Feature selection and importance of predictors of non-communicable diseases medication adherence from machine learning research perspectives

Kanyongo, Wellington; Ezugwu, Absalom E.

doi:10.1016/j.imu.2023.101232

Cited by 8 publications

(4 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This association can be explained considering the multiple components of our experimental Frontiers in Pharmacology frontiersin.org intervention, that include specific sessions dedicated to treatment adherence and to physical activity, with a synergic positive effect of both sessions. Several studies showed that patient's knowledge about treatments is the strongest predictor of adherence (Jankowska-Polańska et al, 2016;López-Pintor et al, 2021;Kanyongo and Ezugwu, 2023), particularly in patients with severe mental disorders, who can have more difficulties than other patients in understanding the need for taking pharmacological drugs. It can be that the improved adherence found in our sample at the end of the intervention is due to the inclusion of psychoeducational components, motivational interview and cognitive-behavioral techniques (Vieta, 2005;Depp et al, 2008;Okazaki et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

Physical activity influences adherence to pharmacological treatments in patients with severe mental disorders: results from the multicentric, randomized controlled LIFESTYLE trial

Sampogna,

Luciano,

Di Vincenzo

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

Introduction: Poor adherence to pharmacological treatment is frequent in people with severe mental disorders and it often causes lack of effectiveness of many psychotropic drugs. Thus, efforts should be made to improve adherence to pharmacological treatments in patients with these disorders.Methods: In this paper, based on the LIFESTYLE randomized, controlled multicentric trial, we aim to: 1) assess the level of adherence in a real-world sample of patients with severe mental disorders; 2) evaluate differences in treatment adherence according to patients’ socio-demographic and clinical characteristics; 3) evaluate the impact of an innovative psychosocial intervention, on patients’ adherence to treatments. The Lifestyle Psychosocial Group Intervention consists of group sessions, focused on different lifestyle behaviours, including healthy diet; physical activity; smoking habits; medication adherence; risky behaviours; and regular circadian rhythms. At end of each session a 20-min moderate physical activity is performed by the whole group.Results: The sample consists of 402 patients, mainly female (57.1%, N = 229), with a mean age of 45.6 years (±11.8). Less than 40% of patients reported a good adherence to pharmacological treatments. Adherence to treatments was not influenced by gender, age, diagnosis and duration of illness. At the end of the intervention, patients receiving the experimental intervention reported a significant improvement in the levels of adherence to treatments (T0: 35.8% vs. T3: 47.6%, p < 0.005). Patients practicing moderate physical activity reported a two-point improvement in the levels of adherence [odds ratio (OR): 1,542; 95% confidence intervals (CI): 1,157–2,055; p < 0.001], even after controlling for several confounding factors.Discussion: The experimental lifestyle intervention, which can be easily implemented in the routine clinical practice of mental health centres, was effective in improving adherence to pharmacological treatments.

show abstract

Section: Discussionmentioning

confidence: 99%

Physical activity influences adherence to pharmacological treatments in patients with severe mental disorders: results from the multicentric, randomized controlled LIFESTYLE trial

Sampogna,

Luciano,

Di Vincenzo

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

show abstract

“…Multiple factors interact to cause perioperative noncommunicable diseases. Triggering variables and predisposing factors are two ways to classify the complex etiology of PNDs [6]. According to research, one controllable element that can impact the onset of postpartum depression is the choices people make on a daily basis.…”

Section: Review Risk Factors For Pnds In Perioperative Settingsmentioning

confidence: 99%

Advancing Perioperative Neurocognitive Health: A Critical Review of Predictive Tools, Diagnostic Methods, and Interventional Strategies

Lakshminarayanan,

Aboobacker,

Brar

et al. 2024

Cureus

View full text Add to dashboard Cite

Perioperative neurocognitive disorders (PNDs) affect a large percentage of people who undergo surgeries that need general anesthesia. There is an increased risk of death and a major disruption to postoperative self-care as a result of this. This study compiles all the relevant materials that the authors have found to investigate postnatal depression and its causes, as well as the methods used to determine the probability and severity of PNDs and how to reduce their risk before surgery. Postnatal depression can have many causes, and this text explores some of them. These include a history of alcohol or opiate use, immunological dysregulation, advanced age, educational background, infections, neurocognitive impairment, and preexisting chronic inflammatory disorders. It also delves into various methods used to gauge the likelihood and severity of postpartum depression. The following assessment tools were covered: the Clock Drawing Test, Domain-Specific Tests, the Mini-Mental State Examination, and the Montreal Cognitive Assessment. In addition to biochemical markers, neuroimaging techniques play an important role in diagnosis. The Frailty Fried assessment, which measures inertia, sluggishness, lack of physical activity, fatigue, and unintentional weight loss, is a key prognostic sign that is highlighted. There is strong evidence that the index, which is derived from these five characteristics, may accurately predict the likelihood of PNDs. Risk mitigation strategies are also covered in this research. Preoperative brain plasticity-based therapies, such as physical exercise and intensive cognitive training, can significantly reduce the incidence and severity of postoperative neurocognitive disorders. A peripheral nerve block, monitoring cerebral oxygen saturation, dexmedetomidine, and a reduction in anesthesia depth are all ways to improve anesthetic procedures. Methods that lower blood pressure should be avoided, the body temperature should be kept down during surgery, or the time without liquids should be lengthened; all of these raise the risk of postoperative nausea and vomiting and make it worse. Potential approaches include a Mediterranean diet, physical activity, cognitive stimulation, smoking cessation, alcohol reduction, avoidance of anticholinergic medications, and non-steroidal anti-inflammatory drug stewardship, although there is no definitive evidence for successful postoperative neurocognitive rehabilitation procedures. More standardized diagnostic criteria, evaluation methods, and PND classification are urgently needed, according to this study. Different cases of PNDs are characterized by different combinations of tests, cutoff values, and methods because there is a broad variety of diagnostic tests used to make the diagnosis. Until now, PNDs and pre-existing neurocognitive disorders have been diagnosed using the Diagnostic and Statistical Manual of Mental Disorders (DSM-V). With an aging population comes an increase in the occurrence and prevalence of PNDs, which calls for a specific way to classify an...

show abstract

“…Reinforcement learning has thus far had limited use in health care 27 , 28 , 30 – 32 and has not been applied to medication adherence, an essential daily activity for most patients with chronic disease, and especially diabetes, which affects 529 million individuals globally 2 , 33 . While machine learning generally has been shown to be helpful in measuring suboptimal adherence 34 , 35 , there remains much opportunity to explore how it and related techniques can improve adherence. Accordingly, we launched the RE inforcement learning to I mprove N on-adherence F or diabetes treatments by O ptimizing R esponse and C ustomizing E ngagement trial (REINFORCE) to evaluate the impact of a text messaging program tailored using reinforcement learning on medication adherence for patients with type 2 diabetes 22 .…”

Section: Introductionmentioning

confidence: 99%

The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial

Lauffenburger,

Yom-Tov,

Keller

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Text messaging can promote healthy behaviors, like adherence to medication, yet its effectiveness remains modest, in part because message content is rarely personalized. Reinforcement learning has been used in consumer technology to personalize content but with limited application in healthcare. We tested a reinforcement learning program that identifies individual responsiveness (“adherence”) to text message content and personalizes messaging accordingly. We randomized 60 individuals with diabetes and glycated hemoglobin A1c [HbA1c] ≥ 7.5% to reinforcement learning intervention or control (no messages). Both arms received electronic pill bottles to measure adherence. The intervention improved absolute adjusted adherence by 13.6% (95%CI: 1.7%–27.1%) versus control and was more effective in patients with HbA1c 7.5- < 9.0% (36.6%, 95%CI: 25.1%–48.2%, interaction p < 0.001). We also explored whether individual patient characteristics were associated with differential response to tested behavioral factors and unique clusters of responsiveness. Reinforcement learning may be a promising approach to improve adherence and personalize communication at scale.

show abstract

Feature selection and importance of predictors of non-communicable diseases medication adherence from machine learning research perspectives

Cited by 8 publications

References 74 publications

Physical activity influences adherence to pharmacological treatments in patients with severe mental disorders: results from the multicentric, randomized controlled LIFESTYLE trial

Physical activity influences adherence to pharmacological treatments in patients with severe mental disorders: results from the multicentric, randomized controlled LIFESTYLE trial

Advancing Perioperative Neurocognitive Health: A Critical Review of Predictive Tools, Diagnostic Methods, and Interventional Strategies

The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial

Contact Info

Product

Resources

About