Risk Of Suboptimal Adherence Research Articles

Use of machine learning to identify patients at risk of sub-optimal adherence: study based on real-world data from 10,929 children using a connected auto-injector device

BackgroundOur aim was to develop a machine learning model, using real-world data captured from a connected auto-injector device and from early indicators from the first 3 months of treatment, to predict sub-optimal adherence to recombinant human growth hormone (r-hGH) in patients with growth disorders.MethodsAdherence to r-hGH treatment was assessed in children (aged < 18 years) who started using a connected auto-injector device (easypod™), and transmitted injection data for ≥ 12 months. Adherence in the following 3, 6, or 9 months after treatment start was categorized as optimal (≥ 85%) versus sub-optimal (< 85%). Logistic regression and tree-based models were applied.ResultsData from 10,929 children showed that a random forest model with mean and standard deviation of adherence over the first 3 months, infrequent transmission of data, not changing certain comfort settings, and starting treatment at an older age was important in predicting the risk of sub-optimal adherence in the following 3, 6, or 9 months. Sensitivities ranged between 0.72 and 0.77, and specificities between 0.80 and 0.81.ConclusionsTo the authors’ knowledge, this is the first attempt to integrate a machine learning model into a digital health ecosystem to help healthcare providers to identify patients at risk of sub-optimal adherence to r-hGH in the following 3, 6, or 9 months. This information, together with patient-specific indicators of sub-optimal adherence, can be used to provide support to at-risk patients and their caregivers to achieve optimal adherence and, subsequently, improve clinical outcomes.

A Machine Learning Approach for Identifying Children at Risk of Suboptimal Adherence to Growth Hormone Therapy

Abstract Background: Suboptimal adherence to recombinant human growth hormone (r-hGH) treatment can lead to suboptimal clinical outcomes. Being able to identify children who are at risk of suboptimal adherence in the near future, and take adequate measures to support adherence, may maximize clinical outcomes. Our aim was to develop a model based on data from the first 3 months of treatment to identify potential indicators of suboptimal adherence and predict adherence over the following 9 months using a machine learning approach. Methods: We assessed adherence to r-hGH treatment in children with growth disorders in their first 12 months of treatment using a connected autoinjector and e-device (easypod™), which automatically transmits adherence data via an online portal (easypod™ connect). We selected children who started the use of the device before 18 years of age and who transmitted their injection data for at least 12 months. Adherence (mg injected/mg prescribed) between 4-12 months (outcome) was categorized as optimal (≥85%) versus suboptimal (&amp;lt;85%). In addition to adherence over the first 3 months, comfort settings (needle speed, injection depth, injection speed, injection time), number of transmissions, number of dose changes, age at start and sex were used as potential indicators of suboptimal adherence. Several machine learning models were optimized on a class-balanced training dataset using a 5-fold cross-validation scheme. On the best performing model, machine learning interpretation techniques and chi-squared statistical tests were applied to extract the statistically significant indicators of suboptimal and optimal adherence. Results: Anonymized data were available for 10,943 children. The optimal prediction performances were achieved with the random forest algorithm. The mean adherence and the adherence standard deviation over the first 3 months were the two most important features for predicting adherence in the following 9 months. Not using the system’s features (e.g. not transmitting data often and not changing some of the comfort settings, such as the needle speed setting), as well as starting treatment at an older age were significantly associated with an increased risk of suboptimal adherence (p&amp;lt;0.001). When tested on first-time seen data following the same class distribution as the original data, the model achieved a sensitivity of 80% and a specificity of 81%. Conclusions: We developed a model predicting whether a child’s adherence in the following 9 months will be below or above the optimal threshold (85%) based on early data from the first 3 months of treatment and we identified the indicators of suboptimal adherence. These results can be used to identify children needing additional medical or other support to reach optimal adherence and therefore optimal clinical outcomes.

Medication Adherence in HIV-Positive African Americans: The Roles of Age, Health Beliefs, and Sensation Seeking.

We examined how two critical constructs, health beliefs and sensation seeking, influence combination antiretroviral therapy adherence in HIV+ African Americans, and whether these factors mediate the association between age and adherence. Two-hundred-and-eighty-six HIV+ African Americans participated in this observational study. Path analyses revealed that higher levels of a specific health belief, perceived utility of treatment, and lower levels of a sensation-seeking component, Thrill and Adventure Seeking, directly predicted optimal adherence. The influence of age on adherence was partially mediated by lower Thrill and Adventure Seeking levels. Depression predicted adherence via perceived utility of treatment and Thrill and Adventure Seeking, whereas current substance abuse and dependence did via Thrill and Adventure Seeking. Poorer neurocognitive function had a direct, adverse effect on adherence. Our findings suggest that supporting the development of more positive perceptions about HIV treatment utility may help increase medication adherence among African Americans. This may be particularly relevant for those with higher levels of depression symptoms, which was directly associated with negative perceptions about treatment. Additionally, clinicians can assess sensation-seeking tendencies to help identify HIV+ African Americans at risk for suboptimal adherence. Compensatory strategies for medication management may help improve adherence among HIV+ individuals with poorer neurocognitive function.

Management of Diabetes Mellitus in Patients with Acquired Immunodeficiency Syndrome

Abstract Acquired immunodeficiency syndrome (AIDS) is a human immune system disease characterized by increased susceptibility to opportunistic infections, certain cancers and neurological disorders. The syndrome is caused by the human immunodeficiency virus (HIV) that is transmitted through blood or blood products, sexual contact or contaminated hypodermic needles. Antiretroviral treatment reduces the mortality and the morbidity of HIV infection but is increasingly reported to be associated with increasing reports of metabolic abnormalities. The prevalence and incidence of diabetes mellitus in patients on antiretroviral therapy is high. Recently, a joint panel of American Diabetes Association (ADA) and European Association for the Study of Diabetes (EASD) experts updated the treatment recommendations for type 2 diabetes (T2DM) in a consensus statement which provides guidance to health care providers. The ADA and EASD consensus statement concur that intervention in T2DM should be early, intensive, and uncompromisingly focused on maintaining glycemic levels as close as possible to the nondiabetic range. Intensive glucose management has been shown to reduce microvascular complications of diabetes but no significant benefits on cardiovascular diseases. Patients with diabetes have a high risk for cardiovascular disease and the treatment of diabetes should emphasize reduction of the cardiovascular factors risk. The treatment of diabetes mellitus in AIDS patients often involves polypharmacy, which increases the risk of suboptimal adherence

Medication Possession Ratio Associated with Short-Term Virologic Response in Individuals Initiating Antiretroviral Therapy in Namibia

The visual-analogue scale (VAS), Likert item (rating scale), pills identification test (PIT), and medication possession ratio (MPR) provide estimates of antiretroviral therapy (ART) adherence which correlate with HIV viral suppression. These simple adherence measures are inexpensive and easy to administer; however, require validation and adjustment prior to implementation. The objective of this study was to define the optimal adherence assessment measure in Namibia to identify patients at risk for sub-optimal adherence and poor virologic response 6 months after ART initiation. We conducted a cross-sectional survey in HIV-infected adults receiving ART for 6–12 months prior to the adherence assessment. Adherence measures included 30-day VAS, 30-day Likert item, self-reported treatment interruptions, PIT, and MPR. Association of adherence measures with 6-month HIV-1 RNA level was assessed using two thresholds (1000 copies/mL and 5000 copies/mL). Adherence was assessed in 236 patients, mean age 37.3 years, 54% female. Mean adherence was 98.1% by 30-day VAS, 84.7% by 30-day Likert item, 97.0% by self-reported treatment interruptions, 90.6% by PIT, and 98.8% by MPR. Agreement between adherence measures was poor using kappa statistic. 76% had HIV-1 RNA <1000 copies/ml, and 88% had HIV-1 RNA <5000 copies/ml. MPR (continuous) was associated with viral suppression <5000 copies/ml (p = 0.036). MPR <75% was associated with virologic failure at ≥5000 copies/ml with OR 3.89 (1.24, 12.21), p = 0.013. Adherence was high with all measures. Only MPR, was associated with short-term virologic response, suggesting its cross-culturally utility for early identification of patients at high risk for virologic failure.