scholarly journals Automated classification of eligibility criteria in clinical trials to facilitate patient-trial matching for specific patient populations

2017 ◽  
Vol 24 (4) ◽  
pp. 781-787 ◽  
Author(s):  
Kevin Zhang ◽  
Dina Demner-Fushman
Keyword(s):  
Clinical Trials ◽  
Pregnant Women ◽  
Hiv Positive ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Specific Patient ◽  
Persons Living With Hiv ◽  
Cancer Trials ◽  
Living With Hiv

Abstract Objective:To develop automated classification methods for eligibility criteria in ClinicalTrials.gov to facilitate patient-trial matching for specific populations such as persons living with HIV or pregnant women. Materials and Methods:We annotated 891 interventional cancer trials from ClinicalTrials.gov based on their eligibility for human immunodeficiency virus (HIV)-positive patients using their eligibility criteria. These annotations were used to develop classifiers based on regular expressions and machine learning (ML). After evaluating classification of cancer trials for eligibility of HIV-positive patients, we sought to evaluate the generalizability of our approach to more general diseases and conditions. We annotated the eligibility criteria for 1570 of the most recent interventional trials from ClinicalTrials.gov for HIV-positive and pregnancy eligibility, and the classifiers were retrained and reevaluated using these data. Results:On the cancer-HIV dataset, the baseline regex model, the bag-of-words ML classifier, and the ML classifier with named entity recognition (NER) achieved macro-averaged F2 scores of 0.77, 0.87, and 0.87, respectively; the addition of NER did not result in a significant performance improvement. On the general dataset, ML + NER achieved macro-averaged F2 scores of 0.91 and 0.85 for HIV and pregnancy, respectively. Discussion and Conclusion:The eligibility status of specific patient populations, such as persons living with HIV and pregnant women, for clinical trials is of interest to both patients and clinicians. We show that it is feasible to develop a high-performing, automated trial classification system for eligibility status that can be integrated into consumer-facing search engines as well as patient-trial matching systems.

scholarly journals Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Kun Zeng ◽  
Yibin Xu ◽  
Ge Lin ◽  
Likeng Liang ◽  
Tianyong Hao
Keyword(s):  
Clinical Trial ◽  
Ensemble Learning ◽  
Metric Learning ◽  
Classification Performance ◽  
Ensemble Model ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Data Imbalance ◽  
The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Antiretroviral Therapy in Pregnant Women

2019 ◽  
pp. 281-286
Author(s):  
William R. Short ◽  
Jason J. Schafer
Keyword(s):  
Clinical Trials ◽  
Pregnant Women ◽  
Hiv Transmission ◽  
Pediatric Aids ◽  
Women Living With Hiv ◽  
Pivotal Study ◽  
Aids Clinical Trials ◽  
Living With Hiv ◽  
Mother To Child ◽  
Over Time

Upon completion of this chapter, the reader should be able to describe the appropriate management of antiretrovirals for pregnant women living with HIV. Over time, research has demonstrated that proper prevention strategies and interventions during pregnancy, labor, and delivery can significantly reduce the rate of mother-to-child transmission (MTCT) of HIV. In 1994, a pivotal study in the field of HIV medicine, the Pediatric AIDS Clinical Trials Group 076, demonstrated that the use of zidovudine (ZDV) monotherapy during pregnancy substantially reduced the risk of HIV transmission to infants by 67% (...

HIV testing of pregnant women—what is needed to protect positive women's needs and rights?

Sexual Health ◽  
2005 ◽  
Vol 2 (3) ◽  
pp. 143 ◽  
Author(s):  
Maria de Bruyn ◽  
Susan Paxton
Keyword(s):  
Pregnant Women ◽  
Hiv Testing ◽  
Perinatal Transmission ◽  
Hiv Positive ◽  
Physical Assault ◽  
People Living With Hiv ◽  
Women's Lives ◽  
Living With Hiv ◽  
Voluntary Counselling And Testing ◽  
The Impact

With increased availability of antiretroviral therapy, there is an escalating global trend to test all pregnant women for HIV in order to stop perinatal transmission. However, insufficient consideration is given to the impact this may have on the lives of these women and their families. Many women feel pressured into HIV testing during pregnancy, do not receive adequate pre-test counselling or do not give truly informed consent. Some women who test positive experience significantly more discrimination from their partners, families and community members than HIV-positive men do. As a consequence, large numbers of women diagnosed during pregnancy do not tell their husband their status because they fear blame, abandonment or abuse, including physical assault. Women who do disclose their HIV status may face dramatic negative repercussions on their own and their children’s wellbeing. Consequently, it is unfair to test women during pregnancy solely or mainly to help prevent perinatal transmission if there are no available support services to protect the women’s rights, enable them to live healthily after an HIV-positive diagnosis and engage them in the policies and programmes that affect women’s lives. We need to create a climate that encourages HIV testing before pregnancy so that women can make informed reproductive choices. Men must be brought into the testing process through couple counselling before pregnancy and scaling up of voluntary counselling and testing programmes outside the antenatal care setting. In addition, people living with HIV have unique expertise and are very effective as peer counsellors. They have been under-utilised in the health care sector to provide support to newly-diagnosed people and to help eliminate AIDS-related shame and stigma.

scholarly journals Ventricular Ectopy and Arrhythmia Characteristics for Persons Living with HIV and Uninfected Controls

2019 ◽  
Vol 18 ◽  
pp. 232595821985212
Author(s):  
Alexander Meyer ◽  
Sanjay Dandamudi ◽  
Chad Achenbach ◽  
Donald Lloyd-Jones ◽  
Matthew Feinstein
Keyword(s):  
Cardiovascular Disease ◽  
Chart Review ◽  
International Classification Of Diseases ◽  
Elevated Risk ◽  
Ventricular Ectopy ◽  
Persons Living With Hiv ◽  
Significant Difference ◽  
Classification Of Diseases ◽  
Living With Hiv

Background: Persons with HIV have elevated risk for cardiovascular disease, but little is known about the risk of ventricular ectopy and ventricular tachycardia (VE/VT) for HIV-infected (HIV+) persons. Methods: We evaluated the presence and anatomic origin of VE/VT for HIV+ persons and controls by screening a cohort using International Classification of Diseases codes and adjudicating positive screens by chart review. We sought to evaluate (1) presence of VE/VT and (2) likely anatomic origin of the VE/VT based on electrocardiogram. Results: There was no significant difference in the prevalence of VE/VT for HIV+ or uninfected persons. Among HIV+ persons, worse HIV control was associated with significantly greater odds of VE/VT. Exploratory analyses suggested that HIV+ persons may have a greater likelihood of VE/VT originating from the left ventricle. Conclusion: Although worse HIV control was associated with higher odds of VE/VT among persons with HIV, odds of VE/VT were not higher for persons with HIV than uninfected persons.

scholarly journals Challenges in Assessing Outcomes among Infants of Pregnant HIV-Positive Women Receiving ART in Uganda

2017 ◽  
Vol 2017 ◽  
pp. 1-4
Author(s):  
Barbara Castelnuovo ◽  
Frank Mubiru ◽  
Ivan Kalule ◽  
Shadia Nakalema ◽  
Agnes Kiragga
Keyword(s):  
Clinical Trials ◽  
Pregnant Women ◽  
Median Time ◽  
Hiv Transmission ◽  
Cd4 Count ◽  
Hiv Positive ◽  
Hiv Positive Women

Since 2012, the WHO recommends lifelong ART with TDF+FTC/3TC+EFV for all HIV-positive pregnant and breastfeeding women (Option B-plus). In this analysis we describe the proportion of early and late transmission in mothers with high retention in Kampala, Uganda. We included 700 pregnant women from January 2012 to August 2014 with a follow-up extended to August 2016; the median age was 31 years (IQR: 26–35), 36.3% in WHO stage 3/4; median CD4 count was 447 cells/μL (IQR: 301–651) and 73.3% were already on ART for a median time of 28 (IQR: 10–57) months; 52% infants were male and median weight was 3.2 Kg (IQR: 2.5–3.5). Five hundred and sixty-five (80.7%) infants had at least one test for HIV; 22 (3.1%) infants died, all with unknown serostatus; 3 tested positive at week 6 and one additional at months 12 and 18. Two of the mothers of the 4 HIV-positive infants were ART-naïve at the time of pregnancy. We report very low documented HIV transmission comparable with those reported in clinical trials settings; however, demonstrating the efficacy of Option B-plus in terms of averted transmission in routine settings is challenging since high proportion of infants do not have documented HIV tests.

scholarly journals Estimating the burden of pediatric HIV in an ‘A’ category district in India: an epidemiological study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Anju Sinha ◽  
Reynold Washington ◽  
Rajeev Sethumadhavan ◽  
Rajaram Subramanian Potty ◽  
Shajy Isac ◽  
...  
Keyword(s):  
Disease Burden ◽  
Control Program ◽  
Hiv Prevalence ◽  
Pediatric Hiv ◽  
Hiv Positive ◽  
People Living With Hiv ◽  
Cross Sectional ◽  
Longitudinal Methods ◽  
Persons Living With Hiv ◽  
Living With Hiv

Abstract Background India lacks epidemiological information on the disease burden of pediatric HIV. The National AIDS Control Program (NACP) estimates the numbers of HIV-positive children as a proportion of adult persons living with HIV. A third of HIV-positive children die before their first birthday and a half before they reach their second birthday. The early detection of HIV is crucial for the prevention of morbidities, growth delays, and death among HIV-positive children. Methods The study aimed to estimate the disease burden of pediatric HIV among children in ‘A’ category district of a high HIV prevalence state. An ‘A’ category district is defined by the presence of > 1% HIV prevalence among the general population, as estimated by HIV Sentinel Surveillance. The study used an innovative three-pronged strategy combining cross-sectional and longitudinal methods. The overall burden of pediatric HIV was calculated as a product of cases detected multiplied by a net inflation factor, for each of three strategies. Results The existing pool of HIV infection in the district is estimated to be 3266 (95% CI: 2621–4197) HIV positive children < 15 years of age, in a mid-year (2013) projected child population of about 1.4 million, thus giving an HIV prevalence of 0.23% (CI: 0.19–0.30) among children (0–14 years of age). The proportion of children among all people living with HIV in the district works out to 10.4% (CI: 8.6–13.5%). Conclusions The study estimate of 0.23% HIV prevalence among children (0–14 years of age) is higher than the NACP estimates (0.02) and is 2.5 higher than the Karnataka state estimate (0.09)22. Similarly, the proportion of children among all persons living with HIV in Belgaum district is 10.4% in this study, as against 6.54% for India. The study methodology is replicable for other settings and other diseases.

scholarly journals Exclusion of Pregnant Women from Clinical Trials during the Coronavirus Disease 2019 Pandemic: A Review of International Registries

2020 ◽  
Vol 37 (08) ◽  
pp. 792-799 ◽  
Author(s):  
Devin D. Smith ◽  
Jessica L. Pippen ◽  
Adebayo A. Adesomo ◽  
Kara M. Rood ◽  
Mark B. Landon ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Pregnant Women ◽  
World Health ◽  
Eligibility Criteria ◽  
Current State ◽  
Key Points ◽  
State Of Research ◽  
Novel Coronavirus ◽  
Health Organization ◽  
Clinical Trials Registry

Objective Pregnant women have been historically excluded from clinical trials for nonobstetric conditions, even during prior epidemics. The objective of this review is to describe the current state of research for pregnant women during the coronavirus disease 2019 (COVID-19) pandemic. Study Design We conducted a search of international trial registries for trials relating to the novel coronavirus. The eligibility criteria for each trial were reviewed for inclusion/exclusion of pregnant women. Relevant data were extracted and descriptive statistics were calculated for individual and combined data. The total number of trials from each registry were compared, as well as the proportions of pregnancy-related trials within each. Results Among 621,370 trials in the World Health Organization International Clinical Trials Registry, 927 (0.15%) were COVID-19 related. Of those, the majority (52%) explicitly excluded pregnancy or failed to address pregnancy at all (46%) and only 16 (1.7%) were pregnancy specific. When categorized by region, 688 (74.2%) of COVID-19 trials were in Asia, followed by 128 (13.8%) in Europe, and 66 (7.2%) in North America. Of the COVID-19 trials which included pregnant women, only three were randomized-controlled drug trials. Conclusion Approximately 1.7% of current COVID-19 research is pregnancy related and the majority of trials either explicitly exclude or fail to address pregnancy. Only three interventional trials worldwide involved pregnant women. The knowledge gap concerning the safety and efficacy of interventions for COVID-19 created by the exclusion of pregnant women may ultimately harm them. While “ethical” concerns about fetal exposure are often cited, it is in fact unethical to habitually exclude pregnant women from research. Key Points

Solid Organ Transplantation in Persons Living with HIV

2019 ◽  
pp. 275-280
Author(s):  
Eurides Lopes ◽  
Jennifer Husson
Keyword(s):  
Antiretroviral Therapy ◽  
End Stage Renal Disease ◽  
Solid Organ Transplantation ◽  
Direct Consequence ◽  
Hiv Positive ◽  
Solid Organ ◽  
Persons Living With Hiv ◽  
Stage Renal Disease ◽  
End Stage ◽  
Living With Hiv

The arrival of combination antiretroviral therapy (ART) in 1996 resulted in increased life expectancy for HIV-positive patients. Consequently, end-organ failure and associated disease has become a major cause of morbidity and mortality in this population. Up to 30% of HIV-positive individuals have end-stage renal disease (ESRD) as a direct consequence of HIV infection (HIV-associated nephropathy [HIVAN]), drug toxicities, or other comorbidities (...

The Pharmacist’s Role in Caring for HIV-Positive Individuals

2019 ◽  
pp. 183-188
Author(s):  
Jennifer Cocohoba
Keyword(s):  
Hiv Positive ◽  
Healthcare Team ◽  
Expert Consultation ◽  
Persons Living With Hiv ◽  
Living With Hiv

Upon completion of this chapter, the reader should be able to • Understand how a pharmacist might be incorporated into a healthcare team that is caring for persons living with HIV • Discuss medication-related issues for which it would be optimal for an HIV to provide expert consultation on....

scholarly journals Management of End Stage Renal Disease in Persons Living with HIV: A Cost-Effectiveness Analysis

2017 ◽  
Vol 4 (suppl_1) ◽  
pp. S436-S436
Author(s):  
Winston B Joe ◽  
Ellen F Eaton
Keyword(s):  
Cost Effectiveness ◽  
Acute Rejection ◽  
Cost Effective ◽  
Small Sample ◽  
Sensitivity Analyses ◽  
Hiv Positive ◽  
Persons Living With Hiv ◽  
The Cost ◽  
Living With Hiv ◽  
Rejection Rates

Abstract Background HIV+ kidney transplant (KT) for persons living with HIV (PLWH) is both safe and effective, with comparable patient and graft survival rates relative to HIV- KT. The objective of this study was to evaluate the cost-effectiveness of HIV+ KT relative to HIV- KT and dialysis. Methods A decision-tree framework was used to assess the cost-effectiveness of the above treatment options for PLWH. Clinical outcomes at 3 years for KT and effectiveness data (expressed in QALYs) were abstracted from previous publications, when available. Costs were assigned from a payer’s perspective using the US Renal Data System and published literature (expressed in 2014 USD). This analysis assumed a three-year time horizon. Sensitivity analyses were explored to understand how changes in 1) acute KT rejection and 2) KT failure impact cost effectiveness. Limitations include small sample size and short follow up time in referenced studies and a lack of health utility data in HIV positive persons with renal failure. We used TreeAge Software (Williamstown, MA). Results HIV+ KT was most cost effective ($299,904/QALY) while both HIV- KT ($329,676) and dialysis ($444,645) were dominated, meaning more costly and less effective. Results were sensitive to the higher KT failure (26% vs. 16%) and acute rejection (39% vs. 17%) observed with HIV- KT relative to HIV+ KT. In sensitivity analysis, as HIV+ KT rejection rates approach 20%, HIV- KT becomes a cost-effective option. As HIV+ KT failure rates approach 26%, HIV- KT becomes cost effective. Conclusion Despite its limitations, this analysis demonstrates that HIV+ kidney transplantation is a cost-effective alternative for PLWH under certain conditions. As KT outcomes, like graft failure and acute rejection rates, continue to improve, it is likely that both HIV positive and negative KT will be cost-effective alternatives to dialysis. Disclosures All authors: No reported disclosures.

Sign in / Sign up

Export Citation Format

Share Document