The Diagnostic Efficacy of the American College of Radiology (ACR) Thyroid Imaging Report and Data System (TI-RADS) and the American Thyroid Association (ATA) Risk Stratification Systems for Thyroid Nodules

Background. This study is aimed at evaluating the diagnostic efficacy of ultrasound-based risk stratification for thyroid nodules in the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) and the American Thyroid Association (ATA) risk stratification systems. Methods. 286 patients with thyroid cancer were included in the tumor group, with 259 nontumor cases included in the nontumor group. The ACR TI-RADS and ATA risk stratification systems assessed all thyroid nodules for malignant risks. The diagnostic effect of ACR and ATA risk stratification system for thyroid nodules was evaluated by receiver operating characteristic (ROC) analysis using postoperative pathological diagnosis as the gold standard. Results. The distributions and mean scores of ACR and ATA rating risk stratification were significantly different between the tumor and nontumor groups. The lesion diameter > 1 cm subgroup had higher malignant ultrasound feature rates detected and ACR and ATA scores. A significant difference was not found in the ACR and ATA scores between patients with or without Hashimoto’s disease. The area under the receiver operating curve (AUC) for the ACR TI-RADS and the ATA systems was 0.891 and 0.896, respectively. The ACR had better specificity (0.90) while the ATA system had higher sensitivity (0.92), with both scenarios having almost the same overall diagnostic accuracy (0.84). Conclusion. Both the ACR TI-RADS and the ATA risk stratification systems provide a clinically feasible thyroid malignant risk classification, with high thyroid nodule malignant risk diagnostic efficacy.

Development of a clinical model to predict vagus nerve stimulation response in pediatric patients with drug-resistant epilepsy

Introduction Epilepsy impacts 470,000 children in the United States, and children with epilepsy are estimated to expend 6 times more on healthcare than those without epilepsy. For patients with antiseizure medication (ASM)-resistant epilepsy and unresectable seizure foci, vagus nerve stimulation (VNS) is a treatment option. Predicting response to VNS has been historically challenging. We aimed to create a clinical prediction score which could be utilized in a routine outpatient clinical setting. Methods We performed an 11-year, single-center retrospective analysis of patients <21 years old with ASM-resistant epilepsy who underwent VNS. The primary outcome was >50% seizure frequency reduction after one year. Univariate and multivariate logistic regressions were performed to assess clinical factors associated with VNS response; 70% and 30% of the sample were used to train and validate the multivariate model, respectively. A prediction score was developed based on the multivariate regression. Sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated. Results This analysis included 365 patients. Multivariate logistic regression revealed that variables associated with VNS response were: <4 years of epilepsy duration before VNS (p=0.008) and focal motor seizures (p=0.037). The variables included in the clinical prediction score were: epilepsy duration before VNS, age at seizure onset, number of pre-VNS ASMs, if VNS was the patient's first therapeutic epilepsy surgery, and predominant seizure semiology. The final AUC was 0.7013 for the "fitted" sample and 0.6159 for the "validation" sample. Conclusions We developed a clinical model to predict VNS response in one of the largest samples of pediatric VNS patients to date. While the presented clinical prediction model demonstrated an acceptable AUC in the training cohort, clinical variables alone likely do not accurately predict VNS response. This score may be useful upon further validation, though its predictive ability underscores the need for more robust biomarkers of treatment response.

Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI

Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.

A prediction model for recurrence after translabyrinthine surgery for vestibular schwannoma: toward personalized postoperative surveillance

Purpose The aim of this study is to compute and validate a statistical predictive model for the risk of recurrence, defined as regrowth of tumor necessitating salvage treatment, after translabyrinthine removal of vestibular schwannomas to individualize postoperative surveillance. Methods The multivariable predictive model for risk of recurrence was based on retrospectively collected patient data between 1995 and 2017 at a tertiary referral center. To assess for internal validity of the prediction model tenfold cross-validation was performed. A ‘low’ calculated risk of recurrence in this study was set at < 1%, based on clinical criteria and expert opinion. Results A total of 596 patients with 33 recurrences (5.5%) were included for analysis. The final prediction model consisted of the predictors ‘age at time of surgery’, ‘preoperative tumor growth’ and ‘first postoperative MRI outcome’. The area under the receiver operating curve of the prediction model was 89%, with a C-index of 0.686 (95% CI 0.614–0.796) after cross-validation. The predicted probability for risk of recurrence was low (< 1%) in 373 patients (63%). The earliest recurrence in these low-risk patients was detected at 46 months after surgery. Conclusion This study presents a well-performing prediction model for the risk of recurrence after translabyrinthine surgery for vestibular schwannoma. The prediction model can be used to tailor the postoperative surveillance to the estimated risk of recurrence of individual patients. It seems that especially in patients with an estimated low risk of recurrence, the interval between the first and second postoperative MRI can be safely prolonged.

A Web-Based Prediction Model for Overall Survival of Elderly Patients With Malignant Bone Tumors: A Population-Based Study

Background: Malignant bone tumors (MBT) are one of the causes of death in elderly patients. The purpose of our study is to establish a nomogram to predict the overall survival (OS) of elderly patients with MBT.Methods: The clinicopathological data of all elderly patients with MBT from 2004 to 2018 were downloaded from the SEER database. They were randomly assigned to the training set (70%) and validation set (30%). Univariate and multivariate Cox regression analysis was used to identify independent risk factors for elderly patients with MBT. A nomogram was built based on these risk factors to predict the 1-, 3-, and 5-year OS of elderly patients with MBT. Then, used the consistency index (C-index), calibration curve, and the area under the receiver operating curve (AUC) to evaluate the accuracy and discrimination of the prediction model was. Decision curve analysis (DCA) was used to assess the clinical potential application value of the nomogram. Based on the scores on the nomogram, patients were divided into high- and low-risk groups. The Kaplan-Meier (K-M) curve was used to test the difference in survival between the two patients.Results: A total of 1,641 patients were included, and they were randomly assigned to the training set (N = 1,156) and the validation set (N = 485). The univariate and multivariate analysis of the training set suggested that age, sex, race, primary site, histologic type, grade, stage, M stage, surgery, and tumor size were independent risk factors for elderly patients with MBT. The C-index of the training set and the validation set were 0.779 [0.759–0.799] and 0.801 [0.772–0.830], respectively. The AUC of the training and validation sets also showed similar results. The calibration curves of the training and validation sets indicated that the observed and predicted values were highly consistent. DCA suggested that the nomogram had potential clinical value compared with traditional TNM staging.Conclusion: We had established a new nomogram to predict the 1-, 3-, 5-year OS of elderly patients with MBT. This predictive model can help doctors and patients develop treatment plans and follow-up strategies.

Criterion Validity and Applicability of Motor Screening Instruments in Children Aged 5–6 Years: A Systematic Review

The detection of motor developmental problems, especially developmental coordination disorder, at age 5–6 contributes to early interventions. Here, we summarize evidence on (1) criterion validity of screening instruments for motor developmental problems at age 5–6, and (2) their applicability. We systematically searched seven databases for studies assessing criterion validity of these screening instruments using the M-ABC as reference standard. We applied COSMIN criteria for systematic reviews of screening instruments to describe the correlation between the tests and the M-ABC. We extracted information on correlation coefficients or area under the receiver operating curve, sensitivity and specificity, and applicability in practice. We included eleven studies, assessing eight instruments: three performance-based tests (MAND, MOT 4–6, BFMT) and five questionnaires (DCD-Q, PQ, ASQ-3, MOQ-T-FI, M-ABC-2-C). The quality of seven studies was fair, one was good, and three were excellent. Seven studies reported low correlation coefficients or AUC (<0.70), four did not report these. Sensitivities ranged from 21–87% and specificities from 50–96%, with the MOT4–6 having the highest sensitivity and specificity. The DCD-Q, PQ, ASQ-3, MOQ-T-FI, and M-ABC-2-C scored highest on applicability. In conclusion, none of the instruments were sufficiently valid for motor screening at age 5–6. More research is needed on screening instruments of motor delay at age 5–6.

Assessing The Inflammatory Severity of The Terminal Ileum In Crohn Disease Using Radiomics Based On MRI

Background: Evaluating inflammatory severity using imaging is essential for Crohn’s disease (CD), but it is limited by potential interobserver variation and subjectivity. We compared the efficiency of magnetic resonance index of activity (MaRIA) collected by radiologists and a radiomics model in assessing the inflammatory severity of terminal ileum (TI).Methods: 121 patients were collected from two centers. Patients were divided into ulcerative group and mucosal remission group based on the TI Crohn's disease Endoscopic Severity Index (tCDEIS). The consistency of bowel wall thickness (BWT), relative contrast enhancement (RCE), edema, ulcer, MaRIA and features of the region of interest (ROI) between radiologists were described by weighted k coefficient and intraclass correlation coefficient (ICC), and developed receiver operating curve (ROC) of MaRIA. The radiomics model was established using reproducible features of logistic regression based on arterial staging of T1WI sequences. Delong test was used to compare radiomics with MaRIA.Results: The consistency between radiologists were moderate in BWT (ICC=0.638), fair in edema (k=0.541), RCE (ICC=0.461), MaRIA (ICC=0.579) and poor in ulcer (k=0.271). Radiomics model was developed by 6 reproducible features (ICC=0.93-0.96) and equivalent to MaRIA which evaluated by the senior radiologist(0.872 vs 0.883 in training group, 0.824 vs 0.783 in testing group, P=0.847, 0.471), both of which were significant higher than MaRIA evaluated by junior radiologist(AUC: 0.621 in training group, 0.557 in testing group, all, PB0.05).

Predictors of In-Hospital Mortality in Stroke Patients

Background: In-hospital mortality is a good indicator to assess the efficacy of stroke care. Identifying the predictors of in-hospital mortality is important to advance the stroke outcome and plan the future strategies of stroke management. Methods: This was a prospective observational study conducted at a tertiary referral center in Sri Lanka to identify the possible predictors of in-hospital mortality. The study included 246 confirmed stroke patients. The diagnosis of stroke was established on the clinical history, examination and neuroimaging. The differentiation of stroke in to haemorrhagic type and ischaemic type was based on the results of computed tomography. In all patients, demographic data, comorbidities, clinical signs (pulse rate, respiratory rate, systolic blood pressure, diastolic blood pressure, on admission Glasgow Coma Scale (GCS) score) and imaging findings were recorded. Serum electrolyte test was performed in all stroke patients and hyponatremia was defined as serum Na+ less than 131mmol/l. All patients were followed up throughout their hospital course and the in-hospital mortality was recorded. In hospital mortality was defined as the deaths which occurred due to stroke after 24 hours of hospital admission. Results: The incidence of in-hospital mortality was 11.7% (95% confidence interval 8-16.4). The mean day of in-hospital deaths to occur was 5.9 days (SD±3.8 Min 2 Max 20). According to multivariate logistic regression analysis on admission GCS score (Odds Ratio (OR)-0.71) and haemorrhagic stroke type (OR-5.12) predict the in-hospital mortality. The area under the curve of receiver operating curve drawn for the on admission GCS score was 0.78 with a sensitivity of 96.31% and specificity of 41.38% for a patient presented with the GCS score of <10. Conclusion: On admission GCS and haemorrhagic stroke are independent predictors of in-hospital mortality. Patients with on admission GCS <10 have a moderate predictive ability in predicting the in-hospital mortality. Thus, a special attention should be given to the patients with low GCS score and haemorrhagic strokes for reducing rates of in-hospital mortality.

Hepatocellular carcinoma diagnosis using a novel electrochemiluminescence immunoassay targeting serum IgM-free AIM

Background Recent increases in the number of patients with non-alcoholic steatohepatitis (NASH) warrant the identification of biomarkers for early detection of hepatocellular carcinoma (HCC) associated with NASH (NASH-HCC). IgM-free apoptosis inhibitor of macrophage (AIM), which generally associates with IgM in blood and exerts its biological function by dissociation from IgM, may serve as an effective biomarker for NASH-HCC. Here, we established a fully automatic and high-throughput electrochemiluminescence immunoassay (ECLIA) to measure IgM-free AIM and investigated its efficacy in diagnosing NASH-HCC and viral HCC. Methods IgM-free AIM levels were measured in 212 serum samples from patients with, or without, HCC related to NASH, hepatitis B virus, and hepatitis C virus, using ECLIA. We also developed an ECLIA for measuring both IgM-free and IgM-bound AIM and investigated the existing form of AIM in blood by size-exclusion chromatography. Results IgM-free AIM levels were significantly higher in the HCC group than in the non-HCC group, regardless of the associated pathogenesis. Moreover, the area under the receiver operating curve for IgM-free AIM was greater than that for conventional HCC biomarkers, alpha-fetoprotein or des-γ-carboxy prothrombin, regardless of the cancer stage. ECLIA counts of IgM-free AIM derived from samples fractionated by size-exclusion chromatography were significantly higher in patients with NASH-HCC than in healthy volunteers and in patients with non-alcoholic fatty liver and NASH. Conclusions Serum IgM-free AIM may represent a universal HCC diagnostic marker superior to alpha-fetoprotein or des-γ-carboxy prothrombin. Our newly established ECLIA could contribute to further clinical studies on AIM and in vitro HCC diagnosis.

Plasma circN4BP2L2 is a promising novel diagnostic biomarker for epithelial ovarian cancer

Background Circular RNAs (circRNAs) are more stable than linear RNA molecules, which makes them promising diagnostic biomarkers for diseases. By circRNA-sequencing analysis, we previously found that circN4BP2L2 was significantly decreased in epithelial ovarian cancer (EOC) tissues, and was predictive of disease progression. The aim of this study was to evaluate the diagnostic value of plasma circN4BP2L2 in EOC. Methods Three hundred seventy-eight plasma samples were acquired prior to surgery. Samples were obtained from 126 EOC patients, 126 benign ovarian cyst patients, and 126 healthy volunteers. CircN4BP2L2 was assessed using reverse transcription-quantitative polymerase chain reaction (RT-qPCR). Cancer antigen 125 (CA125) and human epididymis protein 4 (HE4) were assessed using enzyme-linked immunosorbent assay (ELISA). EOC cells were transfected with small interference RNAs (siRNAs) and cell proliferation, migration, invasion, cell cycle and cell apoptosis were performed to assess the effect of circN4BP2L2 in EOC. Receiver operating curve (ROC), the area under the curve (AUC), sensitivity and specificity were estimated. Results Plasma circN4BP2L2 was significantly downregulated in EOC patients. Decreased circN4BP2L2 was significantly associated with advanced tumor stage, worse histological grade, lymph node metastasis and distant metastasis in EOC. CircN4BP2L2 inhibited tumor cell migration and invasion in vitro. CircN4BP2L2 could significantly separate EOC from benign (AUC = 0.82, P < 0.01) or normal (AUC = 0.90, P < 0.01) cohort. Early stage EOC vs benign (AUC = 0.81, P < 0.01) or normal (AUC = 0.90, P < 0.01) cohort could also be distinguished by circN4BP2L2. In discrimination between EOC cohort and benign or normal cohort, circN4BP2L2 performed equally well in both pre- and post-menopausal women. The combination of circN4BP2L2, CA125 and HE4 showed high sensitivity and specificity in detecting EOC cases. Conclusions Plasma circN4BP2L2 is significantly downregulated in EOC and might serve as a promising novel diagnostic biomarker for EOC patients, especially in early stage EOC cases. CircN4BP2L2 might act as an adjunct to CA125 and HE4 in detecting EOC. Further large-scale studies are warranted to verify our results.