Search Articles

View query in Help articles search

Search Results (1 to 10 of 11 Results)

Download search results: CSV END BibTex RIS


Natural Language Processing Versus Diagnosis Code–Based Methods for Postherpetic Neuralgia Identification: Algorithm Development and Validation

Natural Language Processing Versus Diagnosis Code–Based Methods for Postherpetic Neuralgia Identification: Algorithm Development and Validation

We counted the numbers of true-positive (TP), false-positive (FP), true-negative (TN), and false-negative (FN) cases to calculate the performance metrics: sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F-score [28], and Matthews correlation coefficient (MCC) [29]. The F-score is a combination metric in machine learning and NLP research.

Chengyi Zheng, Bradley Ackerson, Sijia Qiu, Lina S Sy, Leticia I Vega Daily, Jeannie Song, Lei Qian, Yi Luo, Jennifer H Ku, Yanjun Cheng, Jun Wu, Hung Fu Tseng

JMIR Med Inform 2024;12:e57949

The Clinical Suitability of an Artificial Intelligence–Enabled Pain Assessment Tool for Use in Infants: Feasibility and Usability Evaluation Study

The Clinical Suitability of an Artificial Intelligence–Enabled Pain Assessment Tool for Use in Infants: Feasibility and Usability Evaluation Study

The test cutoff value was assigned as the point where sensitivity equals specificity [16]. For each cutoff score, sensitivity (true positive rate) with upper and lower 95% CI, specificity (true negative rate) with 95% CI, precision (positive predictive value), and accuracy were reported. A feasibility and clinical utility questionnaire was used to capture the assessors’ assessments of how easy each scale was to use and how well it performed (Table 1).

Jeffery David Hughes, Paola Chivers, Kreshnik Hoti

J Med Internet Res 2023;25:e41992

Accuracy of COVID-19–Like Illness Diagnoses in Electronic Health Record Data: Retrospective Cohort Study

Accuracy of COVID-19–Like Illness Diagnoses in Electronic Health Record Data: Retrospective Cohort Study

Table 3 summarizes the sensitivity, specificity, PPV, and NPV for each CLI definition among hospitalizations. Among CLI hospitalizations in adults, COVID-19–specific codes had the highest sensitivity (91.6%) and specificity (99.6%) in identifying patients with SARS-Co V-2 PCR positivity. Using the VISION CLI definition, the sensitivity remained high (95.8%), but the specificity was considerably lower (45.5%).

Suchitra Rao, Catherine Bozio, Kristen Butterfield, Sue Reynolds, Sarah E Reese, Sarah Ball, Andrea Steffens, Maria Demarco, Charlene McEvoy, Mark Thompson, Elizabeth Rowley, Rachael M Porter, Rebecca V Fink, Stephanie A Irving, Allison Naleway

JMIR Form Res 2023;7:e39231

An Agreement of Antigen Tests on Oral Pharyngeal Swabs or Less Invasive Testing With Reverse Transcription Polymerase Chain Reaction for Detecting SARS-CoV-2 in Adults: Protocol for a Prospective Nationwide Observational Study

An Agreement of Antigen Tests on Oral Pharyngeal Swabs or Less Invasive Testing With Reverse Transcription Polymerase Chain Reaction for Detecting SARS-CoV-2 in Adults: Protocol for a Prospective Nationwide Observational Study

In a meta-analysis describing the performance of rapid diagnostic tests for group A streptococcal pharyngitis [5], lanthanide immunofluorescent assay (LIFA) and optical immunoassay (OIA) were performing similarly when individual studies were pooled with an average sensitivity of 85% and an average specificity of 97% against culture, but the assays performed with large differences between different suppliers. The sensitivity varied from 71% to 95%, and the specificity varied from 62% to 100% [9-11].

Uffe Vest Schneider, Jenny Dahl Knudsen, Anders Koch, Nikolai Søren Kirkby, Jan Gorm Lisby

JMIR Res Protoc 2022;11(5):e35706

Performance of Artificial Intelligence Imaging Models in Detecting Dermatological Manifestations in Higher Fitzpatrick Skin Color Classifications

Performance of Artificial Intelligence Imaging Models in Detecting Dermatological Manifestations in Higher Fitzpatrick Skin Color Classifications

Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score were calculated for each dermatological manifestation. The F1 score is the harmonic average of the sensitivity and PPV (mean of the recall and precision). The goal of each model was to differentiate between melanoma and BCC.

Pushkar Aggarwal

JMIR Dermatol 2021;4(2):e31697

Self-Sampling for SARS-CoV-2 Diagnostic Testing by Using Nasal and Saliva Specimens: Protocol for Usability and Clinical Evaluation

Self-Sampling for SARS-CoV-2 Diagnostic Testing by Using Nasal and Saliva Specimens: Protocol for Usability and Clinical Evaluation

The primary objective of this study is to comparatively evaluate the clinical sensitivity and specificity of nasal and oral samples self-collected by individuals for COVID-19 PCR testing against the reference method (ie, nasopharyngeal swab) involving sample collection and testing by an HCW, which is the method currently used by the central laboratory for testing of symptomatic patients with COVID-19 symptom-onset in ≤7 days.

Mohammed Majam, Vanessa Msolomba, Lesley Scott, Wendy Stevens, Fadzai Marange, Trish Kahamba, Francois Venter, Donaldson Fadael Conserve

JMIR Res Protoc 2021;10(5):e24811

Self-Care Index and Post-Acute Care Discharge Score to Predict Discharge Destination of Adult Medical Inpatients: Protocol for a Multicenter Validation Study

Self-Care Index and Post-Acute Care Discharge Score to Predict Discharge Destination of Adult Medical Inpatients: Protocol for a Multicenter Validation Study

Both versions showed an acceptable sensitivity and specificity (cutoff at ≥8, PACD day-1: sensitivity 82%, specificity 55%, AUC=0.90; PACD day-3: sensitivity 86%, specificity 69%, AUC=0.79) [20]. In patients admitted from home with urinary tract infections, falls/syncope, or heart failure (n=308), PACD day-1 showed a sensitivity of 90% and a specificity of 62%, and PACD day-3 showed a sensitivity of 80% and a specificity of 60%, with cutoff at ≥8 [21].

Antoinette Conca, Daniel Koch, Katharina Regez, Alexander Kutz, Ciril Bächli, Sebastian Haubitz, Philipp Schuetz, Beat Mueller, Rebecca Spirig, Heidi Petry

JMIR Res Protoc 2021;10(1):e21447

Smartphone-Guided Algorithms for Use by Community Volunteers to Screen and Refer People With Eye Problems in Trans Nzoia County, Kenya: Development and Validation Study

Smartphone-Guided Algorithms for Use by Community Volunteers to Screen and Refer People With Eye Problems in Trans Nzoia County, Kenya: Development and Validation Study

The aim was to assess the usability of the app in identifying people with eye problems and to determine whether the target sensitivity and specificity thresholds could be met. Interim analysis was conducted after two field tests to determine whether the target sensitivity and specificity had been achieved. For this, we compared referral decisions of the CVs using the app with that of the ophthalmologist as a reference standard.

Hillary Rono, Andrew Bastawrous, David Macleod, Cosmas Bunywera, Ronald Mamboleo, Emmanuel Wanjala, Matthew Burton

JMIR Mhealth Uhealth 2020;8(6):e16345

The Aachen Falls Prevention Scale: Multi-Study Evaluation and Comparison

The Aachen Falls Prevention Scale: Multi-Study Evaluation and Comparison

Sensitivity and specificity were calculated regarding the primary outcome of the AFPS subjective risk of falling. Subsequently, sensitivity and specificity were calculated in the case that 1 out of the 3 outcomes of the AFPS identified a positive overall result. The same procedure was applied for the calculation of the ROC and thus the AUC values. Sensitivity and specificity were calculated as described by Lalkhen and Mc Cluskey, Lusardi et al, and Oliver et al [25-27].

Peter Wilhelm Victor Rasche, Verena Nitsch, Lars Rentemeister, Mark Coburn, Benjamin Buecking, Christopher Bliemel, Leo Cornelius Bollheimer, Hans-Christoph Pape, Matthias Knobe

JMIR Aging 2019;2(1):e12114