Machine learning techniques to predict the risk of developing diabetic nephropathy: a literature review.

Purpose: Diabetes is a major public health challenge with widespread prevalence, often leading to complications such as Diabetic Nephropathy (DN)-a chronic condition that progressively impairs kidney function. In this context, it is important to evaluate if Machine learning models can exploit the inherent temporal factor in clinical data to predict the risk of developing DN faster and more accurately than current clinical models. Methods: Three different databases were used for this literature review: Scopus, Web of Science, and PubMed. Only articles written in English and published between January 2015 and December 2022 were included. Results: We included 11 studies, from which we discuss a number of algorithms capable of extracting knowledge from clinical data, incorporating dynamic aspects in patient assessment, and exploring their evolution over time. We also present a comparison of the different approaches, their performance, advantages, disadvantages, interpretation, and the value that the time factor can bring to a more successful prediction of diabetic nephropathy. Conclusion: Our analysis showed that some studies ignored the temporal factor, while others partially exploited it. Greater use of the temporal aspect inherent in Electronic Health Records (EHR) data, together with the integration of omics data, could lead to the development of more reliable and powerful predictive models.

Machine learning models' assessment: trust and performance.

The common black box nature of machine learning models is an obstacle to their application in health care context. Their widespread application is limited by a significant "lack of trust." So, the main goal of this work is the development of an evaluation approach that can assess, simultaneously, trust and performance. Trust assessment is based on (i) model robustness (stability assessment), (ii) confidence (95% CI of geometric mean), and (iii) interpretability (comparison of respective features ranking with clinical evidence). Performance is assessed through geometric mean. For validation, in patients' stratification in cardiovascular risk assessment, a Portuguese dataset (N=1544) was applied. Five different models were compared: (i) GRACE score, the most common risk assessment tool in Portugal for patients with acute coronary syndrome; (ii) logistic regression; (iii) Naïve Bayes; (iv) decision trees; and (v) rule-based approach, previously developed by this team. The obtained results confirm that the simultaneous assessment of trust and performance can be successfully implemented. The rule-based approach seems to have potential for clinical application. It provides a high level of trust in the respective operation while outperformed the GRACE model's performance, enhancing the required physicians' acceptance. This may increase the possibility to effectively aid the clinical decision.

Rationale and design of the iCORONARY trial: improving the cost-effectiveness of coronary artery disease diagnosis.

BACKGROUND: In patients with stable coronary artery disease (CAD), revascularisation decisions are based mainly on the visual grading of the severity of coronary stenosis on invasive coronary angiography (ICA). However, invasive fractional flow reserve (FFR) is the current standard to determine the haemodynamic significance of coronary stenosis. Non-invasive and less-invasive imaging techniques such as computed-tomography-derived FFR (FFR-CT) and angiography-derived FFR (QFR) combine both anatomical and functional information in complex algorithms to calculate FFR. TRIAL DESIGN: The iCORONARY trial is a prospective, multicentre, non-inferiority randomised controlled trial (RCT) with a blinded endpoint evaluation. It investigates the costs, effects and outcomes of different diagnostic strategies to evaluate the presence of CAD and the need for revascularisation in patients with stable angina pectoris who undergo coronary computed tomography angiography. Those with a Coronary Artery Disease-Reporting and Data System (CAD-RADS) score between 0-2 and 5 will be included in a prospective registry, whereas patients with CAD-RADS 3 or 4A will be enrolled in the RCT. The RCT consists of three randomised groups: (1) FFR-CT-guided strategy, (2) QFR-guided strategy or (3) standard of care including ICA and invasive pressure measurements for all intermediate stenoses. The primary endpoint will be the occurrence of major adverse cardiac events (death, myocardial infarction and repeat revascularisation) at 1 year. CLINICALTRIALS: gov-identifier: NCT04939207. CONCLUSION: The iCORONARY trial will assess whether a strategy of FFR-CT or QFR is non-inferior to invasive angiography to guide the need for revascularisation in patients with stable CAD. Non-inferiority to the standard of care implies that these techniques are attractive, less-invasive alternatives to current diagnostic pathways.

An interpretable machine learning approach to estimate the influence of inflammation biomarkers on cardiovascular risk assessment.

BACKGROUND AND OBJECTIVE: Cardiovascular disease has a huge impact on health care services, originating unsustainable costs at clinical, social, and economic levels. In this context, patients' risk stratification tools are central to support clinical decisions contributing to the implementation of effective preventive health care. Although useful, these tools present some limitations, in particular, some lack of performance as well as the impossibility to consider new risk factors potentially important in the prognosis of severe cardiac events. Moreover, the actual use of these tools in the daily practice requires the physicians' trust. The main goal of this work addresses these two issues: (i) evaluate the importance of inflammation biomarkers when combined with a risk assessment tool; (ii) incorporation of personalization and interpretability as key elements of that assessment. METHODS: Firstly, machine learning based models were created to assess the potential of the inflammation biomarkers applied in secondary prevention, namely in the prediction of the six month risk of death/myocardial infarction. Then, an approach based on three main phases was created: (i) set of interpretable rules supported by clinical evidence; (ii) selection based on a machine learning classifier able to identify for a given patient the most suitable subset of rules; (iii) an ensemble scheme combining the previous subset of rules in the estimation of the patient cardiovascular risk. All the results were statistically validated (t-test, Wilcoxon-signed rank test) according to a previous verification of data normality (Shapiro-Wilk). RESULTS: The proposed methodology was applied to a real acute coronary syndrome patients dataset (N = 1544) from the Cardiology Unit of Coimbra Hospital and Universitary centre. The first assessment was based on the GRACE tool and a Random Forest classifier, the incorporation of inflammation biomarkers achieved SE=0.83; SP=0.84 whereas the original GRACE risk factors reached SE=0.75; SP=0.85. In the second phase, the proposed approach with inflammation biomarkers achieved SE=0.763 and SP=0.778. CONCLUSIONS: This approach confirms the potential of combining inflammation markers with the GRACE score, increasing SE and SP, when compared with the original GRACE. Additionally, it assures interpretability and personalization, which are critical issues to allow its application in the daily clinical practice.

GLIM-based malnutrition, protein intake and diet quality in preprocedural Transcatheter Aortic Valve Implantation (TAVI) patients.

BACKGROUND & AIMS: Diagnosed prevalence of malnutrition and dietary intake are currently unknown in patients with severe aortic stenosis planned to undergo Transcatheter Aortic Valve Implantation (TAVI). This study describes the preprocedural nutritional status, protein intake and diet quality. METHODS: Consecutive preprocedural TAVI patients were asked to participate in this explorative study. Nutritional status was diagnosed with the global leadership initiative on malnutrition (GLIM) criteria. Preprocedural protein intake and diet quality were assessed with a three-day dietary record. To increase the record's validity, a researcher visited the participants at their homes to confirm the record. Protein intake was reported as an average intake of three days and diet quality was assessed using the Dutch dietary guidelines (score range 0-14, 1 point for adherence to each guideline). RESULTS: Of the included patients (n = 50, median age 80 ± 5, 56% male) 32% (n = 16) were diagnosed with malnutrition. Patients diagnosed with malnutrition had a lower protein intake (1.02 ± 0.28 g/kg/day vs 0.87 ± 0.21 g/kg/day, p = 0.04). The difference in protein intake mainly took place during lunch (20 ± 13 g/kg vs 13 ± 7 g/kg, p = 0.03). Patients adhered to 6.4 ± 2.2 out of 14 dietary guidelines. Adherence to the guideline of whole grains and ratio of whole grains was lower in the group of patients with malnutrition than in patients with normal nutritional status (both 62% vs 19%, p = 0.01). In a multivariate analysis diabetes mellitus was found as an independent predictor of malnutrition. CONCLUSION: Prevalence of malnutrition among TAVI patients is very high up to 32%. Patients with malnutrition had lower protein and whole grain intake than patients with normal nutritional status. Furthermore, we found diabetes mellitus as independent predictor of malnutrition. Nutrition interventions in this older patient group are highly warranted.

Machine learning-based prediction of insufficient contrast enhancement in coronary computed tomography angiography.

OBJECTIVES: Patient-tailored contrast delivery protocols strongly reduce the total iodine load and in general improve image quality in CT coronary angiography (CTCA). We aim to use machine learning to predict cases with insufficient contrast enhancement and to identify parameters with the highest predictive value. METHODS: Machine learning models were developed using data from 1,447 CTs. We included patient features, imaging settings, and test bolus features. The models were trained to predict CTCA images with a mean attenuation value in the ascending aorta below 400 HU. The accuracy was assessed by the area under the receiver operating characteristic (AUROC) and precision-recall curves (AUPRC). Shapley Additive exPlanations was used to assess the impact of features on the prediction of insufficient contrast enhancement. RESULTS: A total of 399 out of 1,447 scans revealed attenuation values in the ascending aorta below 400 HU. The best model trained using only patient features and CT settings achieved an AUROC of 0.78 (95% CI: 0.73-0.83) and AUPRC of 0.65 (95% CI: 0.58-0.71). With the inclusion of the test bolus features, it achieved an AUROC of 0.84 (95% CI: 0.81-0.87), an AUPRC of 0.71 (95% CI: 0.66-0.76), and a sensitivity of 0.66 and specificity of 0.88. The test bolus' peak height was the feature that impacted low attenuation prediction most. CONCLUSION: Prediction of insufficient contrast enhancement in CT coronary angiography scans can be achieved using machine learning models. Our experiments suggest that test bolus features are strongly predictive of low attenuation values and can be used to further improve patient-specific contrast delivery protocols. KEY POINTS: • Prediction of insufficient contrast enhancement in CT coronary angiography scans can be achieved using machine learning models. • The peak height of the test bolus curve is the most impacting feature for the best performing model.

Routine reporting of grey-white matter differentiation in early brain computed tomography in comatose patients after cardiac arrest: A substudy of the COACT trial.

AIM: A multimodal approach is advised for neurological prognostication in comatose patients after out-of-hospital cardiac arrest (OHCA). Grey-white matter differentiation (grey-white ratio, GWR) obtained from a brain CT scan performed < 24 hours after return of circulation can be part of this approach. The aims of this study were to investigate the frequency and method of reporting the GWR in brain CT scan reports and their association with outcome. METHODS: This is a post-hoc descriptive analysis of the COACT trial. The primary endpoint was the reporting of GWR by the radiologist. Secondary endpoints were APACHE IV score, Cerebral Performance Categories at discharge and 90-day follow-up, Glasgow Coma Scale at discharge, GWR-stratified 1-year survival, and RAND-36 stratified by normal versus abnormal GWR. Associations were analysed using multivariable analysis. RESULTS: A total of 427 OHCA patients were included in this study, 234 (55%) of whom underwent a brain CT scan within 24 hours after ROSC. Median time between arrest and initial CT scan was 12 hours. In 195 patients (83%), the GWR was described in the reports, but always expressed qualitatively. The GWR was deemed abnormal in 57 (29%) CT scans. No differences were found in secondary endpoints between the two groups. CONCLUSION: GWR was frequently described in CT scan reports. Early abnormal GWR, as assessed qualitatively by a radiologist within 24 hours after ROSC, was a poor predictor of neurological prognosis.

Laser induced enhanced coupling between photons and squeezed magnons in antiferromagnets.

In this paper we consider a honeycomb antiferromagnet subject to an external laser field. Obtaining a time-independent effective Hamiltonian, we find that the external laser renormalizes the exchange interaction between the in-plane components of the spin-operators, and induces a synthetic Dzyaloshinskii-Moria interaction (DMI) between second neighbors. The former allows the control of the magnon dispersion's bandwidth and the latter breaks time-reversal symmetry inducing non-reciprocity in momentum space. The eigen-excitations of the system correspond to squeezed magnons whose squeezing parameters depend on the properties of the laser. When studying how these spin excitations couple with cavity photons, we obtain a coupling strength which can be enhanced by an order of magnitude via careful tuning of the laser's intensity, when compared to the case where the laser is absent. The transmission plots through the cavity are presented, allowing the mapping of the magnons' dispersion relation.

A Fundamental Study on Compression Properties and Strain Rate Sensitivity of Spray-Dried Amorphous Solid Dispersions.

Amorphous solid dispersions (ASDs) are a proven method of improving the solubility and bioavailability of poorly soluble compounds. Immediate release tablets are frequently used as final dosage form for ASDs. Increasing tableting process throughput during clinical development requires using larger, faster tablet presses which subject materials to higher strain rate. Many pharmaceutical materials show strain rate sensitivity, i.e., yield pressure sensitivity to compression speed. Currently, there is only scattered information available in scientific literature on how ASDs behave under different tablet compression speeds. The purpose of this study was to examine spray-dried ASDs' sensitivity to strain rate under compression in a comprehensive study. We also investigated the drivers for such a strain sensitive behavior. A set of sample spray-dried powders, selected for their range of properties, were compressed using a simulated Korsch XL100 profile at 3 and 30 RPM and V-profile at 0.1 and 300 mm/s on a Phoenix compaction simulator. The sample set included samples with varying API content (0-50% w/w), stabilizing polymer (HPMC, HPMC-AS, PVP-VA), particle size, and bulk densities, produced on spray driers from lab to commercial scale. We identified that all ASD samples showed plastic flow and deformation behavior and form robust compacts at slow compression speeds. At high speed, tablet defects occurred. The strain rate sensitivity observed in this study was comparable or slightly superior to that observed for microcrystalline cellulose, known to be a mildly strain rate-sensitive material. We showed that compression speed is a critical process parameter for ASD-containing tablets.

Predictive value of DNA repair gene expression for response to neoadjuvant chemotherapy in breast cancer.

Genome-wide analysis using microarrays has revolutionized breast cancer (BC) research. A substantial body of evidence supports the clinical utility of the 21-gene assay (Oncotype DX) and 70-gene assay (MammaPrint) to predict BC recurrence and the magnitude of benefit from chemotherapy. However, there is currently no genetic tool able to predict chemosensitivity and chemoresistance to neoadjuvant chemotherapy (NACT) during BC treatment. In this study, we explored the predictive value of DNA repair gene expression in the neoadjuvant setting. We selected 98 patients with BC treated with NACT. We assessed DNA repair expression in 98 formalin-fixed, paraffin-embedded core biopsy fragments used at diagnosis and in 32 formalin-fixed, paraffin-embedded post-NACT residual tumors using quantitative reverse transcription-polymerase chain reaction. The following genes were selected: BRCA1, PALB2, RAD51C, BRCA2, ATM, FANCA, MSH2, XPA, ERCC1, PARP1, and SNM1. Of 98 patients, 33 (33.7%) achieved pathologic complete response (pCR). The DNA expression of 2 genes assessed in pre-NACT biopsies (PALB2 and ERCC1) was lower in pCR than in non-pCR patients (P=0.005 and P=0.009, respectively). There was no correlation between molecular subtype and expression of DNA repair genes. The genes BRCA2 (P=0.009), ATM (P=0.004), FANCA (P=0.001), and PARP1 (P=0.011) showed a lower expression in post-NACT residual tumor samples (n=32) than in pre-NACT biopsy samples (n=98). The expression of 2 genes (PALB2 and ERCC1) was lower in pCR patients. These alterations in DNA repair could be considered suitable targets for cancer therapy.