RESUMO
Active learning is a technique for maximizing performance of machine learning with minimal labeling effort and letting the machine automatically and adaptively select the most informative data for labeling. Since the labels on records may contain sensitive information, privacy-preserving mechanisms should be integrated into active learning. We propose a privacy-preservation scheme for active learning using homomorphic encryption-based federated learning. Federated learning provides distributed computation from multiple clients, and homomorphic encryption enhances the privacy preservation of user data with a strong security level. The experimental result shows that the proposed homomorphic encryption-based federated learning scheme can preserve privacy in active learning while maintaining model accuracy. Furthermore, we also provide a Deep Leakage Gradient comparison. The proposed scheme has no gradient leakage compared to the related schemes that have more than 74% gradient leakage.
RESUMO
This study demonstrated that Indonesian patients with chronic hepatitis C (mostly ethnic Java people) mostly were infected with hepatitis C virus (HCV) genotype 1; however, they carried mainly the major genotypes of interleukin 28B (IL-28B) single nucleotide polymorphisms (SNPs) (rs12979860 CC, rs11881222 TT, rs8103142 AA, and rs8099917 TT), and they mostly achieved sustained virological responses to pegylated interferon/ribavirin treatment.
Assuntos
Hepatite C Crônica/tratamento farmacológico , Interferon-alfa/uso terapêutico , Interleucinas/genética , Ribavirina/uso terapêutico , Adulto , Idoso , Feminino , Frequência do Gene , Genótipo , Humanos , Indonésia , Interferons , Masculino , Pessoa de Meia-Idade , Polimorfismo de Nucleotídeo Único , Resultado do TratamentoRESUMO
OBJECTIVE: To evaluate the effectiveness of cognitive behavior therapy on anxiety, depression, and quality of life of pre-diagnosed lung cancer patients. METHODS: A total of 32 pre-diagnosed subjects were divided into 16 Cognitive behaviour theraphy (CBT)-intervention patients and 16 control subjects. The study subjects were pre-diagnosed lung cancer patients hospitalized at Regional Public Hospital Dr. Moewardi Surakarta. For the treatment group, CBT psychotherapy interventions were given for up to 6 sessions every 2 days. The patient was tested for Hamilton Anxiety Rating Scale (HARS)-based anxiety symptom criteria and Hamilton Depression Rating Scale (HRSD)-based depression and followed The World Health Organization Quality of Life- Brief version (WHOQOL-BREF)-based quality of life criteria. The effect of CBT intervention was measured using an independent t-test and the Mann-Whitney test. RESULTS: There was a significant difference in the intervention group post-test: HARS criteria decreased by -8.38 ± 2.90, HRSD decreased by an average of -6.75 ± 3.30, and WHOQOL-BREF increased by an average of 16.80 ± 10.13 compared with the control group. CONCLUSION: CBT affects the improvement of anxiety, depression, and quality of life for pre-diagnosed lung cancer patients.
Assuntos
Ansiedade/terapia , Terapia Cognitivo-Comportamental/métodos , Depressão/terapia , Detecção Precoce de Câncer/psicologia , Neoplasias Pulmonares/diagnóstico , Qualidade de Vida , Ansiedade/etiologia , Depressão/etiologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Resultado do TratamentoRESUMO
BACKGROUND AND OBJECTIVES: There is a limited evidentiary base on the development of family medicine in different contexts and countries. The lack of evidence impedes our ability to compare and characterize family medicine models and identify areas of success that have led to the effective provision of care. This paper offers a comparative compilation and analysis of the development of family medicine training programs in seven countries: Brazil, Canada, Ethiopia, Haiti, Indonesia, Kenya, and Mali. METHODS: Using qualitative case studies, this paper examines the process of developing family medicine programs, including enabling strategies and barriers, and shared lessons. An appreciative inquiry framework and complex adaptive systems thinking inform our qualitative study. RESULTS: Committed partnerships, the contribution of champions, health policy, and adaptability were identified as key enablers in all seven case studies. The case studies further reveal that some enablers were more salient in certain contexts as compared to others, and that it is the interaction of enablers that is crucial for understanding how and why initiatives succeeded. The barriers that emerged across the seven case studies include: (1) resistance from other medical specialties, (2) lack of resources and capabilities, (3) difficulty in sustaining support of champions, and (4) challenges in brokering effective partnerships. CONCLUSIONS: A key insight from this study is that the implementation of family medicine is nonlinear, dynamic, and complex. The findings of this comparative analysis offer insights and strategies that can inform the design and development of family medicine programs elsewhere.