IIT Kanpur

Capstone Project
MBA702A, 703A, 704A
Submitted By
Prakhar Dikshit
19125028

Mentor & Guide

Dr. RRK Sharma
 Project Topic - Improving
Medication & Treatment Adherence
using Wearables and IoHT devices data

End Users – US HealthCare Payer

Industry
MBA704A –
MBA702A – Research Implementation of
on Adherence Project

MBA703A –
Synthesizing Data &
Building models
 What is Medication Adherence
Medication adherence usually refers to whether patients take
their medications as prescribed (e.g., twice daily). Medication
nonadherence is a growing concern to clinicians, healthcare
systems, and other stakeholders (e.g., payers) because of
mounting evidence that it is prevalent and associated with
adverse outcomes and higher costs of care. To date,
measurement of patient medication adherence and use of
interventions to improve adherence are rare in routine clinical
practice. The goals of the present report are to address:

• different methods of measuring adherence,

• the prevalence of medication nonadherence,

• the association between nonadherence and outcomes,

• the reasons for nonadherence, and finally,

• interventions to improve medication adherence.

 What is Treatment Adherence
• Treatment adherence, according to
the World Health Organization, is “the
extent to which a person's behavior
— taking medication, following a diet,
and/or executing lifestyle changes —
corresponds with the agreed
recommendations from a healthcare
provider.".
• "Adherence is a more positive,
proactive behavior, which results in a
lifestyle change by the patient, who
must follow a daily regimen, such as
wearing a prescribed brace. In
contrast, compliance is a behavior
exhibited by a patient who is simply
'doing as told' or following a list of
instructions given by the treating
doctor."
 What is Wearable Health Technology
1) What is wearable healthcare technology?
Wearable technology in healthcare includes electronic devices that consumers can wear, like Fitbits and smartwatches,
and are designed to collect the data of users' personal health and exercise. US consumer use of wearables jumped from
9% in 2014 to 33% in 2018, according to Accenture.
2) Examples of Wearable Devices in Healthcare
The advancement of wearable technology and growing demand from consumers to take control of their own health has
influenced the medical industry, including insurers, providers, and technology companies, to develop more wearable
devices such as Fitbits, smartwatches, and wearable monitors.
3) Wearable Fitness Trackers
Some of the simplest and most original forms of wearable technology, wearable fitness trackers, are wristbands equipped
with sensors to keep track of the user's physical activity and heart rate. They provide wearers with health and fitness
recommendations by syncing to various smartphone apps.
 What is Wearable Health Technology(Contd.)
4) Wearable ECG Monitors
Wearable ECG monitors are on the cutting edge of consumer electronics, and
what sets these monitors apart from some smartwatches, is their ability to
measure electrocardiograms, or ECGs. The Move ECG is able to measure an
electrocardiogram and send the reading to the user's doctor, as well as
detect atrial fibrillation. It's also able to track pace, distance, and elevation,
as well as automatic tracking for walking, running, swimming, and biking.
5) Wearable Blood Pressure Monitors
Omron Healthcare launched HeartGuide in 2019, the first wearable blood
pressure monitor. Though it might look like a typical smartwatch, HeartGuide
is an oscillometric blood pressure monitor that can measure blood pressure
and daily activity - like steps taken, distance traveled, and calories burned.
HeartGuide can hold up to 100 readings in memory and all readings can be
transferred to a corresponding mobile app, HeartAdvisor, for review,
comparison, and treatment optimization. HeartAdvisor users have the ability
to store, track, and share their data with their physician while also gaining
insights to determine how personal habits affect their blood pressure.
6) Biosensors
Biosensors are up and coming wearable medical devices that are radically
different from wrist trackers and smartwatches. The Philips' wearable
biosensor is a self-adhesive patch that allows patients to move around while
collecting data on their movement, heart rate, respiratory rate, and
temperature.
 Healthcare in USA

Health care in the United States is provided by many distinct organizations.

Health care facilities are largely owned and operated by private sector businesses.

58% of community hospitals in the United States are non-profit, 21% are government-
owned, and 21% are for-profit.

According to the World Health Organization (WHO), the United States spent $9,403 on
health care per capita, and 17.9% on health care as percentage of its GDP in 2014.

Healthcare coverage is provided through a combination of private health insurance and

public health coverage (e.g., Medicare, Medicaid).
 Role of Payers
1. The payer to a health care provider is the organization that negotiates or
sets rates for provider services, collects revenue through premium
payments or tax dollars, processes provider claims for service, and pays
provider claims using collected premium or tax revenues.
2. Examples include commercial health insurance plans, third-party health
insurance plan administrators, and government programs such as Medicare
and Medicaid.
3. Government programs such as Medicare and Medicaid set amounts they
will pay to health care providers. These are typically much less than the
billed charge. Hospitals have no ability to negotiate the reimbursement
rates for government-paid services.
4. Commercial insurers and third-party insurance plan administrators typically
negotiate discounts with hospitals on behalf of the patients they represent.
Problem Statement
▪ AI-assisted monitoring of treatment
adherence – through collection of
member-side real-time data through
wearable devices
▪ AI-assisted monitoring of medication
adherence – through Internet of Health
Things (IoHT)
▪ Real-time intervention for treatment
non-adherence / medication
nonadherence
Why Adherence is Important?
▪ Approximately, 125,000 deaths per year in the United States are due to
medication nonadherence.
▪ Adherence to treatment, a public health issue, is of particular importance in
chronic disease therapies
▪ Chronic Diseases like Diabetes, Heart Disease, Asthma, Cancer requires
ongoing care and Adherence to treatment and medication.
▪ It is found that 40 – 50 percent of patients with chronic conditions don’t take
their prescriptions.
USA Healthcare Payer System
▪ 30% of population is covered by three publicly funded insurance programs:
Medicare, Medicaid and the Children’s Health Insurance programs.
▪ 50% of population is covered by private insurance either subsidized by
companies or are standalone
▪ Rest of the population are uninsured.
For Insurance Companies
▪ Healthier patients will lead to fewer insurance claims
▪ Non-adherence has a direct impact on the insurance business.
Functional View

Creating System For Diabetes

Model 1: Adherence calculation from wearable

devices & IoHT Devices

Model 2: Pill Count

Intervention through E-Mails

Future Prospect: Conducting Survey

 Design View
Model 1: Treatment Adherence, Input Data: Wearable & IoHT Devices
Pulse Rate: Diabetes
Step Count: To find if
lead to high pulse rate
the exercise routine is
and therefore it should
followed or not
be normal

Glucometer
Readings

Blood Pressure:
Oximeter: To check the
Diabetics can lead to
general well being of a
High BP, known as
person
atherosclerosis

Model 2: Medication Adherence, Input Data: Pills Count

Count 0 2
Count 1 6
Score(Count1/
0.75
Count 0+Count 1)

Most general medication provided to a Diabetic Patient

➢ 0 : Medication provided but not taken on a particular Day
➢ 1 : Medication provided and taken on a day
➢ 2 : Medication not given
 Model Building

Model Training Testing

2. Model Training
1. Data Synthesis Accuracy Accuracy
Algorithms such as
7 parameters from Logistic 81% 77%
Logistic regression, SVM,
wearable devices and Regression
Decision Tree, Random
1000 rows.
Forest were tried. Support Vector 89% 79%
Machines

Decision Tree 100% 82%

3. Model Selection 4. Final Model
AdaBooster and GradientBooster was Random Forest 100% 88%
GradientBooster were selected as it was more
having the best metrics. responsive to changes.
Gradient Booster 99% 97%

Ada 99% 97%

Booster
 2. Payer can Add Patient or See
1. Click Register To create new Payer
My Patient

Application
Demo 3. Add Patient
4. View Patients

6. Email Through Contact Page

5. Click on the
Score Button
to See charts
 Conclusion
Final Training Accuracy Testing Accuracy Specificity Sensitivity F1 Score
Model
Gradient 99 97 99 94 97
Booster
1. My project will help the Health Insurance sector especially the payer in reducing costs and enhancing the quality of patient
care

2. As per the Annals of Internal Medicine, non-adherence costs the U.S. healthcare system between $100 billion and $289
billion annually. With this project I aim to reduce these costs.

3. Patients who maintain a good adherence value for 5 weeks in a row can be given extra benefits. This will keep patients
motivated to maintain there adherence scores which in turn will improve their health.

4. Charts can provide a detailed understanding of a patients Weekly/Daily parameters and Adherence levels.

5. A major difference between medication adherence and treatment adherence can provide a information about Dosage of
drugs prescribed
 Future Scope
• Model Improvement.
• Extending to other Diseases
Natural Adherence: Improving Model
Conduct Surveys to get data for the following variables to calculate natural
adherence
• Demographic Factors – Age and Gender
• Socioeconomic factors – Lower social economic status associated with
lower adherence
• Therapy related factors – Side effects, number and different types of pills to
be taken, complex regimen
• Patient related factors – Understanding of disease, its course and possible
complications, expectation of improvement on medication, Perception of
symptoms, either improving or worsening
Extension To other Chronic Diseases
1. Other data points available from wearables - Body Temperature, Blood
Oxygen Levels, Breathing Rate, Rapid Eye Movement
2. Mobile Application for diseases like Alzheimer: Finger Tapping Speed,
pauses in speech, sleep patterns
3. Chatbots for Patients for regular monitoring
APPENDIX – Summary
of Research Papers
 1. As with other chronic diseases, poor adherence is common and
Treatment results in increased rates of morbidity, healthcare expenditures,
hospitalizations and possibly mortality, as well as unnecessary

adherence in escalation of therapy and reduced quality of life.

2. Examples include overuse, underuse, and alteration of schedule and
doses of medication, continued smoking and lack of exercise.
chronic disease Adherence is affected by patients’ perception of their disease, type
of treatment or medication, the quality of patient provider
communication and the social environment.
3. Patients are more likely to adhere to treatment when they believe it
will improve disease management or control, or anticipate serious
consequences related to non-adherence.
4. Providers play a critical role in helping patients understand the
nature of the disease, potential benefits of treatment, addressing
concerns regarding potential adverse effects and events, and
encouraging patients to develop self-management skills.
5. For clinicians, it is important to explore patients’ beliefs and concerns
about the safety and benefits of the treatment, as many patients
harbor unspoken fears.
6. Complex regimens and polytherapy also contribute to suboptimal
adherence.
7. Patient adherence in chronic obstructive pulmonary disease is
multifactorial and is influenced by the patient, the physician and
society.
 Treatment non-adherence in long-term medical
conditions: systematic review and synthesis of qualitative
studies of caregivers’ views
• Non-adherence to prescribed treatments is the primary cause of treatment
failure in pediatric long-term conditions. Greater understanding of parents
and caregivers’ reasons for non-adherence can help to address this problem
and improve outcomes for children with long-term conditions.
• Findings that contribute to explaining treatment adherence can be
summarized according to six main themes:
➢ beliefs and about the condition or the treatment;
➢ difficulty of treatment regimen;
➢ child resistance;
➢ relationships within families;
➢ preserving ‘normal life’;
➢ input from health professionals.

• A strength of this review is that through drawing together qualitative

findings on diverse pediatric long-term conditions, we were able to see
patterns that may not otherwise have emerged and identify the full range of
factors influencing treatment adherence and the needs of caregivers in
relation to prescribed treatment regimens.
How useful are health behavior theories for developing
interventions to promote long-term medication adherence
Factors associated with treatment non-adherence in
patients with epilepsy in Brazil
• Purpose: To investigate factors associated with treatment non-adherence in
Brazilian patients with epilepsy.
• Methods: Prospective cross-sectional study. Paper evaluated 385 epilepsy
outpatients in a tertiary referral center, 18 years or older, literate, without
cognitive impairment or active psychiatric disorders, who were independent in
daily living activities. Data were analyzed with correlation tests and conjoint
analysis using multivariate logistic regression.
• Results: Non-adherence was higher in men, in younger patients and in patients
with uncontrolled seizures. Increasing treatment complexity was also associated
with decreased treatment adherence.
• Conclusion: Strategies designed to improve treatment adherence should address
peculiarities associated with younger ages and male gender. Physicians should be
made aware that prescription of less complex treatment regimens may result in
better treatment adherence, and, therefore, better seizure control. The challenge
in adjusting AED treatment in this
 Adherence enhancing interventions for oral
anticancer agents: A systematic review
• Background: The use of oral anticancer agents has increased in the last decades. Adherence is a crucial factor for the
success of oral anticancer agent therapy. However, many patients are non-adherent.
• Objective: The objective was to evaluate the effectiveness of adherence interventions in patients taking oral anticancer
agents.
• Methods: A systematic literature search was performed in Medline and Embase. Titles and abstracts and in case of
potential relevance, full-texts were assessed for eligibility according to the predefined inclusion criteria. The study quality
was evaluated. Both process steps were carried out independently by two reviewers. Relevant data on study design,
patients, interventions and results were extracted in standardized tables by one reviewer and checked by a second
reviewer.
• Results: Six controlled studies were included. Only one study was randomized. The study quality was moderate to low.
One study showed statistically significant results in favor of the adherence intervention, two studies showed a tendency
in favor of the intervention, one study showed an inconsistent result depending on the adherence definition and one
study showed almost identical adherence rates in both groups. One study showed a tendency in favor of the control
group.
• Conclusions: Although most of the interventions are not very effective, it appears that certain adherence enhancing
interventions could have a promising effect. One crucial point is the consideration of the baseline adherence when
choosing patients to avoid ceiling effects. The evidence is limited due to lack of sufficient studies and partly inconsistent
results. Further high quality studies are needed.
Validity and reliability of a short self-efficacy instrument
for hypertension treatment adherence among adults
with uncontrolled hypertension
• Objective: To establish the reliability and validity of a self-report measure designed to
assess self-efficacy for hypertension treatment adherence.
• Methods: This investigation was embedded within a six-month randomized clinical trial
(RCT), which demonstrated that a tailored, stage-matched intervention was more
effective at improving hypertension control than usual care among individuals (n = 533)
with repeated uncontrolled hypertension. The instrument used to assess self-efficacy for
hypertension treatment adherence (SE-HTA) comprised three subscales that assessed
diet self-efficacy (DSE), exercise self-efficacy (ESE), and medication self-efficacy(MSE). To
determine SE-HTA validity and reliability, we assessed internal consistency using
Cronbach’s α coefficients, conducted exploratory factor analysis, and evaluated
convergent and discriminant validity, as well as test-retest reliability using Spearman’s r
correlation coefficients.
• Conclusion: The SE-HTA instrument containing diet, exercise, and medication adherence
subscales is valid and reliable in adults with uncontrolled hypertension.
• Practice implications: This SE-HTA instrument measures self-efficacy and could help
facilitate behavior change in hypertension.
Associated factors with treatment adherence of patients
diagnosed with chronic disease: Relationship with health
literacy
• Aim: This study aimed to examine the relationship between the health literacy level and
treatment adherence in patients with chronic disease.
• Background: Nonadherence to treatment and insufficient health literacy can cause a decrease in
understanding treatment methods, an increase in medication errors, and an increase in morbidity
and mortality rates.
• Materials and methods: This cross-sectional study comprised a total of 200 patients who were
taking medication for a chronic disease. Data were collected using an 18-item questionnaire for
sociodemographic and medical characteristics, the Adult Health Literacy Scale (AHLS), and the
Morisky Medication Adherence Scale (MMAS).
• Results: Of the patients, 42.5% reported that they took three or more medications per day, and
32.0% reported that they did not know the side effects of these medications. Of the patients,
39.0% had low adherence to treatment. The mean score of the AHLS was 12.8 ± 4.74 (min = 2;
max = 21). A statistically significant positive correlation was found between the AHLS scores and
MMAS scores (r = 0.604; p = 0.001).
• Conclusions: This study revealed that patients’ adherence to treatment increased as their health
literacy increased. Thus, it is recommended that health literacy levels of the patients be raised
through effective interventions to ensure better adherence to treatment.
 Impact of Medication Non-adherence on
Hospitalizations and Mortality in Heart Failure
• Background: Limited literature exists on the association between medication adherence and
outcomes among patients with heart failure.
• Methods and Results: We conducted a retrospective longitudinal cohort study of 557 patients
with heart failure with reduced ejection fraction in a large health maintenance organization. We
used multivariable Cox proportional hazards models to assess the relationship between
adherence (with angiotensin-converting enzyme inhibitors or angiotensin receptor blockers, b-
blockers, and aldosterone antagonists) and the primary outcome of all-cause mortality plus
cardiovascular hospitalizations. Mean follow-up time was 1.1 years. Nonadherence (defined as
!80% adherence) was associated with a statistically significant increase in the primary outcome in
the cohort overall (hazard ratio 2.07, 95% confidence interval; P < .0001). This association
remained significant when all 3 classes of heart failure medications and the components of the
composite end point were considered separately and when the adherence threshold was varied
to 70% or 90%.
• Conclusions: Medication nonadherence was associated with an increased risk of all-cause
mortality and cardiovascular hospitalizations in a community heart failure population. Further
research is needed to define systems of care that optimize adherence among patients with heart
failure.
Factors related to self-care drug treatment and
medication adherence of elderly people in Japan
• Objectives: The number of home-dwelling elderly people who need drug treatment is increasing with the aging of
the population. Elderly people are often suffering from various chronic diseases requiring treatment with multiple
drugs, which makes self-care at home difficult. This study focused on medication adherence and aimed to identify
the current state of self-care for drug treatment in home-dwelling elderly people and the factors that relate to
selfcare and medication.
• Study design: Cross-sectional study.
• Methods: Medication adherence was measured on a 12-item medication adherence scale for home-dwelling
elderly people aged 65 and over who were taking medications. The present condition of medication self-care for
home dwelling elderly people was clarified in terms of medication adherence. Next, we clarified the relationship
between medication adherence and other factors such as demographic and clinical characteristics, communication
with doctors, and health literacy.
• Results: The average age was 73.7 (47.2% male). Functional health literacy and communicative health literacy were
significantly associated with a high level of medication adherence. There was also a significant association between
medication adherence and good communication with doctors.
• Conclusions: Medication adherence among home-dwelling elderly people was found to be related to the ability to
obtain, understand, and communicate information, in addition to the basic literacy skills of health literacy. We also
found that good communication with doctors was closely related to medication adherence. Our findings suggest
that it is necessary to be consciously involved in promoting health literacy and communication when supporting
self-care for medical treatment of home-dwelling elderly people in the future.
Impact of adherence to Mediterranean diet and/or drug treatment
on glycemic control in type 2 diabetes mellitus patients

• Aim: This study aimed to analyze the association between adherence to treatment and glycaemic control in
people with type 2 diabetes mellitus.
• Methods: Multicenter, cross-sectional study in patients with type 2 diabetes mellitus recruited by primary
care professionals in Castilla y León (Spain). Sociodemographic and clinical characteristics were reflected in
self-reported questionnaire, which included the Morisky-Green Medication Adherence Scale and the 14-
point Mediterranean Diet Adherence Screener. Medication non-adherence and poor glycaemic control were
analyzed by bivariable and multivariable analyses.
• Results: Of 3536 included patients, the 33.8% reported non-adherence to pharmacological treatment, and
the 33.7% had poor glycaemic control (HbA1c ≥58 mmol/mol [7.5%]); 50.6% of patients reported moderate-
high adherence to the Mediterranean diet (≥9 points). The multivariable logistic regression model showed
that educational level (OR 0.73; 95% CI 0.61-0.87; p < 0.001) and sedentarism (OR 1.64; 95% CI 1.36−1.98; p
< 0.001) were associate with low adherence. Younger age, rural residence, smoking, time since diagnosis (OR
1.04; 95% CI 1.03−1.05; p < 0.001) and polypharmacy were associated with poor glycaemic control.
• Conclusion: Lower educational level and sedentarism were associated with low adherence. Younger age,
rural residence, smoking, time since diagnosis and polypharmacy, increased risk of poor glycaemic control.
Predictors of Adherence and Treatment Delays
among African American Women Recommended to
Receive Breast Cancer Chemotherapy
• Background: Recognition of potential explanations for nonadherence or treatment delays is crucial to
improving survival, particularly among African American women, for whom there is limited research
assessing patient factors that influence adherence to breast cancer chemotherapy.
• Objective: This study sought to examine the association of patient factors such as age, income, employment,
and partner status with adherence (full dose/on time) to prescribed breast cancer adjuvant chemotherapy
and delays in treatment among African American women.
• Methods: This observational, prospective study used baseline data from the Adherence, Communication,
Treatment, and Support Intervention Study that included African American women with early stage breast
cancer who were recommended to receive chemotherapy. Eleven baseline demographic variables measured
by a sociodemographic questionnaire were analyzed against the outcome variables of 85% adherence to
chemotherapy, dichotomized as yes or no, and chemotherapy treatment delays measured as number of
days.
• Results: For the 121 African American women included in this study, only employment status and number of
comorbidities were significant predictors for total treatment delays in the adjusted models.
• Implications: Employment status and number of comorbidities are predictors of the ability to receive timely
breast cancer chemotherapy among African American women. This knowledge allows identification of
patients in need of tailored supportive care to encourage adherence and prevent treatment delays.
Competence and adherence in an acceptance and values-
based intervention: Effects on treatment outcome and
early changes in depression
• Background: The present study investigated competence and adherence in an acceptance- and values-based
intervention and their impact on the outcomes of treatment and early changes in depression.
• Method: A total of 74 sessions delivered by novice therapists (n = 37) were rated for overall competence and
adherence to treatment manual, as well as for process-specific components of acceptance and commitment
therapy (ACT) using the ACT Adherence Scale (Plumb & Vilardaga, 2010). The relationships between (a)
competence and adherence, (b) treatment outcome, and (c) early therapeutic changes among patients
diagnosed with major depressive disorder (n = 37) were explored.
• Results: Higher competence and better adherence to ACT were associated with larger overall changes in
depressive symptoms (r = 0.37 and r = 0.39, respectively). Specifically, the more frequently and extensively
the therapists addressed committed action during their intervention, the larger the overall changes in
depression and psychological flexibility. The regression analyses suggested that close to 40% of variation in
overall changes in depressive symptoms was explained by an early change in depressive symptoms and
adherence to the ACT model, in which early change was the strongest predictor. When early change was not
included in the regression model, both competence and adherence in ACT explained 13–14% of variation in
overall changes in depression. Competence and adherence were not associated with overall change in
psychological flexibility.
• Discussion: The present study suggests that competence and adherence in ACT may be associated with
favorable outcomes of treatment in depression. We call for further evidence and discussion about
competence and adherence in process-based interventions.
The Association between Medication Adherence and
Visual Field Progression in the Collaborative Initial
Glaucoma Treatment Study
• Purpose: To evaluate the relationship between medication adherence and visual field progression in
participants randomized to the medication arm of the Collaborative Initial Glaucoma Treatment Study
(CIGTS).
• Design: The CIGTS was a randomized, multicenter clinical trial comparing initial treatment with topical
medications to trabeculectomy for 607 participants with newly diagnosed glaucoma.
• Participants: Three hundred seven participants randomized to the medication arm of the CIGTS.
• Methods: Participants were followed up at 6-month intervals for up to 10 years. Self-reported medication
adherence and visual fields were measured. Medication adherence was assessed by telephone from
responses to the question, “Did you happen to miss any dose of your medication yesterday?” The impact of
medication adherence on mean deviation (MD) over time was assessed with a linear mixed regression
model adjusting for the effects of baseline MD and age, cataract extraction, interactions, and time (through
year 8, excluding time after crossover to surgery). Medication adherence was modeled as a cumulative sum
of the number of prior visits where a missed dose of medication was reported.
• Conclusions: This longitudinal assessment demonstrated a statistically and clinically significant association
between medication nonadherence and glaucomatous vision loss.
 Do improved patient recall and the provision of
memory support enhance treatment adherence?
• Background and objectives: Patient adherence to psychosocial treatment is an important but understudied
topic. The aim of this study was to examine whether better patient recall of treatment contents and
therapist use of memory support (MS) were associated with better treatment adherence.
• Methods: Data were drawn from a pilot randomized controlled trial. Participants were 48 individuals with
Major Depressive Disorder randomized to receive either Cognitive Therapy (CT) with an adjunctive Memory
Support Intervention (CT or Memory Support) or CT. Therapist and patient ratings of treatment adherence
were collected during each treatment session. Patient recall was assessed at mid-treatment. Therapist use of
MS was manually coded for a random selection of sessions.
• Results: Patient recall was significantly associated with better therapist and patient ratings of adherence.
Therapist use of Application, a specific MS strategy, predicted higher therapist ratings of adherence.
Attention Recruitment, another specific MS strategy, appeared to attenuate the positive impact of session
number on patient ratings of adherence. Treatment groups, MS summary scores and other specific MS
strategies were not significantly associated with adherence.
• Limitations: The measure for treatment adherence is in the process of being formally validated. Results were
based on small sample.
• Conclusions: These results support the importance of patient recall in treatment adherence. Although
collectively the effects of MS on treatment adherence were not significant, the results support the use of
certain specific MS strategy (i.e., application) as a potential pathway to improve treatment adherence.
Larger-scale studies are needed to further examine these constructs.
 Effect of social support on the treatment
adherence of hypertension patients
• This descriptive study was conducted to determine the effect of social support on drug treatment adherence in
patients with hypertension.
• The sample of this study consisted of 259 patients who met the research criteria, agreed to participate in the
research, and admitted to the cardiology clinic of a university hospital in Turkey between January and June 2017.
• Data were collected by ‘‘Patient Information Form’’, ‘‘Adherence to Drug Treatment Self-Efficacy Scale’’, and
‘‘Multidimensional Perceived Social Support Scale’’.
• It was determined that 48.3% of the patients participating in the study were in the 61–75 age group, 58.7% were
female, 91.9% were married, and 66.4% were living in the city. It was also found that 71% of the patients had at
least one relative or person with hypertension in the family, 79.2% were using at least one blood pressure
medication, 61% adhered to his/her diet, and 72.2% adhered to the disease.
• The average score of the Medication Adherence Self-Efficacy Scale was calculated as 64.24, whereas the total
score average of the Multidimensional Perceived Social Support Scale was calculated as 53.74.
• Besides, a statistically significant positive correlation was found among Medication Adherence Self-Efficacy Scale
score average, Multidimensional Perceived Social Support Scale total score, and all subgroup score averages (P =
.000).
• In conclusion, in this study, treatment adherence and social support levels of the patients were found to be
substantially good; besides, adherence to drug treatment was found to increase positively as the social support
of patients with hypertension increase.
Validation of the electronic prescription as a method
for measuring treatment adherence in hypertension
• Objective: To validate electronic prescriptions (e-prescriptions) as a method for measuring treatment
adherence in patients with hypertension.
• Methods: This prospective study initially included 120 patients treated for hypertension in primary care
centers. Adherence was measured using the gold standard, the medication event monitoring system(MEMS),
versus the index test, the e-prescription program, at baseline and at 6, 12, 18 and 24 months. We calculated
the adherence rate using the MEMS and the medication possession ratio (MPR) for the e-prescriptions. We
considered patients adherent if they had an adherence rate of 80% to 100%. To validate the e-prescription,
we obtained measures of diagnostic accuracy, the Kappa concordance index, and the area under the ROC
curve (AUC).
• Conclusion: Measures of treatment adherence were not significantly different between e-prescription and
gold standard at most visits, and the e-prescription showed good discriminatory diagnostic capacity.
• Practice implications: If patients are included in an e-prescription program for at least 2 years, e-prescription
is an inexpensive method to measure adherence in hypertension.
 Adherence to treatment in patients with
systemic lupus erythematosus
• Background and objective: Non-adherence to treatment is usually a clinical problem in patients with
systemic lupus erythematosus (SLE). Increasing the knowledge of predictors of treatment adherence can be
meaningful in the clinical setting. The main objective of the present study was to analyze the influence of
sociodemographic, clinical and psychological variables on the degree of treatment adherence in a sample of
Spanish women with SLE.
• Patients and method: This is an observational–transversal study. All participants were evaluated for the
degree of treatment adherence, their clinical status, psychopathological manifestations, the level of
perceived stress and self-efficacy. The sample was divided into two groups (adherent vs non-adherent).The
factors associated with a lack of adherence in this sample were analyzed by means of logistic regression.
• Results: This study comprises 72 women with SLE (average age = 36.72 ± 12.2 years). Almost 64% of patients
with SLE were non-adherent to treatment. The results showed that a low educational level, being
unemployed, living with a partner and alcohol abuse were associated with low treatment adherence. There
were significant mean differences between groups in psychopathological subscales of somatization,
obsession–compulsion and general psychopathological indices. There were also mean differences between
groups for the level of perceived stress. The use of non-steroidal anti-inflammatory drugs, suffering arthrosis
and scoring higher in dimensions of psychopathology were significant predictors of treatment adherence,
explaining between 35% and 47% of its variability.
• Conclusions: Including the clinical and psychopathological manifestations as important aspects in the clinical
reasoning of health professionals could improve the adherence to treatment of patients with SLE.
Predictors of Adherence and Treatment Delays among
African American Women Recommended to Receive
Breast Cancer Chemotherapy
• Background: Recognition of potential explanations for nonadherence or treatment delays is crucial to
improving survival, particularly among African American women, for whom there is limited research
assessing patient factors that influence adherence to breast cancer chemotherapy.
• Objective: This study sought to examine the association of patient factors such as age, income, employment,
and partner status with adherence (full dose/on time) to prescribed breast cancer adjuvant chemotherapy
and delays in treatment among African American women.
• Methods: This observational, prospective study used baseline data from the Adherence, Communication,
Treatment, and Support Intervention Study that included African American women with early stage breast
cancer who were recommended to receive chemotherapy. Eleven baseline demographic variables measured
by a sociodemographic questionnaire were analyzed against the outcome variables of 85% adherence to
chemotherapy, dichotomized as yes or no, and chemotherapy treatment delays measured as number of
days.
• Results: For the 121 African American women included in this study, only employment status and number of
comorbidities were significant predictors for total treatment delays in the adjusted models.
• Implications: Employment status and number of comorbidities are predictors of the ability to receive timely
breast cancer chemotherapy among African American women. This knowledge allows identification of
patients in need of tailored supportive care to encourage adherence and prevent treatment delays.
 Tube feeding during treatment for head and neck
cancer – Adherence and patient reported barriers
• Objectives: The main aim was to investigate the incidence of patient adherence to nutritional tube feeding
recommendations in patients with head and neck cancer and to determine patient barriers to meeting tube
feeding prescription.
• Materials and methods: This was an observational study from a randomized controlled trial in patients with
head and neck cancer deemed at high nutritional risk with prophylactic gastrostomy (n = 125). Patients were
randomized to receive early tube feeding prior to treatment (intervention group) or standard care. All
patients in the intervention and standard care groups then commenced clinical tube feeding as required
during treatment. Patients maintained a daily record of gastrostomy intake, main nutrition impact symptom
necessitating gastrostomy use, and reasons for not meeting nutrition prescription. Adherence was defined
as meeting 75% of total prescribed intake.
• Results: Patients were predominantly male (89%), median age 60, with oropharyngeal tumors (78%), stage
IV disease (87%) treated with chemoradiotherapy (87%). Primary reasons for gastrostomy use were poor
appetite/dysgeusia (week 2–3) and odynophagia/mucositis (week 4–7). Early tube feeding adherence was
51%. Clinical tube feeding adherence was significantly higher in the intervention group (58% vs 38%, p =
0.037). Key barriers to both phases of tube feeding were; nausea, early satiety and treatment factors
(related to hospital healthcare processes).
• Conclusions: Early tube feeding can improve patient adherence to clinically indicated tube feeding during
treatment. Low adherence overall is a likely explanation for clinically significant weight loss despite intensive
nutrition interventions. Optimizing symptom management and strategies to overcome other barriers are key
to improving adherence.
 Factors associated with treatment non-
adherence in patients with epilepsy in Brazil
• Purpose: To investigate factors associated with treatment non-adherence in Brazilian patients with epilepsy.
• Methods: Prospective cross-sectional study. We evaluated 385 epilepsy outpatients in a tertiary referral
center, 18 years or older, literate, without cognitive impairment or active psychiatric disorders, who were
independent in daily living activities. Data were analyzed with correlation tests and conjoint analysis using
multivariate logistic regression.
• Results: Non-adherence was higher in men, in younger patients and in patients with uncontrolled seizures.
Increasing treatment complexity was also associated with decreased treatment adherence.
• Conclusion: Strategies designed to improve treatment adherence should address peculiarities associated
with younger ages and male gender. Physicians should be made aware that prescription of less complex
treatment regimens may result in better treatment adherence, and, therefore, better seizure control. The
challenge in adjusting AED treatment in this population is to minimize treatment complexity, thus increasing
chances for treatment adherence.
 Non-adherence to pharmacological treatment in
schizophrenia and schizophrenia spectrum disorders - An
updated systematic literature review
• Background and objectives: The primary treatment for schizophrenia and schizophrenia
spectrum disorders is antipsychotic medication. One of the many public health challenges in
mental illness, is to identify contributing factors to non-adherence to pharmacological treatment.
The objective of this study was to perform an updated systematic review of risk factors for non-
adherence to pharmacological treatment in schizophrenia in a European and American context.
• Methods: The study was a systematic literature review of studies that included at least two
measurements of pharmacological adherence in adult schizophrenic patients. This was done to
validate the measures of adherence adequately which is rarely done in previous adherence
research. It was conducted using PRISMA guidelines surveying PubMed and PsycINFO.
• Results: The definition of non-adherence varies greatly in eligible studies and the methodological
approach to investigation of non-adherence is inconsistent. Thirteen studies fit the inclusion
criteria and demonstrated several risk factors statistically influencing non-adherence rates. The
most frequent risk factors identified for non-adherence were poor insight into or lack of
awareness of illness, alcohol or drug abuse and unspecified younger age.
• Conclusions: The findings in this systematic literature review are consistent with previous reviews
on non-adherence and schizophrenia. It stresses the methodological challenges in psychiatric
adherence research and establishes the need for more systematic and rigorous study design and
methods within this field.
The Effects of Feedback on Adherence to Treatment: A
Systematic Review and Meta-analysis of RCTs
• Context: The aim of this systematic review is to determine whether providing feedback, guided by subjective
or objective measures of adherence, improves adherence to treatment.
• Evidence acquisition: Data sources included MEDLINE, Embase, CINAHL, and PsycINFO, and reference lists of
retrieved articles. Only RCTs comparing the effect of feedback on adherence outcome were included. Three
independent reviewers extracted data for all potentially eligible studies using an adaptation of the Cochrane
Library data extraction sheet. The primary outcome, change in adherence, was obtained by measuring the
difference between adherence at baseline visit (prior to feedback) and at the last visit (post-feedback).
• Evidence synthesis: Twenty-four studies were included in the systematic review, and 16 found a significant
improvement in adherence in the intervention group whereas adherence worsened in the control group
(change in adherence range, –32% to 10.2%). Meta-analysis included six studies, and the pooled effect
showed that mean percentage adherence increased by 10.02% more between baseline and follow-up in the
intervention groups compared with control groups. Meta-regression confirmed that study quality, form of
monitoring adherence, delivery of feedback, or study duration did not influence effect size.
• Conclusions: Feedback guided by objective or subjective measures of adherence improves adherence and,
perhaps more importantly, prevents worsening of adherence over time even when only small absolute
improvements in adherence were noted. Increased use of feedback to improve treatment adherence has the
potential to reduce avoidable healthcare costs caused by non-adherence.
A web-based program to improve treatment adherence in
patients with type 2 diabetes: Development and study
protocol
• Background: Many patients with type 2 diabetes mellitus (T2DM) sub-optimally adhere to core treatment
recommendations, such as healthy diets, sufficient physical activity and pharmacological support. This paper
describes the development of the web-based computer-tailored program My Diabetes Profile (MDP),
incorporating identified success factors of web-based interventions, and the protocol for testing the
effectiveness of this program in a randomized multicenter trial.
• Methods: Formative research - including the input of a program committee, qualitative and quantitative
studies with patients and health professionals and a literature search - yielded input for the development of
the MDP program. MDP provides video and text tailored advice, based on determinants and salient beliefs
derived from the I-Change Model, on decreasing unhealthy snack intake, increasing physical activity, and
improving adherence to both oral blood glucose lowering drugs and self-administered insulin therapy.
Patients with T2DM recruited by practice nurses and diabetes nurses across the Netherlands fill in online
questionnaires at baseline and six-months follow-up. Participants are randomized on patient level to the
intervention group (access to the MDP program) or control group (receiving care as usual).
• Discussion: The formative research using co-creation principles proved essential in the development of the
MDP program and involved various disciplines in T2DM management including target group representatives.
Cocreation revealed clearly that patients needed short and attractive messages. Consequently, a mix of
video and short text messages were chosen for the ultimate program format. Pilot testing was useful to
further shape the program to needs of patients and professionals.
 Acknowledgement
I would like to express my special thanks of gratitude to my guide Prof. RRK Sharma who gave me the golden opportunity to do this
wonderful project on the Healthcare Topic – Improving medication & treatment adherence using wearables & IoHT data, which
helped me in doing a lot of Research and I came to know about so many new things.

Secondly, I would also like to thank the Capstone Committee and MBA Dept. of IIT Kanpur who helped me a lot in finalizing this
project within the limited time frame.

I am grateful to all those who have helped me to put these ideas, well above the level of simplicity and into something concrete.

Thanking you,

• Prakhar Dikshit

• 19125028

• MBA 2nd Year