scholarly journals Simple, Mobile-based Artificial Intelligence Algorithm in the detection of Diabetic Retinopathy (SMART) study

2020 ◽  
Vol 8 (1) ◽  
pp. e000892 ◽  
Author(s):  
Bhavana Sosale ◽  
Sosale Ramachandra Aravind ◽  
Hemanth Murthy ◽  
Srikanth Narayana ◽  
Usha Sharma ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Diabetic Retinopathy ◽  
Sensitivity And Specificity ◽  
Smart Phone ◽  
High Sensitivity ◽  
Ground Truth ◽  
Cross Sectional Study ◽  
Retinal Images ◽  
Cross Sectional ◽  
Smart Study

IntroductionThe aim of this study is to evaluate the performance of the offline smart phone-based Medios artificial intelligence (AI) algorithm in the diagnosis of diabetic retinopathy (DR) using non-mydriatic (NM) retinal images.MethodsThis cross-sectional study prospectively enrolled 922 individuals with diabetes mellitus. NM retinal images (disc and macula centered) from each eye were captured using the Remidio NM fundus-on-phone (FOP) camera. The images were run offline and the diagnosis of the AI was recorded (DR present or absent). The diagnosis of the AI was compared with the image diagnosis of five retina specialists (majority diagnosis considered as ground truth).ResultsAnalysis included images from 900 individuals (252 had DR). For any DR, the sensitivity and specificity of the AI algorithm was found to be 83.3% (95% CI 80.9% to 85.7%) and 95.5% (95% CI 94.1% to 96.8%). The sensitivity and specificity of the AI algorithm in detecting referable DR (RDR) was 93% (95% CI 91.3% to 94.7%) and 92.5% (95% CI 90.8% to 94.2%).ConclusionThe Medios AI has a high sensitivity and specificity in the detection of RDR using NM retinal images.

scholarly journals Serum high sensitivity C reactive protein levels in patients with diabetic retinopathy: a cross sectional study

2020 ◽  
Vol 7 (3) ◽  
pp. 391
Author(s):  
Harishchandra R. Chaudhari ◽  
Gaurav A. Chaudhari
Keyword(s):  
Diabetic Retinopathy ◽  
Blood Glucose ◽  
High Sensitivity ◽  
Cross Sectional Study ◽  
Postprandial Blood Glucose ◽  
Sectional Study ◽  
C Reactive Protein ◽  
Cross Sectional ◽  
Reactive Protein ◽  
Hs Crp

Background: Diabetic retinopathy (DR) is one of the major visual morbidities associated with diabetes. This study determined the levels of serum high-sensitivity C-reactive protein (hs-CRP) in patients with DR and to correlate the estimated levels of serum hs-CRP with the severity of DR and other coexisting factors.Methods: This was a cross-sectional study conducted between March 2009 and August 2010 and included patients with type 2 diabetes mellitus (T2DM) with or without DR. A detailed fundus evaluation was performed using direct and indirect ophthalmoscopy. The retinopathies were observed and documented in accordance with the Kanski's system of classification as background DR (BDR), pre-proliferative DR (PPDR), and proliferative DR (PDR). Laboratory investigations determined the levels of fasting blood glucose (FBG), postprandial blood glucose (PPBG), glycosylated hemoglobin, urine albumin excretion, and serum hs-CRP levels.Results: In total, 80 patients with T2DM were included (DR group, n=40 [BDR, n=22; PDR, n=11; PPDR, n=7]; control group, n=40). Highest serum hs-CRP levels were found in PDR group (6.68 mg/L), followed by PPDR and BDR group (3.2 mg/L and 1.56 mg/L, respectively). The PDR group showed the longest duration of diabetes (16 years), highest FBG (221.8 mg/dL) and HbA1c (6.68 mg/L). The incidence of albuminuria and maculopathy was higher in PDR group (72.7% and 54.54%, respectively). A significant association of hs-CRP levels with DR in patients with T2DM was observed. A significantly (<0.005) positive correlation of hs-CRP was also observed with age, duration of disease, FBG, PPBG, and HbA1c.Conclusions: Patients with severe grades of retinopathy had significantly higher hs-CRP levels than patients with the milder grades.

scholarly journals Detecting proteinuria: A comparison of diagnostic tests

2011 ◽  
Vol 51 (1) ◽  
pp. 17
Author(s):  
Jeanida Mauliddina ◽  
Rosmayanti Siregar ◽  
Oke Rina Ramayani ◽  
Rafita Ramayati ◽  
Rusdidjas Rusdidjas
Keyword(s):  
Sensitivity And Specificity ◽  
Predictive Value ◽  
High Sensitivity ◽  
Cross Sectional Study ◽  
Common Symptom ◽  
Sulfosalicylic Acid ◽  
Cross Sectional ◽  
Renal Disorders ◽  
Acid Test ◽  
Urine Specimens

Background Proteinuria is a condition when protein is found in urine, a common symptom in children with renal disorders. Proteinuria can also be found in nonnal children and in those with non-renal disorders. A high sensitivity test is needed to detect proteinuria. Spectrophotometry has been used as a standard to detect proteinuria, however, it is expensive and not readily available in health clinics. We tested the use of20% sulfosalicylic add to detect proteinuria, and compared it to spectrophotometry. The sulfosalicylic add test is inexpensive, rapid, and easily performed in primary community health centers.Objective To compare 2 0 % sulfosalicylic acid test t o spectrophotometry as a diagnostic test for proteinuria.Methods We conducted a cross-sectional study in Adam Malik Hospital from September 2009 until December 2009. Inclusion criteria were children aged 3 to 18 years who experienced kidney disease. We collected 24 hour urine specimens from 55 children by consecutive sampling. Urine specimens were tested for proteinuria by 20% sulfosalicylic acid test and spectrophotometry.Results Sensitivity and specificity of 20% sulfosalicylic acid test compared to spectrophotometry were 88.1 % and 69.2%, respectively, with a positive predictive value and a negative predictive value of 90.2% and 64.3%, respectively.Conclusion The sulfosalicylic acid test had low sensitivity and specificity for detecting proteinuria, but it was more practical and less expensive compared to spectrophotometry.

scholarly journals Penggunaan ROC pada Skrining Pre-Eklampsia dengan Metode USG DVAUT pada Ibu Hamil di Puskesmas Mulyorejo Surabaya

2019 ◽  
Vol 8 (2) ◽  
pp. 129
Author(s):  
Intan Laraswati ◽  
Diah Indriani
Keyword(s):  
Pregnant Women ◽  
Sensitivity And Specificity ◽  
Screening Method ◽  
Sampling Technique ◽  
High Sensitivity ◽  
Cross Sectional Study ◽  
Observational Research ◽  
Operating Characteristics ◽  
Cross Sectional ◽  
Uterine Artery Doppler

Pre-eclampsia is the third highest cause of death in pregnant women. Symptoms of pre-eclampsia can be identified by the presence of hypertension, proteinuria and edema during pregnancy until postpartum. Pre-eclampsia cannot be identified with certain risk factors, and cannot be prevented. Pre-eclampsia can be detected early using the pre-eclampsia screening method with sonography. The sonographic device used is referred to as DVAUt ultrasound (Uterine Artery Doppler Velocimetry Ultrasonography). This studying an analytic observational research with a cross sectional study design. The population was all pregnant women who examined at the Mulyorejo primary health center in 2013 until the first quarter of 2018. The sampling technique was consecutive sampling with inclusion and exclusion criteria. The number of samples obtained is 496 data. The study aimed to determine the sensitivity and specificity of the pre-eclampsia screening method using DVAUt ultrasound in detecting the tendency of pregnant women to experience pre-eclampsia. The data were analyzed of sensitivity and specificity and the Receiver Operating Characteristics (ROC) curve with p <0.001. P1GF / sFlt-1 (Gold standard) biomaker test sensitivity of 89% and specificity of 90%. The results of this study were the sensitivity of pre-eclampsia screening at 99.7% and specificity of 81.9%. The ROC method obtained the results of pre-eclampsia screening using DVAUt ultrasound has a high sensitivity and specificity in detecting the tendency of pregnant women to experience pre-eclampsia. Suggestions for research to refresh knowledge and procedures for conducting pre-eclampsia screening checks.

scholarly journals The Alpha-fetoprotein Serum is still Reliable as a Biomarker for the Surveillance of Hepatocellular Carcinoma in Indonesia

2020 ◽  
Author(s):  
Chyntia Olivia Maurine Jasirwan ◽  
Alessa - Fahira ◽  
Lianda - Siregar ◽  
Imelda - Loho
Keyword(s):  
Hepatocellular Carcinoma ◽  
Liver Cancer ◽  
Hepatitis B ◽  
Sensitivity And Specificity ◽  
High Sensitivity ◽  
Cross Sectional Study ◽  
Surveillance Program ◽  
Average Life Expectancy ◽  
Cross Sectional ◽  
Patients At Risk

Abstract Background and Aims: Hepatocellular carcinoma (HCC), the most common type of liver cancer, is one of the leading causes of cancer-related death worldwide with an inferior prognosis. In Indonesia, the average life expectancy is less than 3 months, with most patients being in an advanced stage where in the survival rate is very low. Early detection through surveillance program is very crucial. HCC guidelines worldwide have provided surveillance recommendation through the examination of α-fetoprotein (AFP) and ultrasound for patients at risk in developing HCC. However, there have been some controversies regarding the usage of AFP concerning its low sensitivity and specificity in detecting HCC. Therefore, the effectiveness of AFP in the surveillance of HCC patients and identifying the parameters most associated with the increase of AFP≥10 ng/ml in Indonesia should be evaluated.Methods: We analysed medical records of HCC patients and those at high-risk of developing HCC through cross-sectional study, including patients with cirrhosis and hepatitis B and C, from 2015 to 2017 who underwent treatment at the Cipto Mangunkusumo National Hospital and Dharmais National Cancer Hospital, Indonesia.Results: The sensitivity and specificity of AFP in the surveillance of HCC in Indonesia with a cut-off of 10 ng/ml were 82.6% and 68.9%, respectively. The parameters most associated with the increase of AFP ≥10 ng/ml according to multivariate analysis were the etiology of hepatitis B, the stage of Barcelona Clinic Liver Cancer B and C, and the presence of cirrhosis, respectively.Conclusion: AFP can still be used in the surveillance of HCC in Indonesia for its high sensitivity value.

scholarly journals The Alpha-fetoprotein Serum is still Reliable as a Biomarker for the Surveillance of Hepatocellular Carcinoma in Indonesia

2020 ◽  
Author(s):  
Chyntia Olivia Maurine Jasirwan ◽  
Alessa - Fahira ◽  
Lianda - Siregar ◽  
Imelda - Loho
Keyword(s):  
Hepatocellular Carcinoma ◽  
Liver Cancer ◽  
Hepatitis B ◽  
Sensitivity And Specificity ◽  
High Sensitivity ◽  
Cross Sectional Study ◽  
Surveillance Program ◽  
Average Life Expectancy ◽  
Cross Sectional ◽  
Patients At Risk

Abstract Background and Aims Hepatocellular carcinoma (HCC), the most common type of liver cancer, is one of the leading causes of cancer-related death worldwide with an inferior prognosis. In Indonesia, the average life expectancy is less than 5 months, with most patients being in an advanced stage wherein the survival rate is very low. Early detection through surveillance program is very crucial. HCC guidelines worldwide have provided surveillance recommendation through the examination of α-fetoprotein (AFP) and ultrasound for patients at risk in developing HCC. However, there have been some controversies regarding the usage of AFP concerning its low sensitivity and specificity in detecting HCC. Therefore, the effectiveness of AFP in the surveillance of HCC patients and identifying the parameters most associated with the increase of AFP≥10 ng/ml in Indonesia should be evaluated. Methods We analyzed medical records of HCC patients and those at high risk of developing HCC through cross-sectional study, including patients with cirrhosis and hepatitis B and C, from 2015 to 2017 who underwent treatment at the Cipto Mangunkusumo National Hospital and Dharmais National Cancer Hospital, Indonesia. Results The sensitivity and specificity of AFP in the surveillance of HCC in Indonesia with a cut-off of 10 ng/ml were 82.6% and 71.2%, respectively. The parameters most associated with the increase of AFP ≥10 ng/ml according to multivariate analysis were the etiology of hepatitis B, the stage of Barcelona Clinic Liver Cancer B and C, and the presence of cirrhosis, respectively. Conclusion AFP can still be used in the surveillance of HCC in Indonesia for its high sensitivity value.

scholarly journals Penggunaan ROC pada Skrining Pre-Eklampsia dengan Metode USG DVAUT pada Ibu Hamil di Puskesmas Mulyorejo Surabaya

2019 ◽  
Vol 8 (2) ◽  
pp. 129
Author(s):  
Intan Laraswati ◽  
Diah Indriani
Keyword(s):  
Pregnant Women ◽  
Sensitivity And Specificity ◽  
Screening Method ◽  
Sampling Technique ◽  
High Sensitivity ◽  
Cross Sectional Study ◽  
Observational Research ◽  
Operating Characteristics ◽  
Cross Sectional ◽  
Uterine Artery Doppler

Pre-eclampsia is the third highest cause of death in pregnant women. Symptoms of pre-eclampsia can be identified by the presence of hypertension, proteinuria and edema during pregnancy until postpartum. Pre-eclampsia cannot be identified with certain risk factors, and cannot be prevented. Pre-eclampsia can be detected early using the pre-eclampsia screening method with sonography. The sonographic device used is referred to as DVAUt ultrasound (Uterine Artery Doppler Velocimetry Ultrasonography). This studying an analytic observational research with a cross sectional study design. The population was all pregnant women who examined at the Mulyorejo primary health center in 2013 until the first quarter of 2018. The sampling technique was consecutive sampling with inclusion and exclusion criteria. The number of samples obtained is 496 data. The study aimed to determine the sensitivity and specificity of the pre-eclampsia screening method using DVAUt ultrasound in detecting the tendency of pregnant women to experience pre-eclampsia. The data were analyzed of sensitivity and specificity and the Receiver Operating Characteristics (ROC) curve with p <0.001. P1GF / sFlt-1 (Gold standard) biomaker test sensitivity of 89% and specificity of 90%. The results of this study were the sensitivity of pre-eclampsia screening at 99.7% and specificity of 81.9%. The ROC method obtained the results of pre-eclampsia screening using DVAUt ultrasound has a high sensitivity and specificity in detecting the tendency of pregnant women to experience pre-eclampsia. Suggestions for research to refresh knowledge and procedures for conducting pre-eclampsia screening checks.

The Role of Elastography in Fibroadenoma of the Breast and Differentiating it from its Mimics

QJM ◽  
2021 ◽  
Vol 114 (Supplement_1) ◽  
Author(s):  
Marina Essam Fares Massak ◽  
Sahar M. El Fiky ◽  
Asmaa M Salama
Keyword(s):  
Sensitivity And Specificity ◽  
Diagnostic Performance ◽  
High Sensitivity ◽  
Strain Ratio ◽  
Cross Sectional Study ◽  
Ultrasound Elastography ◽  
University Hospitals ◽  
Cross Sectional ◽  
Strain Elastography ◽  
Imaging Characteristics

Abstract Background Fibroadenomas are one of the most common benign diseases of the breast varying in number and size in all quadrants of the breast. Less than 2% of lesions with the typical ultrasound features of a fibroadenoma, are found to be malignant on biopsy. Aim of the Work To evaluate the diagnostic performance of combined ultrasonography and strain elastography and to compare the imaging characteristics of fibroadenomas with other benign and malignant mimics and assess the results by histopathological characteristics. Patients and Methods Type of Study: Cross-sectional study. Study Setting: The study was conducted at Ain Shams University Hospitals, Radiodiagnosis department. Study Period: 6 months (From March 2020 till September 2020). Study Population: Female Patients with breast lumps. Results Ultrasound elastography combined with B-mode ultrasonography had shown variable degrees of sensitivity and specificity. However, in our study it showed high sensitivity and specificity as compared to other studies. The most reliable tool in our study was the strain ratio having the highest sensitivity and specificity. Conclusion Strain elastography combined to B-mode sonography improves the diagnostic performance of differentiating benign from malignant well circumscribed breast lesions with an additional benefit of preventing unnecessary biopsies and speeding up the diagnosis of malignant lesions instead of follow up of the patient for early diagnosis of malignancies.

scholarly journals Comparison of predicted psychological distress among workers between artificial intelligence and psychiatrists: a cross-sectional study in Tsukuba Science City, Japan

BMJ Open ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. e046265
Author(s):  
Shotaro Doki ◽  
Shinichiro Sasahara ◽  
Daisuke Hori ◽  
Yuichi Oi ◽  
Tsukasa Takahashi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Psychological Distress ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Cross Sectional ◽  
Explanatory Variables ◽  
The Neural Network ◽  
Significant Difference ◽  
Total Data

ObjectivesPsychological distress is a worldwide problem and a serious problem that needs to be addressed in the field of occupational health. This study aimed to use artificial intelligence (AI) to predict psychological distress among workers using sociodemographic, lifestyle and sleep factors, not subjective information such as mood and emotion, and to examine the performance of the AI models through a comparison with psychiatrists.DesignCross-sectional study.SettingWe conducted a survey on psychological distress and living conditions among workers. An AI model for predicting psychological distress was created and then the results were compared in terms of accuracy with predictions made by psychiatrists.ParticipantsAn AI model of the neural network and six psychiatrists.Primary outcomeThe accuracies of the AI model and psychiatrists for predicting psychological distress.MethodsIn total, data from 7251 workers were analysed to predict moderate and severe psychological distress. An AI model of the neural network was created and accuracy, sensitivity and specificity were calculated. Six psychiatrists used the same data as the AI model to predict psychological distress and conduct a comparison with the AI model.ResultsThe accuracies of the AI model and psychiatrists for predicting moderate psychological distress were 65.2% and 64.4%, respectively, showing no significant difference. The accuracies of the AI model and psychiatrists for predicting severe psychological distress were 89.9% and 85.5%, respectively, indicating that the AI model had significantly higher accuracy.ConclusionsA machine learning model was successfully developed to screen workers with depressed mood. The explanatory variables used for the predictions did not directly ask about mood. Therefore, this newly developed model appears to be able to predict psychological distress among workers easily, regardless of their subjective views.

Sign in / Sign up

Export Citation Format

Share Document