The Future of Precision Prevention for Advanced Melanoma

Precision prevention of advanced melanoma is fast becoming a realistic prospect, with personalized, holistic risk stratification allowing patients to be directed to an appropriate level of surveillance, ranging from skin self-examinations to regular total body photography with sequential digital dermoscopic imaging. This approach aims to address both underdiagnosis (a missed or delayed melanoma diagnosis) and overdiagnosis (the diagnosis and treatment of indolent lesions that would not have caused a problem). Holistic risk stratification considers several types of melanoma risk factors: clinical phenotype, comprehensive imaging-based phenotype, familial and polygenic risks. Artificial intelligence computer-aided diagnostics combines these risk factors to produce a personalized risk score, and can also assist in assessing the digital and molecular markers of individual lesions. However, to ensure uptake and efficient use of AI systems, researchers will need to carefully consider how best to incorporate privacy and standardization requirements, and above all address consumer trust concerns.

Machine learning in perioperative medicine: a systematic review

Background Risk stratification plays a central role in anesthetic evaluation. The use of Big Data and machine learning (ML) offers considerable advantages for collection and evaluation of large amounts of complex health-care data. We conducted a systematic review to understand the role of ML in the development of predictive post-surgical outcome models and risk stratification. Methods Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, we selected the period of the research for studies from 1 January 2015 up to 30 March 2021. A systematic search in Scopus, CINAHL, the Cochrane Library, PubMed, and MeSH databases was performed; the strings of research included different combinations of keywords: “risk prediction,” “surgery,” “machine learning,” “intensive care unit (ICU),” and “anesthesia” “perioperative.” We identified 36 eligible studies. This study evaluates the quality of reporting of prediction models using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist. Results The most considered outcomes were mortality risk, systemic complications (pulmonary, cardiovascular, acute kidney injury (AKI), etc.), ICU admission, anesthesiologic risk and prolonged length of hospital stay. Not all the study completely followed the TRIPOD checklist, but the quality was overall acceptable with 75% of studies (Rev #2, comm #minor issue) showing an adherence rate to TRIPOD more than 60%. The most frequently used algorithms were gradient boosting (n = 13), random forest (n = 10), logistic regression (LR; n = 7), artificial neural networks (ANNs; n = 6), and support vector machines (SVM; n = 6). Models with best performance were random forest and gradient boosting, with AUC > 0.90. Conclusions The application of ML in medicine appears to have a great potential. From our analysis, depending on the input features considered and on the specific prediction task, ML algorithms seem effective in outcomes prediction more accurately than validated prognostic scores and traditional statistics. Thus, our review encourages the healthcare domain and artificial intelligence (AI) developers to adopt an interdisciplinary and systemic approach to evaluate the overall impact of AI on perioperative risk assessment and on further health care settings as well.

Pattern of Cytogenetic Abnormality by Fluorescence in Situ Hybridization (FISH) in Multiple Myeloma Patients in a Tertiary Hospital

Background: Multiple myeloma is a plasma cell neoplasm with acquired genetic abnormalities of clinical and prognostic importance, with survival duration ranging from a few months to more than 10 years. Cytogenetic abnormalities (CA) detected by fluorescence in situ hybridization (FISH) are of major prognostic significance since e.g. patients with del(17p), t(4;14) or gain 1q21 show dismal outcome. Objective: To evaluate the cytogenetic patterns by fluorescence in situ hybridization (FISH) of clinically diagnosed cases of multiple myeloma.Methods:This cross-sectional study was conducted in Department of Haematology, Dhaka Medical College Hospital, Dhaka, from January 2018 to December 2018. A total number of 30 patients with multiple myeloma were analyzed cytogenetically by interphase fluorescence in situ hybridization (iFISH). The collected data were analyzed by using the Statistical Package for Social Science (SPSS-24) for windows version 10.0.Results:Out of 30 diagnosed Multiple Myeloma cases the mean age was 56.37±10.38 years and male to female ratio was almost 3:1. Sixteen (56.7%) of 30 patients. Among 30 cases of 8 cases were thyrogenicity positive of 7(23.3%) patients was detected del 13q positive. Isolated del 13q was found in 4 cases. 2 cases were found coexistence of del 13q and del 17p positive ;1 case was found coexistence of del 13q and t(4;14) positive and rest of 1 case had del 17 p positive. There was no detectable t (11; 14) and t(14;16) in any of 30 cases.Conclusion:FISH panel for Multiple Myeloma including del (13q); t(11;14); t(4;14), del(17p), t(14;16) is very important molecular test for the prognosis , risk stratification, treatment modality of the patient. On the basis of cytogenetic abnormality Multiple Myeloma risk stratification is modified now a day. This Revised International Staging system R-ISS is a simple and powerful prognostic staging system.

Prediction and risk stratification from hospital discharge records based on Hierarchical sLDA

Background The greatly accelerated development of information technology has conveniently provided adoption for risk stratification, which means more beneficial for both patients and clinicians. Risk stratification offers accurate individualized prevention and therapeutic decision making etc. Hospital discharge records (HDRs) routinely include accurate conclusions of diagnoses of the patients. For this reason, in this paper, we propose an improved model for risk stratification in a supervised fashion by exploring HDRs about coronary heart disease (CHD). Methods We introduced an improved four-layer supervised latent Dirichlet allocation (sLDA) approach called Hierarchical sLDA model, which categorized patient features in HDRs as patient feature-value pairs in one-hot way according to clinical guidelines for lab test of CHD. To address the data missing and imbalance problem, RFs and SMOTE methods are used respectively. After TF-IDF processing of datasets, variational Bayes expectation-maximization method and generalized linear model were used to recognize the latent clinical state of a patient, i.e., risk stratification, as well as to predict CHD. Accuracy, macro-F1, training and testing time performance were used to evaluate the performance of our model. Results According to the characteristics of our datasets, i.e., patient feature-value pairs, we construct a supervised topic model by adding one more Dirichlet distribution hyperparameter to sLDA. Compared with established supervised algorithm Multi-class sLDA model, we demonstrate that our proposed approach enhances training time by 59.74% and testing time by 25.58% but almost no loss of average prediction accuracy on our datasets. Conclusions A model for risk stratification and prediction of CHD based on sLDA model was proposed. Experimental results show that Hierarchical sLDA model we proposed is competitive in time performance and accuracy. Hierarchical processing of patient features can significantly improve the disadvantages of low efficiency and time-consuming Gibbs sampling of sLDA model.

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.

The Diagnostic Role of Uric Acid to Creatinine Ratio for the Identification of Patients with Adverse Pulmonary Embolism Outcomes

Background: Uric acid (UA) is the final product of purine metabolism and a marker of oxidative stress that may be involved in the pathophysiology of cardiovascular and thromboembolic disease. The aim of the current study is to investigate the potential value of UA to creatinine ratio (UA/Cr) as a diagnostic tool for the outcome of patients admitted with acute pulmonary embolism (PE) and the correlations with other parameters. Methods: We evaluated 116 patients who were admitted for PE in a respiratory medicine department. PE was confirmed with computed tomography pulmonary angiography. Outcomes evaluated were hospitalization duration, mortality or thrombolysis and a composite endpoint (defined as mortality or thrombolysis). Patients were assessed for PE severity with the PE Severity Index (PESI) and the European Society of Cardiology (ESC) 2019 risk stratification. Results: The median (interquartile range) UA/Cr level was 7.59 (6.3–9.3). UA/Cr was significantly associated with PESI (p < 0.001), simplified PESI (p = 0.019), and ESC 2019 risk stratification (p < 0.001). The area under the curve (AUC) for prediction of 30-day mortality by UA/Cr was 0.793 (95% CI: 0.667–0.918). UA/Cr levels ≥7.64 showed 87% specificity and 94% negative predictive value for mortality. In multivariable analysis UA/Cr was an independent predictor of mortality (HR (95% CI): 1.620 (1.245–2.108), p < 0.001) and composite outcome (HR (95% CI): 1.521 (1.211–1.908), p < 0.001). Patients with elevated UA/Cr levels (≥7.64) had longer hospitalization (median (IQR) 7 (5–11) vs. 6 (5–8) days, p = 0.006)), higher mortality (27.3% vs. 3.2%, p = 0.001) and worse composite endpoint (32.7% vs. 3.4%, p < 0.001). Conclusion: Serum UA/Cr ratio levels at the time of PE diagnosis are associated with disease severity and risk stratification, and may be a useful biomarker for the identification of patients at risk of adverse outcomes.

Prognostic Value of Oral Epstein–Barr Virus DNA Load in Locoregionally Advanced Nasopharyngeal Carcinoma

Background: Plasma Epstein–Barr virus (EBV) DNA load has been widely used for nasopharyngeal carcinoma (NPC) prognostic risk stratification. However, oral EBV DNA load, a non-invasive biomarker that reflects the EBV lytic replication activity, has not been evaluated for its prognostic value in NPC yet.Methods: A total number of 1,194 locoregionally advanced NPC (LA-NPC) patients from south China were included from a prospective observational cohort (GARTC) with a median follow-up of 107.3 months. Pretreatment or mid-treatment mouthwashes were collected for EBV DNA detection by quantitative polymerase chain reaction (qPCR). The difference of pre- and mid-treatment oral EBV DNA load was tested by the Wilcoxon signed-rank test. The associations of oral EBV DNA load with overall survival (OS), progression-free survival (PFS), distant metastasis–free survival (DMFS), and locoregional relapse-free survival (LRFS) were assessed using the log-rank test and multivariate Cox regression.Results: The high level of the oral EBV DNA load (&gt;2,100 copies/mL) was independently associated with worse OS (HR = 1.45, 95% CI: 1.20–1.74, p &lt; 0.001), PFS (HR = 1.38, 95% CI: 1.16–1.65, p &lt; 0.001), DMFS (HR = 1.66, 95% CI: 1.25–2.21, p = 0.001), and LRFS (HR = 1.43, 95% CI: 1.05–1.96, p = 0.023). Similar and robust associations between oral EBV DNA load and prognosis were observed for patients in both the pretreatment and mid-treatment stages. The detection rate (71.7 vs. 48.6%, p &lt; 0.001) and the median load of oral EBV DNA (13,368 vs. 382 copies/mL, p &lt; 0.001) for patients in the pretreatment stage were significantly higher than those in the mid-treatment stage. The combination of the oral EBV DNA load and TNM staging provided a more precise risk stratification for the LA-NPC patients.Conclusion: Oral EBV DNA load was an alternative non-invasive predictor of prognosis and may facilitate risk stratification for the LA-NPC patients.