Citations

The eye is prone to various forms of afflictions, either as a manifestation of primary ocular disease or part of systemic disease, including the cardiovascular system. A thorough cardiovascular examination should include a brief ocular assessment. Hypertension and diabetes, for example, would present with retinopathy and dyslipidaemia would present with corneal arcus. Multisystem autoimmune diseases, such as Graves’ disease, rheumatoid arthritis and sarcoidosis, would present with proptosis, episcleritis and scleritis, respectively. Myasthenia gravis, while primarily a neuromuscular disease, presents with fatigable ptosis and is associated with Takotsubo cardiomyopathy and giant cell myocarditis. Connective tissue diseases such as Marfan syndrome, which commonly presents with aortic root dilatation, would be associated with ectopia lentis and myopia. Wilson’s disease, which is associated with arrhythmias and cardiomyopathies, would present usually with the characteristic Kayser-Fleischer rings. Rarer diseases, such as Fabry disease, would be accompanied by ocular signs such as cornea verticillata and such cardiac manifestations include cardiac hypertrophy as well as arrhythmias. This review examines the interplay between the eye and the cardiovascular system and emphasises the use of conventional and emerging tools to improve diagnosis, management and prognostication of patients.

In this study, we investigated whether radiomics features from pre-treatment positron emission tomography (PET) images could be used to predict disease progression in patients with HPV-positive oropharyngeal cancer treated with definitive proton or x-ray radiotherapy. Machine learning models were built using a dataset from Mayo Clinic, Rochester, Minnesota (n = 72) and tested on a dataset from Mayo Clinic, Phoenix, Arizona (n = 22). A total of 71 clinical and radiomics features were considered. The Mann–Whitney U test was used to identify the top 2 clinical and top 20 radiomics features that were significantly different between progression and progression-free patients. Two dimensionality reduction methods were used to define two feature sets (manually filtered or machine-driven). A forward feature selection scheme was conducted on each feature set to build models of increased complexity (number of input features from 1 to 6) and evaluate model robustness and overfitting. The machine-driven features had superior performance and were less prone to overfitting compared to the manually filtered features. The four-variable Gaussian Naïve Bayes model using the ‘Radiation Type’ clinical feature and three machine-driven features achieved a training accuracy of 79% and testing accuracy of 77%. These results demonstrate that radiomics features can provide risk stratification beyond HPV-status to formulate individualized treatment and follow-up strategies.

The Centers for Medicare & Medicaid Services (CMS) recommend covering blood-based tests meeting proposed minimum performance thresholds for colorectal cancer (CRC) screening. Outcomes were compared between currently available stool-based screening tests and a hypothetical blood-based test meeting CMS minimum thresholds. Using the Colorectal Cancer and Adenoma Incidence and Mortality Microsimulation Model (CRC-AIM), outcomes were simulated for average-risk individuals screened between ages 45 and 75 years with triennial multitarget stool DNA (mt-sDNA), annual fecal immunochemical test (FIT), and annual fecal occult blood test (FOBT). Per CMS guidance, blood-based CRC screening was modeled triennially, with 74% CRC sensitivity and 90% specificity. Although not specified by CMS, adenoma sensitivity was set between 10% and 20%. Published adenoma and CRC sensitivity and specificity were used for stool-based tests. Adherence was set at (1) 100%, (2) 30%–70%, in 10% increments, and (3) real-world rates for stool-based tests (mt-sDNA = 65.6%; FIT = 42.6%; FOBT = 34.4%). Assuming perfect adherence, a blood-based test produced ≥19 lower life-years gained (LYG) than stool-based strategies. At the best-case scenario for blood-based tests (100% adherence and 20% adenoma sensitivity), mt-sDNA at real-world adherence achieved more LYG (287.2 vs. 297.1, respectively) with 14% fewer colonoscopies. At 100% blood-based test adherence and real-world mt-sDNA and FIT adherence, the blood-based test would require advanced adenoma sensitivity of 30% to reach the LYG of mt-sDNA (297.1) and ∼15% sensitivity to reach the LYG of FIT (258.9). This model suggests that blood-based tests with CMS minimally acceptable CRC sensitivity and low advanced adenoma sensitivity will frequently yield inferior outcomes to stool-based testing across a wide range of adherence assumptions.

Objectives Machine learning (ML)–based emulators improve the calibration of decision-analytical models, but their performance in complex microsimulation models is yet to be determined. Methods We demonstrated the use of an ML-based emulator with the Colorectal Cancer (CRC)-Adenoma Incidence and Mortality (CRC-AIM) model, which includes 23 unknown natural history input parameters to replicate the CRC epidemiology in the United States. We first generated 15,000 input combinations and ran the CRC-AIM model to evaluate CRC incidence, adenoma size distribution, and the percentage of small adenoma detected by colonoscopy. We then used this data set to train several ML algorithms, including deep neural network (DNN), random forest, and several gradient boosting variants (i.e., XGBoost, LightGBM, CatBoost) and compared their performance. We evaluated 10 million potential input combinations using the selected emulator and examined input combinations that best estimated observed calibration targets. Furthermore, we cross-validated outcomes generated by the CRC-AIM model with those made by CISNET models. The calibrated CRC-AIM model was externally validated using the United Kingdom Flexible Sigmoidoscopy Screening Trial (UKFSST). Results The DNN with proper preprocessing outperformed other tested ML algorithms and successfully predicted all 8 outcomes for different input combinations. It took 473 s for the trained DNN to predict outcomes for 10 million inputs, which would have required 190 CPU-years without our DNN. The overall calibration process took 104 CPU-days, which included building the data set, training, selecting, and hyperparameter tuning of the ML algorithms. While 7 input combinations had acceptable fit to the targets, a combination that best fits all outcomes was selected as the best vector. Almost all of the predictions made by the best vector laid within those from the CISNET models, demonstrating CRC-AIM’s cross-model validity. Similarly, CRC-AIM accurately predicted the hazard ratios of CRC incidence and mortality as reported by UKFSST, demonstrating its external validity. Examination of the impact of calibration targets suggested that the selection of the calibration target had a substantial impact on model outcomes in terms of life-year gains with screening. Conclusions Emulators such as a DNN that is meticulously selected and trained can substantially reduce the computational burden of calibrating complex microsimulation models. Highlights Calibrating a microsimulation model, a process to find unobservable parameters so that the model fits observed data, is computationally complex. We used a deep neural network model, a popular machine learning algorithm, to calibrate the Colorectal Cancer Adenoma Incidence and Mortality (CRC-AIM) model. We demonstrated that our approach provides an efficient and accurate method to significantly speed up calibration in microsimulation models. The calibration process successfully provided cross-model validation of CRC-AIM against 3 established CISNET models and also externally validated against a randomized controlled trial.

Clinical outcomes of deceased donor kidney transplants coming from diabetic donors currently remain inconsistent, possibly due to high heterogeneities in this population. Our study aimed to cluster recipients of diabetic deceased donor kidney transplants using an unsupervised machine learning approach in order to identify subgroups with high risk of inferior outcomes and potential variables associated with these outcomes. Consensus cluster analysis was performed based on recipient-, donor-, and transplant-related characteristics in 7876 recipients of diabetic deceased donor kidney transplants from 2010 to 2019 in the OPTN/UNOS database. We determined the important characteristics of each assigned cluster and compared the post-transplant outcomes between the clusters. Consensus cluster analysis identified three clinically distinct clusters. Recipients in cluster 1 (n = 2903) were characterized by oldest age (64 ± 8 years), highest rate of comorbid diabetes mellitus (55%). They were more likely to receive kidney allografts from donors that were older (58 ± 6.3 years), had hypertension (89%), met expanded criteria donor (ECD) status (78%), had a high rate of cerebrovascular death (63%), and carried a high kidney donor profile index (KDPI). Recipients in cluster 2 (n = 687) were younger (49 ± 13 years) and all were re-transplant patients with higher panel reactive antibodies (PRA) (88 [IQR 46, 98]) who received kidneys from younger (44 ± 11 years), non-ECD deceased donors (88%) with low numbers of HLA mismatch (4 [IQR 2, 5]). The cluster 3 cohort was characterized by first-time kidney transplant recipients (100%) who received kidney allografts from younger (42 ± 11 years), non-ECD deceased donors (98%). Compared to cluster 3, cluster 1 had higher incidence of primary non-function, delayed graft function, patient death and death-censored graft failure, whereas cluster 2 had higher incidence of delayed graft function and death-censored graft failure but comparable primary non-function and patient death. An unsupervised machine learning approach characterized diabetic donor kidney transplant patients into three clinically distinct clusters with differing outcomes. Our data highlight opportunities to improve utilization of high KDPI kidneys coming from diabetic donors in recipients with survival-limiting comorbidities such as those observed in cluster 1.

AbstractContextInhibition of the neonatal fragment crystallizable receptor (FcRn) reduces pathogenic thyrotropin receptor antibodies (TSH-R-Ab) that drive pathology in thyroid eye disease (TED).ObjectiveWe report the first clinical studies of an FcRn inhibitor, batoclimab, in TED.DesignProof-of-concept (POC) and randomized, double-blind placebo-controlled trials.SettingMulticenter.ParticipantsPatients with moderate-to-severe, active TED.InterventionIn the POC trial, patients received weekly subcutaneous injections of batoclimab 680 mg for 2 weeks, followed by 340 mg for 4 weeks. In the double-blind trial, patients were randomized 2:2:1:2 to weekly batoclimab (680 mg, 340 mg, 255 mg) or placebo for 12 weeks.Main OutcomeChange from baseline in serum anti-TSH-R-Ab and total IgG (POC); 12-week proptosis response (randomized trial).ResultsThe randomized trial was terminated because of an unanticipated increase in serum cholesterol; therefore, data from 65 of the planned 77 patients were analyzed. Both trials showed marked decreases in pathogenic anti-TSH-R-Ab and total IgG serum levels (P < .001) with batoclimab. In the randomized trial, there was no statistically significant difference with batoclimab vs placebo in proptosis response at 12 weeks, although significant differences were observed at several earlier timepoints. In addition, orbital muscle volume decreased (P < .03) at 12 weeks, whereas quality of life (appearance subscale) improved (P < .03) at 19 weeks in the 680-mg group. Batoclimab was generally well tolerated, with albumin reductions and increases in lipids that reversed upon discontinuation.ConclusionsThese results provide insight into the efficacy and safety of batoclimab and support its further investigation as a potential therapy for TED.

AbstractObjectivesAlthough hemispheric surgeries are among the most effective procedures for drug‐resistant epilepsy (DRE) in the pediatric population, there is a large variability in seizure outcomes at the group level. A recently developed HOPS score provides individualized estimation of likelihood of seizure freedom to complement clinical judgement. The objective of this study was to develop a freely accessible online calculator that accurately predicts the probability of seizure freedom for any patient at 1‐, 2‐, and 5‐years post‐hemispherectomy.MethodsRetrospective data of all pediatric patients with DRE and seizure outcome data from the original Hemispherectomy Outcome Prediction Scale (HOPS) study were included. The primary outcome of interest was time‐to‐seizure recurrence. A multivariate Cox proportional‐hazards regression model was developed to predict the likelihood of post‐hemispheric surgery seizure freedom at three time points (1‐, 2‐ and 5‐ years) based on a combination of variables identified by clinical judgment and inferential statistics predictive of the primary outcome. The final model from this study was encoded in a publicly accessible online calculator on the International Network for Epilepsy Surgery and Treatment (iNEST) website (https://hops‐calculator.com/).ResultsThe selected variables for inclusion in the final model included the five original HOPS variables (age at seizure onset, etiologic substrate, seizure semiology, prior non‐hemispheric resective surgery, and contralateral fluorodeoxyglucose–positron emission tomography [FDG‐PET] hypometabolism) and three additional variables (age at surgery, history of infantile spasms, and magnetic resonance imaging [MRI] lesion). Predictors of shorter time‐to‐seizure recurrence included younger age at seizure onset, prior resective surgery, generalized seizure semiology, FDG‐PET hypometabolism contralateral to the side of surgery, contralateral MRI lesion, non‐lesional MRI, non‐stroke etiologies, and a history of infantile spasms. The area under the curve (AUC) of the final model was 73.0%.SignificanceOnline calculators are useful, cost‐free tools that can assist physicians in risk estimation and inform joint decision‐making processes with patients and families, potentially leading to greater satisfaction. Although the HOPS data was validated in the original analysis, the authors encourage external validation of this new calculator.

Importance Lensectomy with primary intraocular lens (IOL) implantation is often used in the management of nontraumatic pediatric cataract, but long-term data evaluating the association of age and IOL location with the incidence of complications are limited. Objective To describe the incidence of complications and additional eye surgeries through 5 years following pediatric lensectomy with primary IOL implantation and association with age at surgery and IOL location. Design, Setting, and Participants This prospective cohort study used Pediatric Eye Disease Investigator Group cataract registry data from 61 institution- and community-based practices over 3 years (June 2012 to July 2015). Participants were children younger than 13 years without baseline glaucoma who had primary IOL implantation (345 bilateral and 264 unilateral) for nontraumatic cataract. Data analysis was performed between September 2021 and January 2023. Exposures Lensectomy with primary IOL implantation. Main Outcome and Measures Five-year cumulative incidence of complications by age at surgery (<2 years, 2 to <4 years, 4 to <7 years, and 7 to <13 years) and by IOL location (sulcus vs capsular bag) were estimated using Cox proportional hazards models. Results The cohort included 609 eyes from 491 children (mean [SD] age, 5.6 [3.3] years; 261 [53%] male and 230 [47%] female). Following cataract extraction with primary IOL implantation, a frequent complication was surgery for visual axis opacification (VAO) (cumulative incidence, 32%; 95% CI, 27%-36%). Cumulative incidence was lower with anterior vitrectomy at the time of IOL placement (12%; 95% CI, 8%-16%) vs without (58%; 95% CI, 50%-65%), and the risk of undergoing surgery for VAO was associated with not performing anterior vitrectomy (hazard ratio [HR], 6.19; 95% CI, 3.70-10.34; P < .001). After adjusting for anterior vitrectomy at lens surgery, there were no differences in incidence of surgery for VAO by age at surgery (<2 years, HR, 1.35 [95% CI, 0.63-2.87], 2 to <4 years, HR, 0.86 [95% CI, 0.44-1.68], 4 to <7 years, HR, 1.06 [95% CI, 0.72-1.56]; P = .74) or by capsular bag vs sulcus IOL fixation (HR, 1.22; 95% CI, 0.36-4.17; P = .75). Cumulative incidence of glaucoma plus glaucoma suspect by 5 years was 7% (95% CI, 4%-9%), which did not differ by age after controlling for IOL location and laterality. Conclusions and Relevance In this cohort study, a frequent complication following pediatric lensectomy with primary IOL was surgery for VAO, which was associated with primary anterior vitrectomy not being performed but was not associated with age at surgery or IOL location. The risk of glaucoma development across all ages at surgery suggests a need for long-term monitoring.

Abstract Bowel sounds have been previously used to study intestinal motility and overall digestive health in various clinical settings. However, the blurred definition of bowel sounds and their subtypes, limited resources for interpretation, poor sensitivity, and low positive predictive value led to their restricted utility. Recent advances in artificial intelligence and machine learning have steered interest in developing unique tools using the phonoenterogram to analyze diverse bowel sounds. In our study, bowel sounds were recorded from eight healthy volunteers using the Eko Duo stethoscope. A novel deep-learning algorithm was designed to classify the recordings into baseline or prominent bowel sounds. A total of 11,210 data points (5,605 balanced sounds) were used to train and test the model to yield an accuracy of 0.895, a precision of 0.890, and a recall of 0.854 reflecting successful segregation of these sounds into respective groups. More extensive studies enrolling healthy and diseased subjects with a device specifically tailored to record bowel sounds are needed to generalize these results and determine their application in the patient population.