A Machine Learning-Based Screening Test for Sarcopenic Dysphagia Using Image Recognition

Background: Sarcopenic dysphagia, a swallowing disorder caused by sarcopenia, is prevalent in older patients and can cause malnutrition and aspiration pneumonia. This study aimed to develop a simple screening test using image recognition with a low risk of droplet transmission for sarcopenic dysphagia. Methods: Older patients admitted to a post-acute care hospital were enrolled in this cross-sectional study. As a main variable for the development of a screening test, we photographed the anterior neck to analyze the image features of sarcopenic dysphagia. The studied image features included the pixel values and the number of feature points. We constructed screening models using the image features, age, sex, and body mass index. The prediction performance of each model was investigated. Results: A total of 308 patients participated, including 175 (56.82%) patients without dysphagia and 133 (43.18%) with sarcopenic dysphagia. The area under the receiver operating characteristic curve (ROC-AUC), sensitivity, specificity, positive predictive value, negative predictive value, and area under the precision-recall curve (PR-AUC) values of the best model were 0.877, 87.50%, 76.67%, 66.67%, 92.00%, and 0.838, respectively. The model with image features alone showed an ROC-AUC of 0.814 and PR-AUC of 0.726. Conclusions: The screening test for sarcopenic dysphagia using image recognition of neck appearance had high prediction performance.

Download Full-text

Ultrasound Employed to Detect Breast Lumps among Symptomatic Patients in Tertiary Care Hospital

Journal of Bahria University Medical and Dental College ◽

10.51985/jbumdc2020032 ◽

2020 ◽

Vol 10 (4) ◽

pp. 296-300

Author(s):

Ameet Jesrani ◽

Pari Gul ◽

Nida Khan ◽

Seema Nayab ◽

Fahmida Naheed

Keyword(s):

Predictive Value ◽

Imaging Modality ◽

Tertiary Care ◽

Ultra Sound ◽

Categorical Variables ◽

Breast Lesions ◽

Care Hospital ◽

Continuous Variables ◽

Cross Sectional ◽

Breast Lumps

Objective: To assess different pathological breast lesions in ultra sound in a subgroup of population. Study design and setting: It was a cross sectional study conducted at Bolan Medical Complex Hospital Quetta, Pakistan from June 2018 to January 2019. Methodology: Total 103 patients with breast swelling, pain and discharge were targeted. Gray scale and Doppler Ultrasound of breast followed by FNAC/biopsy of breast lesion was performed. Data presented as mean ± standard deviation for continuous variables and frequency with percentages for categorical variables. Results: Out of 48 clinically palpable lumps US detected all of 48 lumps and additionally 12 clinically non palpable masses were detected on US examination. Thus, overall sensitivity of ultrasound in detecting breast lumps was 100%. Fibroadenoma of the breast was diagnosed accurately in 80.3% of women. Ultrasound reliably differentiated cystic from solid breast masses (100%). The sensitivity of ultrasound for detecting breast carcinoma was 63.4% with a positive predictive value of 87.5%, a negative predictive value of 99.5% and accuracy of 58.33%. US findings most suggestive of benign lesions were oval or round shape in 88.3%, well defined margin in 84%, absent lobulation in 86.04% and wider than taller ratio in 90.69% of the cases.US findings of most predictive for malignancy were of irregular shape in 81.8%, ill-defined margin in 90.9% and length to height ratio in 63.6% of cases. Conclusion: Ultrasound is simple, cheap, safe and relatively accessible imaging modality for evaluation of breast pathologies. Due to its high sensitivity in diagnosing benign breast lesions particularly cystic lesions and fibroadenoma unnecessary interventions can be avoided

Download Full-text

Evaluating Specivity, Sensitivity, Positive and Negative Predictive Values of CA125 for Diagnosing Ovarian Cancer

Journal of Arak University of Medical Sciences ◽

10.32598/jams.24.2.6002.1 ◽

2021 ◽

Vol 24 (2) ◽

pp. 196-203

Author(s):

Elahe Fini ◽

◽

Neda Nasirian ◽

Bahram Hosein Beigy ◽

◽

...

Keyword(s):

Ovarian Cancer ◽

Positive Predictive Value ◽

Tumor Marker ◽

Negative Predictive Value ◽

Predictive Value ◽

Screening Test ◽

High Sensitivity ◽

Medical Community ◽

Cross Sectional ◽

Predictive Values

Background and Aim: Ovarian cancer is among the most common cancers in women worldwide. CA125 is the most frequent biomarker used in the screening for ovarian cancer. CA125 has no high sensitivity and specificity as a screening test in the medical community; however, because of being simple and noninvasive, it is almost always requested for evaluation and ruling out cancer. It plays an important role in the treatment and post-treatment process, the prediction of prognosis, and the relapse of the disease. The present study aimed to determine the relationship between a high level of CA125 tumor marker and ovarian cancer by detecting spesivity, sensivity, positive and negative predictive values. Methods & Materials: In this cross-sectional study, all cases undergoing CA125 test in Velayat Hospital in 2017-1028 were evaluated for having ovarian cancer. In addition, the CA125 level was compared between healthy individuals and patients with ovarian cancer. Finally, the obtained data were analyzed using SPSS. Ethical Considerations: The present study was approved by the Qazvin University of Medical Sciences (Ethics Code: IR.QUMS.REC.1396.316). Results: In this study, 35.3% of the study participants received a definite diagnosis of ovarian cancer. Generally, CA125 values were negative in 41.8% and positive in.58.2% of the study subjects. The sensitivity of the test was measured as 80.1%, the specivity as 53.6%, the positive predictive value equaled 48.4%, and the negative predictive value was measured as 83%. There was a significant relationship between age and the presence of ovarian cancer, and serum CA125 levels. Conclusion: The present study suggested that age and the serum level of CA125 were statistically significant. Finally, CA125 levels were significantly related to ovarian cancer. It provided moderate specivity and specivity as well as low positive predictive value and high negative predictive value as a tumor marker; it is valuable for ruling out of tumor but not appropriate as a screening test.

Download Full-text

Diagnostic accuracy of IGF-1 for screening growth hormone deficiency: a prospective, single-center, diagnostic accuracy study

10.21203/rs.3.rs-430014/v1 ◽

2021 ◽

Author(s):

Hideyuki Iwayama ◽

Sachiko Kitagawa ◽

Jyun Sada ◽

Ryosuke Miyamoto ◽

Tomohito Hayakawa ◽

...

Keyword(s):

Growth Hormone ◽

Diagnostic Accuracy ◽

Growth Hormone Deficiency ◽

Predictive Value ◽

Screening Test ◽

Characteristic Curve ◽

Area Under The Curve ◽

Rank Correlation ◽

Hormone Deficiency ◽

Height Velocity

Abstract Purpose We evaluated the diagnostic accuracy of insulin-like growth factor-1 (IGF-1) for screening growth hormone deficiency (GHD) to determine the usefulness of IGF-1 as a screening test. Methods On 298 consecutive children who had short stature or decreased height velocity, we measured IGF-1 levels and performed growth hormone (GH) secretion test using clonidine, arginine, and, in cases with different results of the two tests, L-dopa. Patients with congenital abnormalities were excluded. GHD was defined as peak GH ≤ 6.0 ng/mL in the two tests. Results We identified 60 and 238 patients with and without GHD, respectively. The mean IGF-1 (SD) was not significantly different between the GHD and non-GHD groups (p = 0.23). Receiver operating characteristic curve analysis demonstrated the best diagnostic accuracy at an IGF-1 cutoff of −1.493 SD, with sensitivity of 0.685, specificity of 0.417, positive predictive value of 0.25, negative predictive value of 0.823, and area under the curve of 0.517. Spearman’s rank correlation coefficient showed that IGF-1 (SD) was weakly correlated with age, bone age, height velocity before examination, weight (SD), and BMI (SD) and very weakly correlated with height (SD), target height (SD), and maximum GH peak. Conclusion IGF-1 level had poor diagnostic accuracy as a screening test for GHD. Correlation analysis revealed that none of the items increased the diagnostic power of IGF-1. Therefore, IGF-1 should not be used alone in the screening of GHD. A predictive biomarker for GHD should be developed in the future.

Download Full-text

Anthropometric parameters’ cut-off points and predictive value for metabolic syndrome in women from Cartagena, Colombia

Salud Pública de México ◽

10.21149/spm.v56i2.7330 ◽

2014 ◽

Vol 56 (2) ◽

pp. 146 ◽

Cited By ~ 10

Author(s):

Gustavo José Mora-García ◽

Doris Gómez-Camargo ◽

Enrique Mazenett ◽

Ángelo Alario ◽

Álvaro Fortich ◽

...

Keyword(s):

Metabolic Syndrome ◽

Latin American ◽

Predictive Value ◽

Characteristic Curve ◽

Cross Sectional Study ◽

Adult Women ◽

Anthropometric Parameters ◽

Cross Sectional ◽

Body Adiposity ◽

Cartagena De Indias

Objective. To estimate anthropometric parameters’ (APs) cut-off points and association for metabolic syndrome (MetS). Materials and methods. A cross-sectional study was carried out with a total of 434 adult women from Cartagena de Indias, Colombia, in 2012. APs measured were waist circumference (WC), body mass index (BMI), body adiposity index (BAI), waist-hip ratio (WHR) and waist-height ratio (WHtR). Cut-off points were estimated by a receiver operating characteristic curve (ROC). Logistic regression was applied to estimate possible associations. Results. Cut-off points for WC, BMI, BAI, WHR and WHtR were 85 cm, 28 kg/m2, 39%, 0.80 and 56, respectively. Only WHtR was associated to MetS (OR=1.11, CI95% [1.07-1.15]). Conclusion. WC cut-off point was higher than those proposed for Latin-American women by the Joint Interim Statement (JIS). WHtR had a low predictive value for MetS.

Download Full-text

Development of the Brief Bedside Dysphagia Screening Test – Revised: a Cross-Sectional Czech Study

Acta Medica (Hradec Kralove Czech Republic) ◽

10.14712/18059694.2015.93 ◽

2015 ◽

Vol 58 (2) ◽

pp. 49-55 ◽

Cited By ~ 7

Author(s):

Petra Mandysová ◽

Edvard Ehler ◽

Jana Škvrňáková ◽

Michal Černý ◽

Iva Bártová ◽

...

Keyword(s):

Negative Predictive Value ◽

Predictive Value ◽

Gold Standard ◽

Screening Test ◽

High Sensitivity ◽

Endoscopic Examination ◽

Swallowing Function ◽

Cross Sectional ◽

Neurological Conditions ◽

Nose And Throat

Aim: The purpose of this study was to develop a revised version of the Brief Bedside Dysphagia Screening Test for determining penetration/aspiration risk in patients prone to dysphagia. The priority was to achieve high sensitivity and negative predictive value. Methods: The study screeners conducted bedside assessment of the swallowing function in 157 patients with a neurological (mainly stroke) or an ear, nose, and throat diagnosis (mainly head and neck cancer). The results were compared with a gold standard, flexible endoscopic examination of swallowing. Results: For the neurological subgroup (N = 106), eight statistically significant bedside assessment items were combined into the Brief Bedside Dysphagia Screening Test-Revised (BBDST-R). Cut-off score 1 produced the highest sensitivity (95.5%; 95% confidence interval CI [CI]: 84.9–98.7%) and negative predictive value (88.9%; 95% CI 67.2–96.9%). Conclusion: The BBDST-R is suitable for dysphagia screening in departments caring for patients with neurological conditions.

Download Full-text

INNV-11. GLIOBLASTOMA IN THE OLDER PERSON – HOW DO WE DECIDE ON TREATMENT?

Neuro-Oncology ◽

10.1093/neuonc/noaa215.494 ◽

2020 ◽

Vol 22 (Supplement_2) ◽

pp. ii118-ii118

Author(s):

Cressida Lorimer ◽

Anthony Chalmers ◽

Margaret Johnson ◽

Juliet Brock

Keyword(s):

Screening Test ◽

Older Patients ◽

Performance Status ◽

Treatment Options ◽

Treatment Decision ◽

Treatment Decisions ◽

Clinical Factor ◽

Cross Sectional ◽

Multiple Treatment ◽

The Impact

Abstract The incidence of glioblastoma (GBM) peaks in the 7th and 8th decades of life. Multiple treatment options exist for older patients with GBM however, the assessment of older patients prior to treatment decisions is poorly researched and lacks standardization. In order to address this issue we performed a cross-sectional electronic survey distributed to all full members of the Society for Neuro-Oncology. There were 116 respondents from a total of 1515 recipients (8% response rate). The survey was distributed during the peak of COVID-19 which undoubtedly affected response rates. 97% of respondents were clinicians with 86% academic. 72% had been in practice > 10 years and the majority saw 5–10 new GBM cases per month. 95% of respondents were from the USA, with involvement from Japan, Australia, Canada and Italy. 37% of respondents routinely perform a cognitive or frailty screening test. Of these, MMSE and MoCA were the most commonly used. Of those who performed a screening test, the majority reported that the results changed their treatment decision in approximately 50% of cases. 50% of respondents have access to a multidisciplinary team during their clinic, with physical therapy being the most available. When making treatment decisions, participants ranked performance status as the most important clinical factor. Considering the heterogeneity of this patient population, we argue that performance status is a crude measure of vulnerability within this cohort. In the first survey of this kind, we have shown a disparity in assessment techniques across the international neuro-oncology field and the impact performing a cognitive screen has on decision making. Older patients with GBM represent a unique clinical scenario because of the complexity of distinguishing neuro- oncology related symptoms from general frailty. There is a need for specific geriatric assessment models tailored to the older neuro-oncology population in order to facilitate treatment decisions.

Download Full-text

Lung ultrasound for the diagnosis of cystic fibrosis pulmonary exacerbation

BMC Pulmonary Medicine ◽

10.1186/s12890-021-01728-8 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Maryam Hassanzad ◽

Arda Kiani ◽

Atefeh Abedini ◽

Hoseinali Ghaffaripour ◽

Habib Emami ◽

...

Keyword(s):

Cystic Fibrosis ◽

Predictive Value ◽

Diagnostic Performance ◽

Lung Ultrasound ◽

Characteristic Curve ◽

Cross Sectional Study ◽

Pulmonary Exacerbation ◽

High Resolution Computed Tomography ◽

Cross Sectional ◽

Pleural Thickening

Abstract Background High-resolution computed tomography (HRCT) is the gold standard for the evaluation of cystic fibrosis (CF) lung disease; however, lung ultrasound (LUS) is being increasingly used for the assessment of lung in these patients due to its lower cost, availability, and lack of irradiation. We aimed to determine the diagnostic performance of LUS for the evaluation of CF pulmonary exacerbation. Methods This cross-sectional study included patients with CF pulmonary exacerbation admitted to Masih Daneshvari Hospital, Tehran, Iran, from March 21, 2020 to March 20, 2021. Age, gender, and body mass index (BMI) of the patients were recorded. All patients underwent chest X-ray (CXR), HRCT, and LUS on admission. Pleural thickening, atelectasis, air bronchogram, B-line, and consolidation were noted in LUS and then compared with the corresponding findings in CXR and HRCT. Taking HRCT findings as reference, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy (DA) of LUS and CXR for the detection of each pulmonary abnormality were determined. Results Of the 30 patients included in this study, with a mean age of 19.62 ± 5.53 years, 14 (46.7%) were male. Of the 15 patients aged 2–20 years, BMI was below the 5th percentile in 10 (66.7%), within the 5–10 percentiles in 1 (6.7%), 10–25 percentiles in 3 (20%), and 25-50 percentiles in 1 (6.7%). The mean BMI for 15 patients > 20 years was 18.03 ± 2.53 kg/m2. LUS had better diagnostic performance compared to CXR for the detection of air bronchogram, consolidation, and pleural thickening (area under the receiver operating characteristic curve [AUROC]: 0.966 vs. 0.483, 0.900 vs. 0.575, and 0.656 vs. 0.531, respectively). Also, LUS was 100% and 96.7% specific for the diagnosis of pleural effusion and atelectasis, respectively. Conclusions LUS appears to be superior to CXR and comparable with HRCT for the evaluation of CF pulmonary exacerbation, especially in terms of air bronchogram and consolidation detection. LUS can be used to lengthen the HRCT evaluation intervals in this regard or utilized along with HRCT for better evaluation of CF pulmonary exacerbation.

Download Full-text

Validity of Immunochromatographic Test for Antibody in Diagnosis of Typhoid Fever in Children Admitted in A Tertiary Care Hospital

Chattagram Maa-O-Shishu Hospital Medical College Journal ◽

10.3329/cmoshmcj.v16i2.37288 ◽

2018 ◽

Vol 16 (2) ◽

pp. 20-24

Author(s):

Zabeen Choudhury ◽

Mohammed Rezaul Karim ◽

Rasheda Samad ◽

Shanjana Islam

Keyword(s):

Blood Culture ◽

Typhoid Fever ◽

Predictive Value ◽

Tertiary Care ◽

False Negative ◽

Care Hospital ◽

Immunochromatographic Test ◽

True Negative ◽

College Hospital ◽

Cross Sectional

Background: To determine the Validity of Immunochromatographic Test (ICT) in diagnosis of typhoid fever in children admitted in a tertiary care hospital.Methods: This cross sectional study was carried out the in Pediatric & Medicine wards of Chittagong Medical College Hospital (CMCH), Chittagong during the period July 2012 to June 2013. A total number of 150 clinically suspected cases of typhoid fever (Age >6 months to18 years) were enrolled in this study. After taking informed written consent, detailed history & clinical examination were completed. A blood culture sample was taken on the day of admission before starting antibiotic. On the 5th day onwards of appearance of fever, blood sample was taken to perform ICT. Patients received standard medical treatment of the admitting wards.Results: Blood C/S for Salmonella typhi was found positive in 16(10.7%) cases. Positive ICT for typhoid fever was found in 37(24.7%) cases. Among then, IgM was 18(12.0%) IgM+IgG were 8(5.3%) and IgG was 11(7.3%). ICT found true positive in 14, false positive in 23, false negative in 2 and true negative in 111 cases, where blood culture considered as gold standard. The difference was statistically significant (p<0.05) between two groups. Immunochromatographic Test (ICT) showed sensitivity 87.5%, specificity 82.8%, accuracy 83.3%, positive predictive value 37.8% and negative predictive value 98.2% for identification of typhoid fever.Conclusion: The present study has shown high sensitivity & specificity of ICT, it can be used as a useful & prospectful diagnostic tool.Chatt Maa Shi Hosp Med Coll J; Vol.16 (2); July 2017; Page 20-24

Download Full-text

Ratio of height to thyromental distance: a comparison with Mallampati and Upper lip Bite test for predicting difficult intubation in Pakistani population

Journal of the Pakistan Medical Association ◽

10.47391/jpma.1215 ◽

2021 ◽

pp. 1-15

Author(s):

Saman Tauheed Ali ◽

Khalid Samad ◽

Syed Amir Raza ◽

Muhammad Qamarul Hoda

Keyword(s):

Predictive Value ◽

Characteristic Curve ◽

Cross Sectional Study ◽

Difficult Laryngoscopy ◽

University Hospital ◽

Upper Lip ◽

Cross Sectional ◽

Elective Surgical Procedures ◽

Lehane Grade ◽

Sensitivity Specificity

Objectives: We conducted this study to compare the accuracy of three diagnostic tests; ratio of height to thyromental distance (RHTMD), Modified Mallampati Test (MMT) and Upper Lip Bite Test (ULBT) in predicting difficult laryngoscopy using Cormack and Lehane grade as gold standard.Methods: This study was conducted in Aga Khan University Hospital, Karachi. Based on calculated sample size, 383 patients who required endotracheal intubation for elective surgical procedures were enrolled with consecutive sampling techniques during August 2014 to August 2015 for this cross-sectional study. Primary investigator used RHTMD, ULBT, and MMT for assessing the airway and correlated with laryngoscopic view.Results: A total of 383 patients were incorporated in this research, out of which 59(15.4%) classified as difficult laryngoscopy based on Cormack and Lehane (CL) grading. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy of RHTMD (84.7%, 90.1%, 60.9%, 97%, 89.3%) and ULBT (83.1%, 89.2%, 58.3%, 96.7%, 88.3%) values were highest as compared to MMT (30.5%, 84.3%, 26.1%, 86.9%, 79.9%). The area under a receiver-operating characteristic curve (AUC of ROC curve) for ULBT and RHTMD was significantly more than for MMT (P<0.01). RHTMD and ULBT both are acceptable alternatives for prediction of difficult laryngoscopy as a simple, single bed-side test. Continuous...

Download Full-text

Association and Predictive Value Analysis for Resting Heart Rate and Diabetes Mellitus on Cardiovascular Autonomic Neuropathy in General Population

Journal of Diabetes Research ◽

10.1155/2014/215473 ◽

2014 ◽

Vol 2014 ◽

pp. 1-7 ◽

Cited By ~ 7

Author(s):

Zi-Hui Tang ◽

Fangfang Zeng ◽

Zhongtao Li ◽

Linuo Zhou

Keyword(s):

General Population ◽

Predictive Value ◽

Large Scale ◽

Reference Group ◽

Characteristic Curve ◽

Predictive Performance ◽

Population Based ◽

Cross Sectional Study ◽

Cross Sectional ◽

Value Analysis

Background.The purpose of this study was to evaluate the predictive value of DM and resting HR on CAN in a large sample derived from a Chinese population.Materials and Methods.We conducted a large-scale, population-based, cross-sectional study to explore the relationships of CAN with DM and resting HR. A total of 387 subjects were diagnosed with CAN in our dataset. The associations of CAN with DM and resting HR were assessed by a multivariate logistic regression (MLR) analysis (using subjects without CAN as a reference group) after controlling for potential confounding factors. The area under the receiver-operating characteristic curve (AUC) was used to evaluate the predictive performance of resting HR and DM.Results.A tendency toward increased CAN prevalence with increasing resting HR was reported (Pfor trend<0.001). MLR analysis showed that DM and resting HR were very significantly and independently associated with CAN (P<0.001for both). Resting HR alone or combined with DM (DM-HR) both strongly predicted CAN (AUC = 0.719, 95% CI 0.690–0.748 for resting HR and AUC = 0.738, 95% CI 0.710–0.766 for DM-HR).Conclusion.Our findings signify that resting HR and DM-HR have a high value in predicting CAN in the general population.

Download Full-text