A Randomized Clinical Trial Comparing Visual Inspection with Acetic Acid (VIA) to Pocket Colposcopy for the Triage of HPV+ women living with HIV in Kisumu, Kenya DOI Creative Commons
Mary Elizabeth Dotson,

E. P. Steinberg,

Maria Santos

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 5, 2024

Abstract Objective The World Health Organization recommends a “screen, triage, treat” approach for cervical cancer screening Women Living with HIV (WLWH) in resource-limited settings, Human Papillomavirus (HPV) testing preferred screening. We assessed the use of Pocket colposcope as an adjunct tool to Visual Assessment Acetic Acid (VIA) triage HPV+ WLWH. Methods carried out randomized clinical trial across six clinics Kisumu, Kenya between November 2022 and April 2023 ( NCT04998318 ). WLWH who screened positive self-collected HPV were either VIA or arm. Exam positivity was determined by presence absence aceto-white epithelium (AWE). Directed biopsies performed on AWE; if negative, two random taken. Pathology used determine diagnostic accuracy. Providers participants took brief surveys after each exam. Findings rate exams 17.3% compared 14.3% Pocket. overall CIN2/3 15.4%, 12.2% Arm is 18.8% Arm. comparably all sensitivity, specificity negative predictive value (NPV). For VIA, Sensitivity 26.3% vs 25.0%; 88.9% 84.0%; NPV 82.9% 87.1%. However, (PPV) arm almost factor higher than that (Pocket PPV 375 20.6%). Colposcope acceptable providers patients clinic-based positivity. Conclusion Provider assessment detected significantly more treatable disease, thereby reducing need overtreatment. This study indicates feasible, lower cost colposcopic device, which could facilitate biopsy-confirmation increase provider training, patient education remote diagnosis.

Language: Английский

Sparrow Search Algorithm (SSA) Based Feature Selection and Optimized Feed-Forward Neural Network (OFFNN) for Semen Quality Analysis DOI

C. Shanthini,

S. Silvia Priscila

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 669 - 682

Published: Jan. 1, 2025

Language: Английский

Citations

0
SAPNN: Self-attention Pyramidal Neural Network for Face Emotion Recognition with Multimodal Fusion DOI
Madan Mohan Tito Ayyalasomayajula,

Santhosh Bussa,

Shahnawaz Khan

et al.

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 539 - 550

Published: Jan. 1, 2025

Language: Английский

Citations

0
Optimized CNN-BiLSTM with Attention: A High Performance Model for Predicting Heart Disease Using Cleveland and Framingham Datasets DOI

K. Kayalvizhi,

S. Kanchana,

Silvia Priscila S

et al.

Journal of Machine and Computing, Journal Year: 2024, Volume and Issue: unknown, P. 1195 - 1205

Published: Oct. 5, 2024

Worldwide, some 17.9 million survives are lost each year due to heart disease (HD), which is acknowledged by the World Health Organisation (WHO) as top cause of mortality. In order simplify further action, HD prediction—a difficult problem—can give a computerised estimate level. Improving patient outcomes and allowing for timely medical interventions both made possible early detection accurate calculation HD. As result, prediction has garnered great deal interest from healthcare facilities around globe. There been encouraging progress in cardiac illness thanks recent developments machine learning (ML). Transparency explainability, addition generalisability robustness, crucial ML models be used therapeutic settings. The efficient diagnosis numerous diseases was greatly aided systems based on Deep Learning (DL). By combining Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTMs), besides Attention Mechanisms (CNN-AM), this paper aims build strong scheme. Minimal preparation necessary procedure. To extract spatial features, CNN used. temporal characteristics, Bi-LSTM Lastly, filter out more ighted channel output classification, two ights allotted through attention mechanism. proposed model's parameters fine-tuned using new optimisation approach known Newton-Raphson-based Optimiser (NRO), ultimately leads better classification accuracy. With accuracy 95.3% Cleveland dataset 98.1% Framingham dataset, respectively, optimised CNN-BiLSTM-AM model demonstrated best performance experimental findings.

Language: Английский

Citations

1
A Randomized Clinical Trial Comparing Visual Inspection with Acetic Acid (VIA) to Pocket Colposcopy for the Triage of HPV+ women living with HIV in Kisumu, Kenya DOI Creative Commons
Mary Elizabeth Dotson,

E. P. Steinberg,

Maria Santos

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 5, 2024

Abstract Objective The World Health Organization recommends a “screen, triage, treat” approach for cervical cancer screening Women Living with HIV (WLWH) in resource-limited settings, Human Papillomavirus (HPV) testing preferred screening. We assessed the use of Pocket colposcope as an adjunct tool to Visual Assessment Acetic Acid (VIA) triage HPV+ WLWH. Methods carried out randomized clinical trial across six clinics Kisumu, Kenya between November 2022 and April 2023 ( NCT04998318 ). WLWH who screened positive self-collected HPV were either VIA or arm. Exam positivity was determined by presence absence aceto-white epithelium (AWE). Directed biopsies performed on AWE; if negative, two random taken. Pathology used determine diagnostic accuracy. Providers participants took brief surveys after each exam. Findings rate exams 17.3% compared 14.3% Pocket. overall CIN2/3 15.4%, 12.2% Arm is 18.8% Arm. comparably all sensitivity, specificity negative predictive value (NPV). For VIA, Sensitivity 26.3% vs 25.0%; 88.9% 84.0%; NPV 82.9% 87.1%. However, (PPV) arm almost factor higher than that (Pocket PPV 375 20.6%). Colposcope acceptable providers patients clinic-based positivity. Conclusion Provider assessment detected significantly more treatable disease, thereby reducing need overtreatment. This study indicates feasible, lower cost colposcopic device, which could facilitate biopsy-confirmation increase provider training, patient education remote diagnosis.

Language: Английский

Citations

0