protocol. Although laser irradiation and application of 99% glycerol separately produced scattering light reduction, the maximal clearing effect was obtained while irradiating the sample with a laser for 20 min and then immersing it in 99% glycerol for a maximum of 18 min.

Validating existing clinical cut-points for the parent-reported Strengths and Difficulties Questionnaire in a large sample of Canadian children and youth. / Validation des seuils cliniques dans la version remplie par les parents du Questionnaire sur les points forts et les points faibles au sein d'un vaste échantillon d'enfants et de jeunes canadiens.

INTRODUCTION: The Strengths and Difficulties Questionnaire (SDQ), for assessing behavioural and emotional difficulties, has been used internationally as a screening measure for mental health problems. Our objective was to validate the existing (British) SDQ cut-points in a sample of Canadian children and youth, and develop new Canadian SDQ cut-points if needed. METHODS: This study includes data from children and youth aged 6 to 17 years from the Canadian Health Measures Survey (n = 3435) and outpatient records from the Children's Hospital of Eastern Ontario (n = 1075). The parent-reported SDQ data were collected. We adjusted the existing SDQ cut-points using a distributional and receiver-operating characteristic (ROC) curve approach. We subsequently calculated the sensitivity, specificity and diagnostic odds ratio of the existing and new SDQ clinical cut-points to determine whether the new cut-points had better clinical utility, using both analytic approaches. RESULTS: Our data show differences in the screening effectiveness between the existing British and the Canadian-specific clinical cut-points. Specificity is maximized using the Canadian distributional cut-points, improving the likelihood of identifying true negative results. The total SDQ score met the threshold for clinical utility (diagnostic odds ratio > 20) using both the existing and new cut-points; however, the individual scales did not reach clinical utility threshold using either cut-points. CONCLUSIONS: Future Canadian SDQ research should consider the new cut-points derived from our study population and the existing British cut-points to allow for historical and international comparisons.

Differentiating tumour progression from pseudoprogression in glioblastoma patients: a monoexponential, biexponential, and stretched-exponential model-based DWI study.

BACKGROUND: To investigate the diagnostic performance of parameters derived from monoexponential, biexponential, and stretched-exponential diffusion-weighted imaging models in differentiating tumour progression from pseudoprogression in glioblastoma patients. METHODS: Forty patients with pathologically confirmed glioblastoma exhibiting enhancing lesions after completion of chemoradiation therapy were enrolled in the study, which were then classified as tumour progression and pseudoprogression. All patients underwent conventional and multi-b diffusion-weighted MRI. The apparent diffusion coefficient (ADC) from a monoexponential model, the true diffusion coefficient (D), pseudodiffusion coefficient (D*) and perfusion fraction (f) from a biexponential model, and the distributed diffusion coefficient (DDC) and intravoxel heterogeneity index (α) from a stretched-exponential model were compared between tumour progression and pseudoprogression groups. Receiver operating characteristic curves (ROC) analysis was used to investigate the diagnostic performance of different DWI parameters. Interclass correlation coefficient (ICC) was used to evaluate the consistency of measurements. RESULTS: The values of ADC, D, DDC, and α values were lower in tumour progression patients than that in pseudoprogression patients (p < 0.05). The values of D* and f were higher in tumour progression patients than that in pseudoprogression patients (p < 0.05). Diagnostic accuracy for differentiating tumour progression from pseudoprogression was highest for α(AUC = 0.94) than that for ADC (AUC = 0.91), D (AUC = 0.92), D* (AUC = 0.81), f (AUC = 0.75), and DDC (AUC = 0.88). CONCLUSIONS: Multi-b DWI is a promising method for differentiating tumour progression from pseudoprogression with high diagnostic accuracy. In addition, the α derived from stretched-exponential model is the most promising DWI parameter for the prediction of tumour progression in glioblastoma patients.

Diagnostic evaluation of Panbio™ antigen rapid diagnostic test for SARS-CoV-2: A systematic review and meta-analysis.

INTRODUCTION: The reverse transcriptase polymerase chain reaction (RT-PCR) is the reference diagnostic method for the confirmation of SARS-CoV-2 infected cases. However, various antigen rapid diagnostic tests (Ag-RDTs) have been developed. The purpose of this meta-analysis study was to assess the diagnostic performance of Panbio™ Ag-RDT (Abbott Point of Care) in identifying the SARS-CoV-2 virus. METHODS: We systematically searched eight databases from March 2020 until March 2023 to look for potentially eligible articles. Diagnostic meta-analysis of Panbio™ Ag-RDT used diverse evaluation indicators, including sensitivity, specificity, Diagnostic Odds Ratio (DOR), and the area under the curve (AUC) value. RESULTS: Of the 794 articles identified, 49 studies met the inclusion criteria. The pooled estimates of Panbio™ Ag-RDT for the diagnosis of SARS-CoV-2 were 0,65 (95% CI: 0,64-0,66), 0,99 (95% CI: 0,99-1,00), 578,03 (95% CI: 333,37-1002,26) for sensitivity, specificity, and DOR, respectively. Moreover, the summary receiver operating characteristic (SROC) curve revealed an AUC value of 0,942 (95% CI: 0,941-0,943), suggesting an outstanding diagnostic accuracy. Subgroup and meta-regression analyses showed that continent, study period, age, study population and cycle threshold (Ct) values constituted a source of heterogeneity. Furthermore, we demonstrated proof of publication bias for DOR values analyzed using Deek's test (p = 0,001) and funnel plot. CONCLUSION: Panbio™ Ag-RDT presented an outstanding diagnostic accuracy in the detection of the SARS-CoV-2 virus in both adults and children with or without symptoms.

Spatial Variation Generation Algorithm for Motor Imagery Data Augmentation: Increasing the Density of Sample Vicinity.

The imbalanced development between deep learning-based model design and motor imagery (MI) data acquisition raises concerns about the potential overfitting issue-models can identify training data well but fail to generalize test data. In this study, a Spatial Variation Generation (SVG) algorithm for MI data augmentation is proposed to alleviate the overfitting issue. In essence, SVG generates MI data using variations of electrode placement and brain spatial pattern, ultimately elevating the density of the raw sample vicinity. The proposed SVG prevents models from memorizing the training data by replacing the raw samples with the proper vicinal distribution. Moreover, SVG generates a uniform distribution and stabilizes the training process of models. In comparison studies involving five deep learning-based models across eight datasets, the proposed SVG algorithm exhibited a notable improvement of 0.021 in the area under the receiver operating characteristic curve (AUC). The improvement achieved by SVG outperforms other data augmentation algorithms. Further results from the ablation study verify the effectiveness of each component of SVG. Finally, the studies in the control group with varying numbers of samples show that the SVG algorithm consistently improves the AUC, with improvements ranging from approximately 0.02 to 0.15.

The predictive value of [TIMP-2]*[IGFBP7] in adverse outcomes for acute kidney injury: a systematic review and meta-analysis.

MATERIALS AND METHODS: Relevant articles published up to 17 June 2023 were retrieved from five databases (Cochrane Library/Embase/PubMed/SinoMed/Web of Science). The pre-established inclusion and exclusion criteria determined the selection of publications. Pooled sensitivity (SEN), specificity (SPE), diagnostic odds ratio, likelihood ratio, and summary receiver operating characteristic curve were employed to assess the predictive value. The presence or potential sources of heterogeneity were investigated via subgroup and SEN analyses. RESULTS: Ten published and eligible studies (1559 cases) were included in the evaluation for the capability of [TIMP-2]*[IGFBP7] to predict the poor prognosis of AKI through the random effect model. Pooled SEN, SPE, diagnostic odds ratio, and positive and negative likelihood ratios were 0.82 (95% CI: 0.77-0.86, I2 = 53.4%), 0.64 (95% CI: 0.61-0.67, I2 = 88.3%), 14.06 (95% CI: 7.31-27.05, I2 = 55.0%), 2.859 (95% CI: 2.15-3.77, I2 = 80.7%), and 0.28 (95% CI: 0.20-0.40, I2 = 35.0%), respectively. The estimated area under the curve was 0.8864 (standard error: 0.0306), and the Q* was 0.7970 (standard error: 0.0299). The endpoints and cutoff values were the main causes of heterogeneity. CONCLUSIONS: [TIMP-2]*[IGFBP7] is possible in predicting poor prognosis of AKI, but it is better to be applied along with other indicators or clinical risk factors.

Evidence of questionable research practices in clinical prediction models.

BACKGROUND: Clinical prediction models are widely used in health and medical research. The area under the receiver operating characteristic curve (AUC) is a frequently used estimate to describe the discriminatory ability of a clinical prediction model. The AUC is often interpreted relative to thresholds, with "good" or "excellent" models defined at 0.7, 0.8 or 0.9. These thresholds may create targets that result in "hacking", where researchers are motivated to re-analyse their data until they achieve a "good" result. METHODS: We extracted AUC values from PubMed abstracts to look for evidence of hacking. We used histograms of the AUC values in bins of size 0.01 and compared the observed distribution to a smooth distribution from a spline. RESULTS: The distribution of 306,888 AUC values showed clear excesses above the thresholds of 0.7, 0.8 and 0.9 and shortfalls below the thresholds. CONCLUSIONS: The AUCs for some models are over-inflated, which risks exposing patients to sub-optimal clinical decision-making. Greater modelling transparency is needed, including published protocols, and data and code sharing.

Diagnostic efficacy of systemic immune-inflammation biomarkers in benign prostatic hyperplasia using receiver operating characteristic and artificial neural network.

Benign prostatic hyperplasia (BPH) is a chronic, progressive disease characterized by mesenchymal cell-predominance and stromal and glandular cell-hyperproliferation. Although, the precise cause of BPH is unknown, it is believed to be associated with hormonal changes in aging men. Despite androgens and ageing are likely to play a role in the development of BPH, the pathophysiology of BPH remains uncertain. This paper aims to evaluate the diagnostic efficacy of platelet-to-lymphocyte ratio (PLR), neutrophil-lymphocyte ratio (NLR) and systemic immune-inflammation index in in diagnosing BPH. A single-center-randomized-retrospective study was carried out at Alzahraa university hospital between January 2022 and November 2022 on 80 participants (40 non-BPH subjects and 40 patients with symptomatic enlarged prostate) who visited the outpatient clinic or admitted to the urology department. The BPH cases were evaluated by digital rectal examination (DRE), International Prostate Symptom Score (IPSS), prostate size, prostate specific antigen (PSA), TRUS biopsy in elevated PSA > 4 ng/ml, PLR, NLR and systemic immune inflammatory (SII). The diagnosing efficiency of the selected parameters was evaluated using Receiver Operating Characteristic (ROC) and Artificial Neural Network (ANN) showing excellent discrimination with 100% accuracy and AUC = 1 in the ROC curves. Moreover, the accuracy rate of the ANN exceeds 99%. Conclusion: PLR, NLR and SII can be significantly employed for diagnosing BPH.

Machine Learning Approach for Predicting Systemic Lupus Erythematosus in an Oman-Based Cohort.

Objectives: This study aimed to design a machine learning-based prediction framework to predict the presence or absence of systemic lupus erythematosus (SLE) in a cohort of Omani patients. Methods: Data of 219 patients from 2006 to 2019 were extracted from Sultan Qaboos University Hospital's electronic records. Among these, 138 patients had SLE, while the remaining 81 had other rheumatologic diseases. Clinical and demographic features were analysed to focus on the early stages of the disease. Recursive feature selection was implemented to choose the most informative features. The CatBoost classification algorithm was utilised to predict SLE, and the SHAP explainer algorithm was applied on top of the CatBoost model to provide individual prediction reasoning, which was then validated by rheumatologists. Results: CatBoost achieved an area under the receiver operating characteristic curve score of 0.95 and a sensitivity of 92%. The SHAP algorithm identified four clinical features (alopecia, renal disorders, acute cutaneous lupus and haemolytic anaemia) and the patient's age as having the greatest contribution to the prediction. Conclusion: An explainable framework to predict SLE in patients and provide reasoning for its prediction was designed and validated. This framework enables clinicians to implement early interventions that will lead to positive healthcare outcomes.

Heterogeneidad del tumor primario en la18F-FDG PET/TC pretratamiento para predecir el pronóstico en pacientes con cáncer de recto sometidos a cirugía tras terapia neoadyuvante / Primary tumor heterogeneity on pretreatment18F-FDG PET/CT to predict outcome in patients with rectal cancer who underwent surgery after neoadjuvant therapy

Objetivo Estudio retrospectivo cuyo objetivo fue investigar el valor de las características de textura de los tumores primarios en la PET/TC con 18F-FDG pretratamiento para la predicción de la respuesta al tratamiento, la progresión y la supervivencia global en pacientes con cáncer de recto que se sometieron a cirugía después de la terapia neoadyuvante (TNA). Métodos Se incluyeron en este estudio pacientes con cáncer de recto que se sometieron a estudio PET/TC con 18F-FDG antes del tratamiento y se sometieron a cirugía después de TNA. Se registraron las características clínico-patológicas, la fecha del último seguimiento, la evolución y fallecimiento. Los parámetros de las texturas y los convencionales de PET (Standard Uptake Value-SUVmax, volumen tumoral metabólico-MTV, glucólisis total de la lesión-TLG) se obtuvieron a partir de imágenes PET/TC utilizando el programa LifeX. Los parámetros se agruparon utilizando el índice de Youden en el análisis ROC. Los factores que predicen la respuesta patológica al tratamiento, la progresión y la supervivencia global se determinaron mediante regresión logística y análisis de regresión de Cox. Resultados Cuarenta y cuatro pacientes (26-59% hombres, 18-41% mujeres; 60,1 ± 11,4 años) con cáncer de recto fueron incluidos en este estudio. El número de pacientes respondedores y no respondedores a TNA fueron de 15 (34,9%) y 28 (65,1%), respectivamente. La mediana de la duración del seguimiento fue de 29,9 meses. 9 (20,5%) mostraron progresión de la enfermedad y 8 (18,2%) fallecieron durante el período de seguimiento. Los parámetros de entropía GLCM de diferencia y correlación GLCM se encontraron como predictores independientes para la respuesta a TNA. Los parámetros de positividad del margen quirúrgico, rango intercuartílico de intensidad CONV y textura AUC-CSHDISC fueron predictores independientes de progresión (AU)

Purpose This retrospective study aimed to investigate the value of texture features of primary tumors in pretreatment18F-FDG PET/CT in the prediction of response to treatment, progression, and overall survival in patients with rectal cancer who underwent surgery after neoadjuvant therapy (NAT). Method Patients with rectal cancer who had pretreatment18F-FDG PET/CT, and underwent surgery after NAT were included in this study. Clinicopathologic features, date of last follow-up, progression, and death were recorded. Textural and conventional PET parameters (maximum standardized uptake value-SUVmax, metabolic tumor volume-MTV, total lesion glycolysis-TLG) were obtained from PET/CT images using LifeX program. Parameters were grouped using Youden index in ROC analysis. Factors predicting the pathological response to treatment, progression, and overall survival were determined using logistic regression and Cox regression analyses. Results Forty-four patients (26(59%) male, 18 (41%) female; 60.1 ± 11.4 years) with rectal cancer were included in this study. The numbers of patients with responders and non-responders to NAT were15(34.9%) and 28(65.1%), respectively. One patient’ pathology report did not contain the response status to NAT. The median of follow-up duration was 29.9 months. 9(20.5%) showed disease progression, and 8(18.2%) died during the follow-up period. Difference entropy GLCM and correlation GLCM parameters were found as independent predictors for response to NAT. The positivity of surgical margin, intensity interquartile range CONV and AUC-CSHDISC texture parameters were independent predictors of progression, while normalized inverse difference GLCM and LZLGEGLZLM parameters were independent predictorsof mortality. Conclusion The texture parameters obtained from pretreatment18F-FDG PET/CT have presented a more robust predictive value than conventional parameters in patients with rectal cancer who underwent surgery after NAT (AU)