scholarly journals Predicting Frailty and Geriatric Interventions in Older Cancer Patients: Performance of Two Screening Tools for Seven Frailty Definitions—ELCAPA Cohort

Cancers ◽  
2022 ◽  
Vol 14 (1) ◽  
pp. 244
Author(s):  
Claudia Martinez-Tapia ◽  
Marie Laurent ◽  
Elena Paillaud ◽  
Philippe Caillet ◽  
Emilie Ferrat ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Diagnostic Performance ◽  
Latent Class ◽  
Task Force ◽  
Characteristic Curve ◽  
Frailty Index ◽  
Geriatric Oncology ◽  
Reference Standards ◽  
Screening Tools ◽  
Geriatric Intervention

Screening tools have been developed to identify patients warranting a complete geriatric assessment (GA). However, GA lacks standardization and does not capture important aspects of geriatric oncology practice. We measured and compared the diagnostic performance of screening tools G8 and modified G8 according to multiple clinically relevant reference standards. We included 1136 cancer patients ≥ 70 years old referred for GA (ELCAPA cohort; median age, 80 years; males, 52%; main locations: digestive (36.3%), breast (16%), and urinary tract (14.8%); metastases, 43.5%). Area under the receiver operating characteristic curve (AUROC) estimates were compared between both tools against: (1) the detection of ≥1 or (2) ≥2 GA impairments, (3) the prescription of ≥1 geriatric intervention and the identification of an unfit profile according to (4) a latent class typology, expert-based classifications from (5) Balducci, (6) the International Society of Geriatric Oncology task force (SIOG), or using (7) a GA frailty index according to the Rockwood accumulation of deficits principle. AUROC values were ≥0.80 for both tools under all tested definitions. They were statistically significantly higher for the modified G8 for six reference standards: ≥1 GA impairment (0.93 vs. 0.89), ≥2 GA impairments (0.90 vs. 0.87), ≥1 geriatric intervention (0.85 vs. 0.81), unfit according to Balducci (0.86 vs. 0.80) and SIOG classifications (0.88 vs. 0.83), and according to the GA frailty index (0.86 vs. 0.84). Our findings demonstrate the robustness of both screening tools against different reference standards, with evidence of better diagnostic performance of the modified G8.

Diagnostic usefulness of differential time to positivity in neutropenic cancer patients with suspected catheter-related candidemia

2019 ◽  
Vol 58 (1) ◽  
pp. 137-140
Author(s):  
Kyeong Min Jo ◽  
Sungim Choi ◽  
Kyung Hwa Jung ◽  
Jung Wan Park ◽  
Ji Hyun Yun ◽  
...  
Keyword(s):  
Confidence Interval ◽  
Cancer Patients ◽  
Diagnostic Performance ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Optimal Cutoff ◽  
Cutoff Value ◽  
Time To Positivity ◽  
Diagnostic Usefulness ◽  
Operating Characteristic Curve

Abstract Methods for distinguishing catheter-related candidemia (CRC) from non-CRC before catheter removal remain limited. We thus evaluated the diagnostic performance of differential time to positivity (DTP) to diagnose CRC in neutropenic cancer patients with suspected CRC. Of the 35 patients enrolled, 15 (43%) with CRC (six definite and nine probable) and 17 (49%) with non-CRC were finally analyzed. Based on the receiver operating characteristic curve, the optimal cutoff value of DTP for diagnosing CRC was ≥1.45 hours with the sensitivity 80% (95% confidence interval [CI], 51–95) and specificity 100% (95% CI, 80–100), respectively.

scholarly journals “SQiD, the Single Question in Delirium; can a single question help clinicians to detect delirium in hospitalised cancer patients?” running heading Single Question in Delirium” (Bcan-D-20-01665)

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Megan B. Sands ◽  
Swapnil Sharma ◽  
Lindsay Carpenter ◽  
Andrew Hartshorn ◽  
Jessica T. Lee ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Clinical Care ◽  
Length Of Hospital Stay ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Clinical Staff ◽  
Screening Tools ◽  
Diagnostic Values ◽  
D 20 ◽  
Single Question

Abstract Aim A serious syndrome for cancer in-patients, delirium risk increases with age and medical acuity. Screening tools exist but detection is frequently delayed or missed. We test the ‘Single Question in Delirium’ (SQiD), in comparison to psychiatrist clinical interview. Methods Inpatients in two comprehensive cancer centres were prospectively screened. Clinical staff asked informants to respond to the SQiD: “Do you feel that [patient’s name] has been more confused lately?”. The primary endpoint was negative predictive value (NPV) of the SQiD versus psychiatrist diagnosis (Diagnostic and Statistics Manual criteria). Secondary endpoints included: NPV of the Confusion Assessment Method (CAM), sensitivity, specificity and Cohen’s Kappa coefficient. Results Between May 2012 and July 2015, the SQiD plus CAM was applied to 122 patients; 73 had the SQiD and psychiatrist interview. Median age was 65 yrs. (interquartile range 54–74), 46% were female; median length of hospital stay was 12 days (5–18 days). Major cancer types were lung (19%), gastric or other upper GI (15%) and breast (14%). 70% of participants had stage 4 cancer. Diagnostic values were similar between the SQiD (NPV = 74, 95% CI 67–81; kappa = 0.32) and CAM (NPV = 72, 95% CI 67–77, kappa = 0.32), compared with psychiatrist interview. Overall the CAM identified only a small number of delirious cases but all were true positives. The specificity of the SQiD was 87% (74–95) The SQiD had higher sensitivity than CAM (44% [95% CI 41–80] vs 26% [10–48]). Conclusion The SQiD, administered by bedside clinical staff, was feasible and its psychometric properties are now better understood. The SQiD can contribute to delirium detection and clinical care for hospitalised cancer patients.

419 STOP-Bang Score and History of Radiation Predicts Risk of Obstructive Sleep Apnea in Cancer Patients: A Machine Learning Study

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A166-A166
Author(s):  
Ankita Paul ◽  
Karen Wong ◽  
Anup Das ◽  
Diane Lim ◽  
Miranda Tan
Keyword(s):  
Machine Learning ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Cancer Patients ◽  
Prediction Accuracy ◽  
Screening Tools ◽  
Cancer Type ◽  
Sleep Study ◽  
Obstructive Sleep ◽  
History Of

Abstract Introduction Cancer patients are at an increased risk of moderate-to-severe obstructive sleep apnea (OSA). The STOP-Bang score is a commonly used screening questionnaire to assess risk of OSA in the general population. We hypothesize that cancer-relevant features, like radiation therapy (RT), may be used to determine the risk of OSA in cancer patients. Machine learning (ML) with non-parametric regression is applied to increase the prediction accuracy of OSA risk. Methods Ten features namely STOP-Bang score, history of RT to the head/neck/thorax, cancer type, cancer stage, metastasis, hypertension, diabetes, asthma, COPD, and chronic kidney disease were extracted from a database of cancer patients with a sleep study. The ML technique, K-Nearest-Neighbor (KNN), with a range of k values (5 to 20), was chosen because, unlike Logistic Regression (LR), KNN is not presumptive of data distribution and mapping function, and supports non-linear relationships among features. A correlation heatmap was computed to identify features having high correlation with OSA. Principal Component Analysis (PCA) was performed on the correlated features and then KNN was applied on the components to predict the risk of OSA. Receiver Operating Characteristic (ROC) - Area Under Curve (AUC) and Precision-Recall curves were computed to compare and validate performance for different test sets and majority class scenarios. Results In our cohort of 174 cancer patients, the accuracy in determining OSA among cancer patients using STOP-Bang score was 82.3% (LR) and 90.69% (KNN) but reduced to 89.9% in KNN using all 10 features mentioned above. PCA + KNN application using STOP-Bang score and RT as features, increased prediction accuracy to 94.1%. We validated our ML approach using a separate cohort of 20 cancer patients; the accuracies in OSA prediction were 85.57% (LR), 91.1% (KNN), and 92.8% (PCA + KNN). Conclusion STOP-Bang score and history of RT can be useful to predict risk of OSA in cancer patients with the PCA + KNN approach. This ML technique can refine screening tools to improve prediction accuracy of OSA in cancer patients. Larger studies investigating additional features using ML may improve OSA screening accuracy in various populations Support (if any):

scholarly journals 20 Comparison of Six Frailty Screening Tools in Patients Aged 65+ with An Arm Fragility Fracture

2021 ◽  
Vol 50 (Supplement_1) ◽  
pp. i1-i6
Author(s):  
K Ibrahim ◽  
T Lim ◽  
M A Mullee ◽  
G L Yao ◽  
S Zhu ◽  
...  
Keyword(s):  
Fragility Fracture ◽  
Frailty Index ◽  
Screening Tools ◽  
Frailty Phenotype ◽  
Fracture Clinic ◽  
Increased Risk ◽  
Sensitivity Range ◽  
Practical Tool ◽  
Acute Trust ◽  
Medication Changes

Abstract Introduction Frailty is associated with an increased risk of falling and fracture, but not routinely assessed in fracture clinic. Early identification and management of frailty among older people with arm fragility fracture could help avoid further falls and fractures, especially of the hip. We evaluated the feasibility of assessing frailty in a busy fracture clinic. Methods People aged 65+ years with an arm fracture in one acute trust were recruited. Frailty was assessed in fracture clinics using six tools: Fried Frailty Phenotype (FFP), FRAIL scale, PRISMA-7, electronic Frailty Index (e-FI), Clinical Frailty Score (CFS), and Study of Osteoporotic Fracture (SOF). The sensitivity and specificity of each tool was compared against FFP as a reference. Participants identified as frail by 2+ tools were referred for Comprehensive Geriatric Assessment (CGA). Results 100 patients (mean age 75 years±7.2; 20 men) were recruited. Frailty prevalence was 9% (FRAIL scale), 13% (SOF), 14% (CFS > 6), 15% (FFP; e-FI > 0.25), and 25% (PRISMA-7). Men were more likely to be frail than women. Data were complete for all assessments and completion time ranged from one minute (PRISMA-7; CFS) to six minutes for the FFP which required most equipment. Comparing with FFP, the most accurate instrument for stratifying frail from non-frail was the PRISMA-7 (sensitivity = 93%, specificity = 87%) while the remaining tools had good specificity (range 93%–100%) but average sensitivity (range 40%–60%). Twenty patients were eligible for CGA. Five had recently had CGA and 11/15 referred were assessed. CGA led to 3–6 interventions per participant including medication changes, life-style advice, investigations, and onward referrals. Conclusion It was feasible to assess frailty in fracture clinic and to identify patients who benefitted from CGA. Frailty prevalence was 9%—25% depending on the tool used and was higher among men. PRISMA-7 could be a practical tool for routine use in fracture clinics.

scholarly journals Diagnostic utility of alarm features in predicting malignancy in patients with dyspeptic symptoms

2021 ◽  
Author(s):  
Anurag Shetty ◽  
Girisha Balaraju ◽  
Shiran Shetty ◽  
Cannanore Ganesh Pai
Keyword(s):  
Weight Loss ◽  
Epigastric Pain ◽  
Characteristic Curve ◽  
Abdominal Mass ◽  
Screening Tools ◽  
Disease Epidemiology ◽  
Dyspeptic Symptoms ◽  
Malignant Lesions ◽  
Alarm Features ◽  
Gastric Malignancy

Abstract Background Clinical features are of modest benefit in determining the etiology of dyspepsia. Dyspeptic patients with alarm features are suspected to have malignancy; but the proportions of patients and true cutoff values of various quantitative parameters in predicting malignancy are explored to a lesser extent. Methods This is a prospective observational study of consecutive patients undergoing esophagogastroduodenoscopy (EGD) for dyspeptic symptoms. Patients’ alarm features and clinical details were recorded in a predesigned questionnaire. The diagnostic accuracy of alarm features in predicting malignancy was studied. Results Nine hundred patients, 678 (75.3%) males, with a mean (standard deviation [SD]) age of 44.6 (13.54) years were enrolled. Commonest indication for EGD was epigastric pain in 614 (68.2%) patients. Dyspepsia was functional in 311 (34.6%) patients. EGD revealed benign lesions in 340 (37.8%) and malignancy in 50 (5.5%) patients. Among the malignant lesions, gastric malignancy was present in 28 (56%) and esophageal malignancy in 20 (40%) patients. Alarm features were present in 206 (22.9%), out of which malignant lesions were seen in 46 (22.3%) patients. Altogether, the alarm features had a sensitivity of 92% and specificity of 81.2% for predicting malignancy. The sensitivity and specificity for weight loss were 76% and 90.8%, while that of abdominal mass were 10% and 99.9% respectively. Based on receiver operating characteristic curve, the optimal age for screening of malignancy was 46.5 years in this population. Conclusions Patients of age group 40 to 49 years with dyspeptic alarm symptoms (predominant weight loss) need prompt endoscopy to screen for malignancy. The alarm features are inexpensive screening tools, found to be useful in India, and should be utilized in countries with similar healthcare conditions and disease epidemiology.

scholarly journals Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 786
Author(s):  
Daniel M. Lang ◽  
Jan C. Peeken ◽  
Stephanie E. Combs ◽  
Jan J. Wilkens ◽  
Stefan Bartzsch
Keyword(s):  
Deep Learning ◽  
Cancer Patients ◽  
Oropharyngeal Cancer ◽  
Characteristic Curve ◽  
Learning Models ◽  
Convolutional Network ◽  
Hpv Status ◽  
3D Information ◽  
External Test

Infection with the human papillomavirus (HPV) has been identified as a major risk factor for oropharyngeal cancer (OPC). HPV-related OPCs have been shown to be more radiosensitive and to have a reduced risk for cancer related death. Hence, the histological determination of HPV status of cancer patients depicts an essential diagnostic factor. We investigated the ability of deep learning models for imaging based HPV status detection. To overcome the problem of small medical datasets, we used a transfer learning approach. A 3D convolutional network pre-trained on sports video clips was fine-tuned, such that full 3D information in the CT images could be exploited. The video pre-trained model was able to differentiate HPV-positive from HPV-negative cases, with an area under the receiver operating characteristic curve (AUC) of 0.81 for an external test set. In comparison to a 3D convolutional neural network (CNN) trained from scratch and a 2D architecture pre-trained on ImageNet, the video pre-trained model performed best. Deep learning models are capable of CT image-based HPV status determination. Video based pre-training has the ability to improve training for 3D medical data, but further studies are needed for verification.

GERIATRIC-ONCOLOGY ASSESSMENT FOR COMPLEX CANCER PATIENTS MANAGEMENT IN RADIATION ONCOLOGY UNIT

2019 ◽  
Vol 10 (6) ◽  
pp. S53
Author(s):  
A. Bellieni ◽  
G.F. Colloca ◽  
B. Di Capua ◽  
D. Fusco ◽  
M.A. Gambacorta ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Radiation Oncology ◽  
Geriatric Oncology ◽  
Oncology Unit
Sign in / Sign up

Export Citation Format

Share Document