A Prediction Model to Discriminate Small Choroidal Melanoma from Choroidal Nevus

2021 ◽  
Author(s):  
Emily C. Zabor ◽  
Vishal Raval ◽  
Shiming Luo ◽  
David E. Pelayes ◽  
Arun D. Singh
Keyword(s):  
Prediction Model ◽  
External Validation ◽  
Choroidal Melanoma ◽  
Subretinal Fluid ◽  
Training Data ◽  
Validation Data ◽  
Orange Pigment ◽  
Melanocytic Tumor ◽  
Predicted Probability ◽  
Choroidal Nevus

Objective: To develop a validated machine learning model to diagnose small choroidal melanoma. Design: Cohort study Subjects, Participants, and/or Controls: The training data included 123 patients diagnosed as small choroidal melanocytic tumor (5.0-16.0 mm in largest basal diameter and 1.0 mm to 2.5 mm in height; Collaborative Ocular Melanoma Study criteria). Those diagnosed as melanoma (n=61) had either documented growth or pathologic confirmation. 62 patients with stable lesions classified as choroidal nevus, were used as negative controls. The external validation data set included 240 patients managed at a different tertiary clinic, also with small choroidal melanocytic tumor, observed for malignant growth. Methods: In the training data, lasso logistic regression was used to select variables for inclusion in the final model for the association with melanoma versus choroidal nevus. Internal and external validation were performed to assess model performance. Main Outcome Measures: Predicted probability of small choroidal melanoma Results: Distance to optic disc ≥3mm and drusen were associated with decreased odds of melanoma whereas male versus female sex, increased height, subretinal fluid, and orange pigment were associated with increased odds of choroidal melanoma. The area under the receiver operating characteristic (AUROC) “discrimination value” for this model was 0.880. The top four variables that were most frequently selected for inclusion in the model on internal validation, implying their importance as predictors of melanoma, were subretinal fluid, height, distance to optic disc, and orange pigment. When tested against the validation data, the prediction model could distinguish between choroidal nevus and melanoma with high discrimination of 0.861. The final prediction model was converted into an online calculator to generate predicted probability of melanoma. Conclusions: To minimize diagnostic uncertainty, a machine learning based diagnostic prediction calculator can be readily applied for decision making and counselling patients with small choroidal melanoma.

Small Choroidal Melanoma: Correlation of Growth Rate with Pathology

2021 ◽  
pp. 1-10
Author(s):  
Vishal Raval ◽  
Shiming Luo ◽  
Emily C. Zabor ◽  
Arun D. Singh
Keyword(s):  
Growth Rate ◽  
Retinal Pigment ◽  
Choroidal Melanoma ◽  
Case Series ◽  
Subretinal Fluid ◽  
Categorical Variables ◽  
Continuous Variables ◽  
Basal Diameter ◽  
Orange Pigment ◽  
Rpe Atrophy

<b><i>Purpose:</i></b> The aim of the study was to evaluate equivalence of growth rate and pathologic confirmation in small choroidal melanoma (SCM). <b><i>Design:</i></b> This study is a case series. <b><i>Subjects, Participants, and Controls:</i></b> A total of 61 patients with a choroidal melanocytic tumor of size 5.0–16.0 mm in the largest basal diameter and 1.0–2.5 mm in thickness were classified into the pathology-confirmed group (<i>n</i> = 19), growth-confirmed group (<i>n</i> = 30), and with combined observations (<i>n</i> = 12). <b><i>Methods:</i></b> Distribution of clinical variables (age, gender, laterality, tumor dimensions, tumor location, and presence of orange pigment, subretinal fluid, drusen, and retinal pigment epithelial [RPE] atrophy) between the groups was analyzed. Patient and disease characteristics were summarized as the median and interquartile range for continuous variables and the frequency and percentage for categorical variables. Comparisons were made using the Wilcoxon rank sum test for continuous variables and either Fisher’s exact test or the χ<sup>2</sup> test for categorical variables with a <i>p</i> value threshold of 0.05 for statistical significance. Growth rate (change in basal dimension/12 months) diagnostic of SCM was quantified. <b><i>Main Outcome Measures:</i></b> The primary aim of this study was to test the hypothesis that “growth” was diagnostic of SCM with the secondary aim of quantifying the malignant “growth rate” (growth rate of SCM). <b><i>Results:</i></b> The clinical characteristics among all 3 groups were similar except more patients with symptoms (68 vs. 20 vs. 42%, <i>p</i> = 0.004) and juxtapapillary location (<i>p</i> = 0.03) were in the pathology group than in the growth-confirmed group. Those in the combined and growth-confirmed groups had more patients with drusen (11 vs. 60 vs. 50%, <i>p</i> = 0.003) and RPE atrophy (11 vs. 23 vs. 67%, <i>p</i> = 0.003), respectively, than in the pathology group. The median time to detect growth was 9 months (range 3–26 months). The mean growth rate in basal dimension was 1.8 mm/12 months (range, 0.0–7.4 mm; [95% CI: 1.32–2.28]). <b><i>Conclusions and Relevance:</i></b> Choroidal melanocytic lesions exhibiting a defined growth rate can be clinically diagnosed as SCM without a need for biopsy.

scholarly journals Regression patterns of choroidal melanoma: After palladium-103 (103Pd) plaque brachytherapy

2018 ◽  
Vol 28 (6) ◽  
pp. 722-730 ◽  
Author(s):  
Abhilasha Maheshwari ◽  
Paul T Finger
Keyword(s):  
Complete Resolution ◽  
Retinal Pigment Epithelial ◽  
Retinal Pigment ◽  
Choroidal Melanoma ◽  
Subretinal Fluid ◽  
Tumor Thickness ◽  
Tumor Vascularity ◽  
Orange Pigment ◽  
Pigment Epithelial ◽  
Plaque Brachytherapy

Purpose: To describe the patterns of regression of choroidal melanoma after treatment with plaque brachytherapy. Methods: Retrospective interventional case series including 170 consecutive patients treated with 103Pd eye plaque radiation for choroidal melanoma. Outcome measures were changes in tumor thickness, surface characteristics, tumor vascularity, ultrasonography, fluorescein angiography, optical coherence tomography, and histopathology. Results: The mean initial tumor thickness was 3.9 mm (median 2.8 mm; range 2–11.3 mm) that decreased to 1.7 mm (median 1.2 mm; range 0–7.1 mm) after plaque brachytherapy. On imaging, tumors were pigmented in 51% ( n = 86/170), amelanotic in 10% ( n = 17/170), and variably pigmented in 39% ( n = 67/170). Tumor pigmentation increased in 64% ( n = 106/166), decreased in 18% ( n = 30/166), and was unchanged in 18% ( n = 30/166). Of the 120 that demonstrated intrinsic vascularity, 10% ( n = 12/120) had decreased tumor-related vascularity and 90% ( n = 108/120) showed complete resolution. Subretinal fluid was present in 34% ( n = 58/170) of eyes at presentation. Of them, 15% (9; n = 9/58) had persistent SRF at last follow-up. On ultrasound imaging, 88% ( n = 149/170) tumors presented with low to moderate internal reflectivity of which 61% ( n = 91/149) showed increased reflectivity on regression. We noted a crescendo–decrescendo fluctuation in the presence of orange pigment lipofuscin along with complete resolution of drusenoid retinal pigment epithelial detachments. In the entire series of 170 patients, there was 0.5% (1) failure of local control, 2% (4) secondary enucleations, and 6% (10) patients developing metastasis. Conclusion: Findings related to choroidal melanoma regression after 103Pd plaque brachytherapy included decreased intrinsic tumor vascularity, decreased tumor-related subretinal fluid, increased pigmentation, specific changes in orange pigment lipofuscin and resolution of drusenoid retinal pigment epithelial detachments, as well as decreased tumor thickness with an increase in internal reflectivity on ultrasound.

scholarly journals Prediction of individuals at high risk of chronic kidney disease during treatment with lithium for bipolar disorder

BMC Medicine ◽  
2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Joseph F. Hayes ◽  
David P. J. Osborn ◽  
Emma Francis ◽  
Gareth Ambler ◽  
Laurie A. Tomlinson ◽  
...  
Keyword(s):  
Bipolar Disorder ◽  
High Risk ◽  
Prediction Model ◽  
Lithium Treatment ◽  
External Validation ◽  
Elastic Net ◽  
Validation Data ◽  
Data Set ◽  
Roc Area

Abstract Background Lithium is the most effective treatment in bipolar disorder. Its use is limited by concerns about risk of chronic kidney disease (CKD). We aimed to develop a model to predict risk of CKD following lithium treatment initiation, by identifying individuals with a high-risk trajectory of kidney function. Methods We used United Kingdom Clinical Practice Research Datalink (CPRD) electronic health records (EHRs) from 2000 to 2018. CPRD Aurum for prediction model development and CPRD Gold for external validation. We used elastic net regularised regression to generate a prediction model from potential features. We performed discrimination and calibration assessments in an external validation data set. We included all patients aged ≥ 16 with bipolar disorder prescribed lithium. To be included patients had to have ≥ 1 year of follow-up before lithium initiation, ≥ 3 estimated glomerular filtration rate (eGFR) measures after lithium initiation (to be able to determine a trajectory) and a normal (≥ 60 mL/min/1.73 m2) eGFR at lithium initiation (baseline). In the Aurum development cohort, 1609 fulfilled these criteria. The Gold external validation cohort included 934 patients. We included 44 potential baseline features in the prediction model, including sociodemographic, mental and physical health and drug treatment characteristics. We compared a full model with the 3-variable 5-year kidney failure risk equation (KFRE) and a 3-variable elastic net model. We used group-based trajectory modelling to identify latent trajectory groups for eGFR. We were interested in the group with deteriorating kidney function (the high-risk group). Results The high risk of deteriorating eGFR group included 191 (11.87%) of the Aurum cohort and 137 (14.67%) of the Gold cohort. Of these, 168 (87.96%) and 117 (85.40%) respectively developed CKD 3a or more severe during follow-up. The model, developed in Aurum, had a ROC area of 0.879 (95%CI 0.853–0.904) in the Gold external validation data set. At the empirical optimal cut-point defined in the development dataset, the model had a sensitivity of 0.91 (95%CI 0.84–0.97) and a specificity of 0.74 (95% CI 0.67–0.82). However, a 3-variable elastic net model (including only age, sex and baseline eGFR) performed similarly well (ROC area 0.888; 95%CI 0.864–0.912), as did the KFRE (ROC area 0.870; 95%CI 0.841–0.898). Conclusions Individuals at high risk of a poor eGFR trajectory can be identified before initiation of lithium treatment by a simple equation including age, sex and baseline eGFR. Risk was increased in individuals who were younger at commencement of lithium, female and had a lower baseline eGFR. We did not identify strong predicters of eGFR decline specific to lithium-treated patients. Notably, lithium duration and toxicity were not associated with high-risk trajectory.

scholarly journals Bilateral Diffuse Uveal Melanocytic Proliferation Presenting as Small Choroidal Melanoma

2011 ◽  
Vol 2011 ◽  
pp. 1-3 ◽  
Author(s):  
J. N. Ulrich ◽  
S. Garg ◽  
G. K. Escaravage ◽  
T. M. Meredith
Keyword(s):  
Visual Acuity ◽  
Clinical Picture ◽  
Clinical Case ◽  
Radioactive Iodine ◽  
Palliative Chemotherapy ◽  
Choroidal Melanoma ◽  
Orange Pigment ◽  
History Of ◽  
Choroidal Nevus ◽  
The Right

Purpose. To describe a patient with Bilateral Diffuse Uveal Proliferation who presented initially with a clinical picture consistent with choroidal melanoma.Methods. Presentation of a clinical case with fundus photos, fluorescein angiography, and optical coherence tomography.Results. A 70-year-old Caucasian male with history of esophageal cancer presented with an asymptomatic pigmented choroidal lesion in his left eye initially diagnosed as choroidal nevus. This lesion enlarged over the course of a year and developed orange pigment and increased thickness. A metastatic workup was negative, and a radioactive iodine plaque was placed on the left eye. Over the next six months, the visual acuity in his left eye decreased. His clinical picture was consistent with unilateral Diffuse Uveal Proliferation. A recurrence of his esophageal carcinoma with metastasis was discovered and palliative chemotherapy was initiated. Although his visual acuity improved in the left eye, similar pigmentary changes developed in the right fundus. His visual acuity in both eyes gradually decreased to 20/200 until his death a year later.Conclusion. BDUMP should always be considered in the differential diagnosis of patients with pigmented fundus lesions and a history of nonocular tumors.

scholarly journals The MOLES System for Planning Management of Melanocytic Choroidal Tumors: Is It Safe?

Cancers ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 1311 ◽  
Author(s):  
Kelsey A. Roelofs ◽  
Roderick O’Day ◽  
Lamis Al Harby ◽  
Amit K. Arora ◽  
Victoria M.L. Cohen ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Ciliary Body ◽  
Demographic Data ◽  
Choroidal Melanoma ◽  
Subretinal Fluid ◽  
Fundus Photography ◽  
Tumor Diameter ◽  
Specialist Care ◽  
Orange Pigment ◽  
Large Size

Purpose: To evaluate the MOLES system for identifying malignancy in melanocytic choroidal tumors in patients treated for choroidal melanoma. Methods: Records of 615 patients treated for choroidal melanoma between January 2017 and December 2019 were reviewed. Patients were excluded if iris and/or ciliary body involvement (106 patients), inadequate fundus photography (26 patients), no images available for review (21 patients) and/or treatment was not primary (11 patients). Demographic data and AJCC TNM Stage were collected. Color fundus and autofluorescence photographs (FAF), optical coherence tomography (OCT) and B-scan ultrasounds were prospectively reviewed. MOLES scores were assigned according to five criteria: mushroom shape, orange pigment, large size, enlarging tumor and subretinal fluid. Results: A total of 451 patients (mean age, 63.9 ± 13.9 years) were included. At treatment, mean largest basal tumor diameter (LBD) and thickness were 10.3 ± 2.8 mm (range, 3.0–23.0) and 4.3 mm (range, 1.0–17.0). All but one (0.2%) had MOLES scores of ≥3. Eighty-two patients were treated after surveillance lasting a mean of 1.5 years. Initially, most (63/82; 76.8%) had a MOLES score ≥ 3. Importantly, none of the 451 tumors had a score of <2, and as such, the MOLES protocol would have indicated referral to an ocular oncologist for 100% of patients. Conclusion: The MOLES scoring system is a sensitive (99.8%) tool for indicating malignancy in melanocytic choroidal tumors (MOLES ≥ 3). If the examining practitioner can recognize the five features suggestive of malignancy, MOLES is a safe tool to optimize referral of melanocytic choroidal tumors for specialist care.

scholarly journals Isolated choroidal melanocytosis: clinical update on 37 cases

2020 ◽  
Vol 258 (12) ◽  
pp. 2819-2829
Author(s):  
James J. Augsburger ◽  
Cassandra C. Brooks ◽  
Zelia M. Correa
Keyword(s):  
Choroidal Melanoma ◽  
Initial Diagnosis ◽  
Adult Patients ◽  
Basal Diameter ◽  
Orange Pigment ◽  
Fellow Eye ◽  
Retrospective Clinical Study ◽  
Choroidal Malignant Melanoma ◽  
Choroidal Nevus

Abstract Purpose Isolated choroidal melanocytosis is a congenital melanocytic hyperpigmentation involving the choroid that is not associated with iridic or scleral features of ocular melanocytosis. The purpose of this work was to describe the clinical features and course of a relatively large series of patients with this disorder. Methods A retrospective clinical study of 37 patients with isolated choroidal melanocytosis encountered in a single practice 1986–2018 was done. All lesions were 5 mm or larger in the largest basal diameter, homogeneously melanotic, and completely flat by conventional ocular ultrasonography. Results The 37 patients ranged in age from 2 weeks to 87 years (mean 31.5 years, median 18 years) at initial diagnosis of the melanotic choroidal lesion. Arc length largest basal diameter of the melanotic choroidal lesion ranged from 5.5 to 37 mm (mean 14.6 mm, median 13 mm). The lesion extended beneath the fovea in 18 eyes and to the optic disc margin in 6 eyes. Ten of the lesions straddled the ocular equator, but the center point of all of the lesions was posterior to the equator. The retina was fully attached and appeared normal over the melanotic choroidal lesion in each of these eyes. None of the melanotic choroidal lesions exhibited clumps of orange pigment or drusen on its surface. The lesion was unilateral and unifocal in 36 of the 37 patients. One patient had bilateral choroidal melanocytosis that was isolated in one eye but associated with partial iris melanocytosis in the fellow eye. Three adult patients had a choroidal melanoma localized to the patch of choroidal melanocytosis at baseline. One other adult patient had a choroidal melanoma in the fellow eye at baseline. One pediatric patient had viable unilateral non-familial retinoblastoma in the fellow eye and two adult patients had a classic choroidal nevus in the fellow eye. None of the flat patches of choroidal melanocytosis that were monitored periodically after initial diagnosis expanded appreciably during follow-up ranging from 4.9 months to 15.2 years (mean 5.0 years, median 2.3 years). Conclusions Isolated choroidal melanocytosis is a distinct clinical entity that must be distinguished from broad-based choroidal nevus, choroidal melanocytoma, small choroidal malignant melanoma, acquired bilateral patchy-streaky choroidal melanocytic fundopathy associated with disorders such as cutaneous vitiligo and Waardenburg syndrome, acquired bilateral zonal choroidal melanocytic fundopathy, and diffuse uveal melanocytic proliferation associated with systemic cancer. This disorder appears to predispose affected eyes to development of choroidal melanoma arising from the hypermelanotic patch.

scholarly journals Characterization of Slovenian coal and estimation of coal heating value based on proximate analysis using regression and artificial neural networks

2013 ◽  
Vol 11 (9) ◽  
pp. 1481-1491 ◽  
Author(s):  
Darja Kavšek ◽  
Adriána Bednárová ◽  
Miša Biro ◽  
Roman Kranvogl ◽  
Darinka Vončina ◽  
...  
Keyword(s):  
External Validation ◽  
Relative Difference ◽  
Proximate Analysis ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Validation Data ◽  
Data Set ◽  
Heating Value ◽  
The Mean ◽  
Artificial Neural

AbstractAbstract Chemical composition of Slovenian coal has been characterised in terms of proximate and ultimate analyses and the relations among the chemical descriptors and the higher heating value (HHV) examined using correlation analysis and multivariate data analysis methods. The proximate analysis descriptors were used to predict HHV using multiple linear regression (MLR) and artificial neural network (ANN) methods. An attempt has been made to select the model with the optimal number of predictor variables. According to the adjusted multiple coefficient of determination in the MLR model, and alternatively, according to sensitivity analysis in ANN developing, two descriptors were evaluated by both methods as optimal predictors: fixed carbon and volatile matter. The performances of MLR and ANN when modelling HHV were comparable; the mean relative difference between the actual and calculated HHV values in the training data was 1.11% for MLR and 0.91% for ANN. The predictive ability of the models was evaluated by an external validation data set; the mean relative difference between the actual and predicted HHV values was 1.39% in MLR and 1.47% in ANN. Thus, the developed models could be appropriately used to calculate HHV. Graphical abstract

scholarly journals The diagnosis of tuberculous meningitis in adults and adolescents: protocol for a systematic review and individual patient data meta-analysis to inform a multivariable prediction model

2019 ◽  
Vol 4 ◽  
pp. 19
Author(s):  
Tom Boyles ◽  
Anna Stadelman ◽  
Jayne P. Ellis ◽  
Fiona V. Cresswell ◽  
Vittoria Lutje ◽  
...  
Keyword(s):  
Systematic Review ◽  
Prediction Model ◽  
Tuberculous Meningitis ◽  
Latent Variables ◽  
Individual Patient Data ◽  
External Validation ◽  
Patient Data ◽  
Nucleic Acid Amplification ◽  
Validation Data ◽  
Data Set

Background: Tuberculous meningitis (TBM) is the most lethal and disabling form of tuberculosis. Delayed diagnosis and treatment, which is a risk factor for poor outcome, is caused in part by lack of availability of diagnostic tests that are both rapid and accurate. Several attempts have been made to develop clinical scoring systems to fill this gap, but none have performed sufficiently well to be broadly implemented. We aim to identify and validate a set of clinical predictors that accurately classify TBM using individual patient data (IPD) from published studies. Methods: We will perform a systematic review and obtain IPD from studies published from the year 1990 which undertook diagnostic testing for TBM in adolescents or adults using at least one of, microscopy for acid-fast bacilli, commercial nucleic acid amplification test for Mycobacterium tuberculosis or mycobacterial culture of cerebrospinal fluid.  Clinical data that have previously been shown to be associated with TBM, and can inform the final diagnosis, will be requested. The data-set will be divided into training and test/validation data-sets for model building. A predictive logistic model will be built using a training set with patients with definite TBM and no TBM. Should it be warranted, factor analysis may be employed, depending on evidence for multicollinearity or the case for including latent variables in the model. Discussion: We will systematically identify and extract key clinical parameters associated with TBM from published studies and use a ‘big data’ approach to develop and validate a clinical prediction model with enhanced generalisability. The final model will be made available through a smartphone application. Further work will be external validation of the model and test of efficacy in a randomised controlled trial.

scholarly journals A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients in China

2021 ◽  
Author(s):  
Dong Wang ◽  
JinBo Li ◽  
Yali Sun ◽  
Xianfei Ding ◽  
Xiaojuan Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Model ◽  
Secondary Analysis ◽  
Adverse Outcomes ◽  
Training Data ◽  
Medical Systems ◽  
Validation Data ◽  
Data Set ◽  
Icu Patients

Abstract Background: Although numerous studies are conducted every year on how to reduce the fatality rate associated with sepsis, it is still a major challenge faced by patients, clinicians, and medical systems worldwide. Early identification and prediction of patients at risk of sepsis and adverse outcomes associated with sepsis are critical. We aimed to develop an artificial intelligence algorithm that can predict sepsis early.Methods: This was a secondary analysis of an observational cohort study from the Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University. A total of 4449 infected patients were randomly assigned to the development and validation data set at a ratio of 4:1. After extracting electronic medical record data, a set of 55 features (variables) was calculated and passed to the random forest algorithm to predict the onset of sepsis.Results: The pre-procedure clinical variables were used to build a prediction model from the training data set using the random forest machine learning method; a 5-fold cross-validation was used to evaluate the prediction accuracy of the model. Finally, we tested the model using the validation data set. The area obtained by the model under the receiver operating characteristic (ROC) curve (AUC) was 0.91, the sensitivity was 87%, and the specificity was 89%.Conclusions: The newly established model can accurately predict the onset of sepsis in ICU patients in clinical settings as early as possible. Prospective studies are necessary to determine the clinical utility of the proposed sepsis prediction model.

Sign in / Sign up

Export Citation Format

Share Document