Application of Machine Learning to Ranking Predictors of Anti-VEGF Response.

Age-related macular degeneration (AMD) is a heterogeneous disease affecting the macula of individuals and is a cause of irreversible vision loss. Patients with neovascular AMD (nAMD) are candidates for the anti-vascular endothelial growth factor (anti-VEGF) treatment, designed to regress the growth of abnormal blood vessels in the eye. Some patients fail to maintain vision despite treatment. This study aimed to develop a prediction model based on features weighted in order of importance with respect to their impact on visual acuity (VA). Evaluations included an assessment of clinical, lifestyle, and demographic factors from patients that were treated over a period of two years. The methods included mixed-effects and relative importance modelling, and models were tested against model selection criteria, diagnostic and assumption checks, and forecasting errors. The most important predictors of an anti-VEGF response were the baseline VA of the treated eye, the time (in weeks), treatment quantity, and the treated eye. The model also ranked the impact of other variables, such as intra-retinal fluid, haemorrhage, pigment epithelium detachment, treatment drug, baseline VA of the untreated eye, and various lifestyle and demographic factors. The results identified variables that could be targeted for further investigation in support of personalised treatments based on patient data.

Progression of Geographic Atrophy: Epistemic Uncertainties Affecting Mathematical Models and Machine Learning.

Purpose: The purpose of this study was to identify a taxonomy of epistemic uncertainties that affect results for geographic atrophy (GA) assessment and progression. Methods: An important source of variability is called "epistemic uncertainty," which is due to incomplete system knowledge (i.e. limitations in measurement devices, artifacts, and human subjective evaluation, including annotation errors). In this study, different epistemic uncertainties affecting the analysis of GA were identified and organized into a taxonomy. The uncertainties were discussed and analyzed, and an example was provided in the case of model structure uncertainty by characterizing progression of GA by mathematical modelling and machine learning. It was hypothesized that GA growth follows a logistic (sigmoidal) function. Using case studies, the GA growth data were used to test the sigmoidal hypothesis. Results: Epistemic uncertainties were identified, including measurement error (imperfect outcomes from measuring tools), subjective judgment (grading affected by grader's vision and experience), model input uncertainties (data corruption or entry errors), and model structure uncertainties (elucidating the right progression pattern). Using GA growth data from case studies, it was demonstrated that GA growth can be represented by a sigmoidal function, where growth eventually approaches an upper limit. Conclusion: Epistemic uncertainties contribute to errors in study results and are reducible if identified and addressed. By prior identification of epistemic uncertainties, it is possible to (a) quantify uncertainty not accounted for by natural statistical variability, and (b) reduce the presence of these uncertainties in future studies. Translational Relevance: Lowering epistemic uncertainty will reduce experimental error, improve consistency and reproducibility, and increase confidence in diagnostics.

Deep Learning Applied to Automated Segmentation of Geographic Atrophy in Fundus Autofluorescence Images.

Purpose: This study describes the development of a deep learning algorithm based on the U-Net architecture for automated segmentation of geographic atrophy (GA) lesions in fundus autofluorescence (FAF) images. Methods: Image preprocessing and normalization by modified adaptive histogram equalization were used for image standardization to improve effectiveness of deep learning. A U-Net-based deep learning algorithm was developed and trained and tested by fivefold cross-validation using FAF images from clinical datasets. The following metrics were used for evaluating the performance for lesion segmentation in GA: dice similarity coefficient (DSC), DSC loss, sensitivity, specificity, mean absolute error (MAE), accuracy, recall, and precision. Results: In total, 702 FAF images from 51 patients were analyzed. After fivefold cross-validation for lesion segmentation, the average training and validation scores were found for the most important metric, DSC (0.9874 and 0.9779), for accuracy (0.9912 and 0.9815), for sensitivity (0.9955 and 0.9928), and for specificity (0.8686 and 0.7261). Scores for testing were all similar to the validation scores. The algorithm segmented GA lesions six times more quickly than human performance. Conclusions: The deep learning algorithm can be implemented using clinical data with a very high level of performance for lesion segmentation. Automation of diagnostics for GA assessment has the potential to provide savings with respect to patient visit duration, operational cost and measurement reliability in routine GA assessments. Translational Relevance: A deep learning algorithm based on the U-Net architecture and image preprocessing appears to be suitable for automated segmentation of GA lesions on clinical data, producing fast and accurate results.

Model Structure Uncertainty in the Characterization and Growth of Geographic Atrophy.

Purpose: To identify the most suitable model for assessing the rate of growth of total geographic atrophy (GA) by analysis of model structure uncertainty. Methods: Model structure uncertainty refers to unexplained variability arising from the choice of mathematical model and represents an example of epistemic uncertainty. In this study, we quantified this uncertainty to help identify a model most representative of GA progression. Fundus autofluorescence (FAF) images and GA progression data (i.e., total GA area estimation at each presentation) were acquired using Spectralis HRA+OCT instrumentation and RegionFinder software. Six regression models were evaluated. Models were compared using various statistical tests, [i.e., coefficient of determination (r2), uncertainty metric (U), and test of significance for the correlation coefficient, r], as well as adherence to expected physical and clinical assumptions of GA growth. Results: Analysis was carried out for 81 GA-affected eyes, 531 FAF images (range: 3-17 images per eye), over median of 57 months (IQR: 42, 74), with a mean baseline lesion size of 2.62 ± 4.49 mm2 (range: 0.11-20.69 mm2). The linear model proved to be the most representative of total GA growth, with lowest average uncertainty (original scale: U = 0.025, square root scale: U = 0.014), high average r2 (original scale: 0.92, square root scale: 0.93), and applicability of the model was supported by a high correlation coefficient, r, with statistical significance (P = 0.01). Conclusions: Statistical analysis of uncertainty suggests that the linear model provides an effective and practical representation of the rate and progression of total GA growth based on data from patient presentations in clinical settings. Translational Relevance: Identification of correct model structure to characterize rate of growth of total GA in the retina using FAF images provides an objective metric for comparing interventions and charting GA progression in clinical presentations.

Artificial Intelligence and Telehealth may Provide Early Warning of Epidemics.

The COVID-19 pandemic produced a very sudden and serious impact on public health around the world, greatly adding to the burden of overloaded professionals and national medical systems. Recent medical research has demonstrated the value of using online systems to predict emerging spatial distributions of transmittable diseases. Concerned internet users often resort to online sources in an effort to explain their medical symptoms. This raises the prospect that incidence of COVID-19 may be tracked online by search queries and social media posts analyzed by advanced methods in data science, such as Artificial Intelligence. Online queries can provide early warning of an impending epidemic, which is valuable information needed to support planning timely interventions. Identification of the location of clusters geographically helps to support containment measures by providing information for decision-making and modeling.

Radiofrequency electromagnetic field exposure assessment: a pilot study on mobile phone signal strength and transmitted power levels.

In many epidemiological studies mobile phone use has been used as an exposure proxy for radiofrequency electromagnetic field (RF-EMF) exposure. However, RF-EMF exposure assessment from mobile phone use is prone to measurement errors limiting epidemiological research. An often-overlooked aspect is received signal strength levels from base stations and its correlation with mobile phone transmit (Tx) power. The Qualipoc android phone is a tool that provides information on both signal strength and Tx power. The phone produces simultaneous measurements of Received Signal Strength Indicator (RSSI), Reference Signal Received Power (RSRP), Received Signal Code Power (RSCP), and Tx power on the 3G and 4G networks. Measurements taken in the greater Melbourne area found a wide range of signal strength levels. The correlations between multiple signal strength indicators and Tx power were assessed with strong negative correlations found for 3G and 4G data technologies (3G RSSI -0.93, RSCP -0.93; 4G RSSI -0.85, RSRP -0.87). Variations in Tx power over categorical levels of signal strength were quantified and showed large increases in Tx power as signal level decreased. Future epidemiological studies should control for signal strength or factors influencing signal strength to reduce RF-EMF exposure measurement error.

Artificial Intelligence Algorithms for Analysis of Geographic Atrophy: A Review and Evaluation.

Purpose: The purpose of this study was to summarize and evaluate artificial intelligence (AI) algorithms used in geographic atrophy (GA) diagnostic processes (e.g. isolating lesions or disease progression). Methods: The search strategy and selection of publications were both conducted in accordance with the Preferred of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed and Web of Science were used to extract literary data. The algorithms were summarized by objective, performance, and scope of coverage of GA diagnosis (e.g. lesion automation and GA progression). Results: Twenty-seven studies were identified for this review. A total of 18 publications focused on lesion segmentation only, 2 were designed to detect and classify GA, 2 were designed to predict future overall GA progression, 3 focused on prediction of future spatial GA progression, and 2 focused on prediction of visual function in GA. GA-related algorithms reported sensitivities from 0.47 to 0.98, specificities from 0.73 to 0.99, accuracies from 0.42 to 0.995, and Dice coefficients from 0.66 to 0.89. Conclusions: Current GA-AI publications have a predominant focus on lesion segmentation and a minor focus on classification and progression analysis. AI could be applied to other facets of GA diagnoses, such as understanding the role of hyperfluorescent areas in GA. Using AI for GA has several advantages, including improved diagnostic accuracy and faster processing speeds. Translational Relevance: AI can be used to quantify GA lesions and therefore allows one to impute visual function and quality-of-life. However, there is a need for the development of reliable and objective models and software to predict the rate of GA progression and to quantify improvements due to interventions.

Uncertainty Analysis of Mobile Phone Use and Its Effect on Cognitive Function: The Application of Monte Carlo Simulation in a Cohort of Australian Primary School Children.

Previous epidemiological studies on health effects of radiation exposure from mobile phones have produced inconsistent results. This may be due to experimental difficulties and various sources of uncertainty, such as statistical variability, measurement errors, and model uncertainty. An analytical technique known as the Monte Carlo simulation provides an additional approach to analysis by addressing uncertainty in model inputs using error probability distributions, rather than point-source data. The aim of this investigation was to demonstrate using Monte Carlo simulation of data from the ExPOSURE (Examination of Psychological Outcomes in Students using Radiofrequency dEvices) study to quantify uncertainty in the output of the model. Data were collected twice, approximately one year apart (between 2011 and 2013) for 412 primary school participants in Australia. Monte Carlo simulation was used to estimate output uncertainty in the model due to uncertainties in the call exposure data. Multiple linear regression models evaluated associations between mobile phone calls with cognitive function and found weak evidence of an association. Similar to previous longitudinal analysis, associations were found for the Go/No Go and Groton maze learning tasks, and a Stroop time ratio. However, with the introduction of uncertainty analysis, the results were closer to the null hypothesis.

Radiofrequency Electromagnetic Radiation and Memory Performance: Sources of Uncertainty in Epidemiological Cohort Studies.

Uncertainty in experimental studies of exposure to radiation from mobile phones has in the past only been framed within the context of statistical variability. It is now becoming more apparent to researchers that epistemic or reducible uncertainties can also affect the total error in results. These uncertainties are derived from a wide range of sources including human error, such as data transcription, model structure, measurement and linguistic errors in communication. The issue of epistemic uncertainty is reviewed and interpreted in the context of the MoRPhEUS, ExPOSURE and HERMES cohort studies which investigate the effect of radiofrequency electromagnetic radiation from mobile phones on memory performance. Research into this field has found inconsistent results due to limitations from a range of epistemic sources. Potential analytic approaches are suggested based on quantification of epistemic error using Monte Carlo simulation. It is recommended that future studies investigating the relationship between radiofrequency electromagnetic radiation and memory performance pay more attention to treatment of epistemic uncertainties as well as further research into improving exposure assessment. Use of directed acyclic graphs is also encouraged to display the assumed covariate relationship.

Estimating global arthropod species richness: refining probabilistic models using probability bounds analysis.

A key challenge in the estimation of tropical arthropod species richness is the appropriate management of the large uncertainties associated with any model. Such uncertainties had largely been ignored until recently, when we attempted to account for uncertainty associated with model variables, using Monte Carlo analysis. This model is restricted by various assumptions. Here, we use a technique known as probability bounds analysis to assess the influence of assumptions about (1) distributional form and (2) dependencies between variables, and to construct probability bounds around the original model prediction distribution. The original Monte Carlo model yielded a median estimate of 6.1 million species, with a 90 % confidence interval of [3.6, 11.4]. Here we found that the probability bounds (p-bounds) surrounding this cumulative distribution were very broad, owing to uncertainties in distributional form and dependencies between variables. Replacing the implicit assumption of pure statistical independence between variables in the model with no dependency assumptions resulted in lower and upper p-bounds at 0.5 cumulative probability (i.e., at the median estimate) of 2.9-12.7 million. From here, replacing probability distributions with probability boxes, which represent classes of distributions, led to even wider bounds (2.4-20.0 million at 0.5 cumulative probability). Even the 100th percentile of the uppermost bound produced (i.e., the absolutely most conservative scenario) did not encompass the well-known hyper-estimate of 30 million species of tropical arthropods. This supports the lower estimates made by several authors over the last two decades.

Quantifying uncertainty in estimation of tropical arthropod species richness.

There is a bewildering range of estimates for the number of arthropods on Earth. Several measures are based on extrapolation from species specialized to tropical rain forest, each using specific assumptions and justifications. These approaches have not provided any sound measure of uncertainty associated with richness estimates. We present two models that account for parameter uncertainty by replacing point estimates with probability distributions. The models predict medians of 3.7 million and 2.5 million tropical arthropod species globally, with 90% confidence intervals of [2.0, 7.4] million and [1.1, 5.4] million, respectively. Estimates of 30 million or greater are predicted to have <0.00001 probability. Sensitivity analyses identified uncertainty in the proportion of canopy arthropod species that are beetles as the most influential parameter, although uncertainties associated with three other parameters were also important. Using the median estimates suggests that in spite of 250 years of taxonomy and around 855,000 species of arthropods already described, approximately 70% await description.