Incremental Healthcare Expenditures Associated with Thyroid Disorders among Individuals with Diabetes

Identification of important symptoms and diagnostic hypothyroidism patients using machine learning algorithms

Background

Hypothyroidism is one of the most common endocrine diseases. It is, however, usually challenging for physicians to diagnose due to nonspecific symptoms. The usual procedure for diagnosis of Hypothyroidism is a blood test. In recent years, machine learning algorithms have proved to be powerful tools in medicine due to their diagnostic accuracy. In this study, the authors aim to predict and identify the most important symptoms of Hypothyroidism using machine learning algorithms.

Method

In this cross-sectional, single-center study, 1296 individuals who visited an endocrinologist for the first time with symptoms of Hypothyroidism were studied, 676 of whom were identified as patients through thyroid-stimulating hormone testing. The outcome was binary (with Hypothyroidism /without Hypothyroidism). In a comparative analysis, random forest, decision tree, and logistic regression methods were used to diagnose primary Hypothyroidism.

Results

Symptoms such as tiredness, unusual cold feeling, yellow skin (jaundice), cold hands and feet, numbness of hands, loss of appetite, and weight Hypothyroidism gain were recognized as the most important symptoms in identifying Hypothyroidism. Among the studied algorithms, random forest had the best performance in identifying these symptoms (accuracy=0.83, kappa=0.46, sensitivity=0.88, specificity=0.88).

Conclusions

The findings suggest that machine learning methods can identify Hypothyroidism patients who show relatively simple symptoms with acceptable accuracy without the need for a blood test. Greater familiarity and utilization of such methods by physicians may, therefore, reduce the expense and stress burden of clinical testing.

Machine Learning Approach with Harmonized Multinational Datasets for Enhanced Prediction of Hypothyroidism in Patients with Type 2 Diabetes

Type 2 diabetes (T2D) is a global health concern with increasing prevalence. Comorbid hypothyroidism (HT) exacerbates kidney, cardiac, neurological and other complications of T2D; these risks can be mitigated pharmacologically upon detecting HT. The current HT standard of care (SOC) screening in T2D is infrequent, delaying HT diagnosis and treatment. We present a first-to-date machine learning algorithm (MLA) clinical decision tool to classify patients as low vs. high risk for developing HT comorbid with T2D; the MLA was developed using readily available patient data from harmonized multinational datasets. The MLA was trained on data from NIH All of US (AoU) and UK Biobank (UKBB) (Combined dataset) and achieved a high negative predictive value (NPV) of 0.989 and an AUROC of 0.762 in the Combined dataset, exceeding AUROCs for the models trained on AoU or UKBB alone (0.666 and 0.622, respectively), indicating that increasing dataset diversity for MLA training improves performance. This high-NPV automated tool can supplement SOC screening and rule out T2D patients with low HT risk, allowing for the prioritization of lab-based testing for at-risk patients. Conversely, an MLA output that designates a patient to be at risk of developing HT allows for tailored clinical management and thereby promotes improved patient outcomes.

Treatment of Hypothyroidism and Stress Using Neuro-Emotional Technique (NET): A Case Study

Hypothyroidism is generally considered an autoimmune condition, and typical medical management involves taking levothyroxine (synthetic thyroid hormone) for life. This case report details the results of a mind-body intervention (MBI) called the Neuro-Emotional Technique (NET) used to treat a 28-year-old Caucasian female presenting with symptoms and bloodwork markers associated with two years of hypothyroidism and a long history of stress. The patient's medical doctor provided a diagnosis of hypothyroidism after blood tests showed that thyroid-stimulating hormone (TSH) levels were high at 6.87 mIU/L (where the acceptable range is 0.40-3.50 mIU/L) and free T4 (FT4) levels were low at 8.6 pmol/L (where the acceptable range is 9.0-19.0 pmol/L). Psychometric tests were completed at baseline and after 12 weeks of treatment to evaluate changes in mental health and emotional well-being. The Adverse Childhood Experiences Questionnaire (ACE-Q) revealed a high degree of childhood trauma that may have predisposed to the underlying autoimmune thyroid dysfunction. At the conclusion of the treatment period, serum thyroid-stimulating hormone (TSH) and free T4 were within normal ranges and psychometric indicators normalized. We hypothesize that these changes may be due to the stress-reducing mechanism of NET and outline possible mechanisms via the Psycho-Immune-Neuroendocrine (PINE) network. The PINE network model asserts that chronic stress acts as a potential driver of pathophysiology that can lead to one or more medical and mental health conditions. While further studies with larger sample sizes are required to establish whether these results could be extrapolated to a wider population, the results of this case suggest that it may be pertinent to consider co-management of subclinical hypothyroidism with a relatively quick and cost-effective MBI such as NET.

Knowledge Assessment Regarding the Differences Between Hypothyroidism and Hyperthyroidism Among Saudi Arabia's Adult Population

Introduction Worldwide, thyroid diseases are among the most prevalent endocrine disorders. According to the Saudi Arabian Ministry of Health (MOH), many thyroid disease cases remain undiagnosed and, as a result, are not treated because the patient has no symptoms or is unaware of them. Hence, this study aims to assess the knowledge about hypothyroidism and hyperthyroidism among Saudi Arabia's population. Methodology A cross-sectional survey was conducted among Saudi adults in five randomly selected regions in Saudi Arabia from December 2022 - January 2023. An Arabic self-administered questionnaire was sent to randomly selected participants via an online link. The questionnaire was composed of four parts: Sociodemographic; knowledge related to hypothyroidism and hyperthyroidism diseases and their differences; knowledge about the thyroid gland in terms of functions and causes of thyroid dysfunction. The Statistical Package for Social Sciences was used for data analysis. Results Out of 996 participants (66.2% women), 70.1% knew the function of the thyroid gland, 66.4% knew that women are more susceptible to thyroid disease, and 49.5% knew the association between thyroid dysfunction and heart disease. Female sex, higher education, and old age were associated with good knowledge, and no differences were evident regarding nationality and residence. The results showed inadequate awareness regarding thyroid diseases in Saudi Arabia, with some parts of this population being very clearly below average. Conclusion Knowledge regarding thyroid disorders was sub-optimal in Saudi Arabia; older women with higher education had the best knowledge. With even larger samples, we recommend that future studies be made to develop clear and decisive public health strategies that can be implemented at once.

Prevalence and risk factors of untreated thyroid dysfunctions in the older Caucasian adults: Results of PolSenior 2 survey

Introduction

To determine the prevalence of treated and untreated thyroid dysfunction and to identify factors associated with increased risk of undiagnosed thyroid dysfunction in older adults.

Methods

The population of 5987 community-dwelling Polish Caucasian seniors aged 60 years and above who participated in the PolSenior 2 study (2018–2019). Population-based cross-sectional multidisciplinary study in design. Data from structured questionnaires, geriatric tests, and scales were obtained from all study participants who underwent anthropometric and blood pressure measurements during three home visits. Assessment of thyroid function was based on TSH serum measurements.

Results

The prevalence of thyroid dysfunction in the Polish population aged 60 years or above was estimated at 15.5% (21.5% in women and 7.2% in men), with 3.2% of undiagnosed individuals among them. The prevalence of hypothyroidism and hyperthyroidism in the studied group was 13.9% (19.4% in women and 6.3% in men) and 1.6% (2.1% in women and 0.9% in men) respectively, untreated hypothyroidism was revealed in 21.9% (in 160 out of 732 subjects) and untreated hyperthyroidism in 34.2% of subjects (in 41 out of 120 participants). In multiple regression analysis independent risk factors for thyroid disorders being untreated were older age (> 75 years), male sex, a low education level (primary or lower), and low utilization of medical services.

Conclusions

One-fifth of Polish Caucasian seniors with hypothyroidism and one-third with hyperthyroidism are untreated. Older, poorly educated and rarely utilizing medical services seniors, especially men, are more frequently untreated for thyroid dysfunction and some of them do not benefit from contemporary achievements in medicine.

Costs of multimorbidity: a systematic review and meta-analyses

BACKGROUND

Multimorbidity is a rising global phenomenon, placing strains on countries' population health and finances. This systematic review provides insight into the costs of multimorbidity through addressing the following primary and secondary research questions: What evidence exists on the costs of multimorbidity? How do costs of specific disease combinations vary across countries? How do multimorbidity costs vary across disease combinations? What "cost ingredients" are most commonly included in these multimorbidity studies?

METHODS

We conducted a systematic review (PROSPERO: CRD42020204871) of studies published from January 2010 to January 2022, which reported on costs associated with combinations of at least two specified conditions. Systematic string-based searches were conducted in MEDLINE, The Cochrane Library, SCOPUS, Global Health, Web of Science, and Business Source Complete. We explored the association between costs of multimorbidity and country Gross Domestic Product (GDP) per capita using a linear mixed model with random intercept. Annual mean direct medical costs per capita were pooled in fixed-effects meta-analyses for each of the frequently reported dyads. Costs are reported in 2021 International Dollars (I$).

RESULTS

Fifty-nine studies were included in the review, the majority of which were from high-income countries, particularly the United States. (1) Reported annual costs of multimorbidity per person ranged from I$800 to I$150,000, depending on disease combination, country, cost ingredients, and other study characteristics. (2) Our results further demonstrated that increased country GDP per capita was associated with higher costs of multimorbidity. (3) Meta-analyses of 15 studies showed that on average, dyads which featured Hypertension were among the least expensive to manage, with the most expensive dyads being Respiratory and Mental Health condition (I$36,840), Diabetes and Heart/vascular condition (I$37,090), and Cancer and Mental Health condition in the first year after cancer diagnosis (I$85,820). (4) Most studies reported only direct medical costs, such as costs of hospitalization, outpatient care, emergency care, and drugs.

CONCLUSIONS

Multimorbidity imposes a large economic burden on both the health system and society, most notably for patients with cancer and mental health condition in the first year after cancer diagnosis. Whether the cost of a disease combination is more or less than the additive costs of the component diseases needs to be further explored. Multimorbidity costing studies typically consider only a limited number of disease combinations, and few have been conducted in low- and middle-income countries and Europe. Rigorous and standardized methods of data collection and costing for multimorbidity should be developed to provide more comprehensive and comparable evidence for the costs of multimorbidity.

Hypothyroidism in Context: Where We've Been and Where We're Going

Hypothyroidism affects up to 5% of the general population, with a further estimated 5% being undiagnosed. Over 99% of affected patients suffer from primary hypothyroidism. Worldwide, environmental iodine deficiency is the most common cause of all thyroid disorders, including hypothyroidism, but in areas of iodine sufficiency, Hashimoto’s disease (chronic autoimmune thyroiditis) is the most common cause of thyroid failure. Hypothyroidism is diagnosed biochemically, being overt primary hypothyroidism defined as serum thyroid-stimulating hormone (TSH) concentrations above and thyroxine concentrations below the normal reference range. Symptoms of hypothyroidism are non-specific and include mild to moderate weight gain, fatigue, poor concentration, depression, and menstrual irregularities, while the consequences of untreated or under-treated hypothyroidism include cardiovascular disease and increased mortality. Levothyroxine has long been the main tool for treating hypothyroidism and is one of the world’s most widely prescribed medicines. In adults with overt hypothyroidism, levothyroxine is usually prescribed at a starting dose of 1.6 µg/kg/day, which is then titrated to achieve optimal TSH levels (0.4–4.0 mIU/L), according to the therapeutic target. We here summarise the history of levothyroxine and discuss future issues regarding the optimal treatment of hypothyroidism. Because nearly one-third of patients with treated hypothyroidism still exhibit symptoms, it is important that levothyroxine is used more appropriately to achieve maximum benefit for patients. In order to ensure this, further research should include more accurate assessments of the true prevalence of hypothyroidism in the community, optimisation of the levothyroxine substitution dose, proper duration of treatment, and identification of patients who may benefit from combination therapy with levothyroxine plus levotriiodothyronine.

Funding: Merck.

Plain Language Summary: Plain language summary available for this article.

Hypothyroidism is one of the most common diseases worldwide, and levothyroxine is the usual medication prescribed to manage it. Hypothyroidism occurs when the thyroid gland, located in the neck, does not produce enough thyroid hormone for the body’s requirements. This can result in heart disease, infertility, and poor brain development in children. People with hypothyroidism may have changes in body weight, and feel tired, weak or unhappy, all of which can reduce their quality of life. In underdeveloped parts of the world, the main reason why people develop hypothyroidism is that they not getting enough iodine from food. Thus, many countries try to increase iodine intake by adding iodine to salt. In areas of the world where people ingest enough iodine, the most common cause of hypothyroidism is Hashimoto’s disease. This is an autoimmune disease in which the person’s immune system produces cells and antibodies that attack the thyroid gland. Most people with hypothyroidism will need to take levothyroxine for a long time, perhaps even for the rest of their lives. Levothyroxine replaces the person’s levels of thyroid hormone and makes them feel better, but the dose often needs to be adjusted for the best effect. In addition, many people with hypothyroidism do not know they have it. Research is ongoing to ensure that more people with hypothyroidism are diagnosed and are given effective treatment, and to work out the best way to use levothyroxine so that patients get the best results.

Incremental health care services and expenditures associated with depression among individuals with cutaneous lupus erythematosus (CLE)

Objectives

The objective of this paper is to describe the annual direct medical expenditures for cutaneous lupus erythematosus (CLE) patients, and to estimate the incremental health care expenditures and utilization associated with depression among adults with CLE, while controlling for covariates.

Methods

Using the 2014 Medical Expenditure Panel Survey (MEPS), we compared CLE patients with and without depression to determine differences in: (a) health care utilization—inpatient, outpatient, office-based and emergency room (ER) visits, and prescriptions filled; and (b) expenditures—total costs, inpatient, outpatient, office-based, ER, and prescription medication costs, and other costs using demography-adjusted and comorbidity-adjusted multivariate models (age, gender, race/ethnicity, marital status, education, perception of health status, poverty category, smoking status, and Charlson Comorbidity Index).

Results

The total direct medical expenditure associated with CLE is estimated at approximately $29.7 billion in 2014 US dollars. After adjusting for covariates, adults with CLE and depression had more hospital discharges (utilization ratio (UR) = 1.13, 95% confidence interval (CI) (1.00–1.28)), ER visits (UR = 1.17, 95% CI (1.09–1.37)), and prescribed medicines (UR = 2.15, 95% CI (1.51–3.05)) than those without depression. Adults with CLE and depression had significantly higher average annual total expenditure that those without depression ($19,854 vs. $9735).

Conclusions

High health care expenditures are significant for patients with CLE, especially among those with depression. Prescription drugs, inpatient visits, and ER visits contributed most to the total expenditures in CLE patients with depression. Early diagnosis and treatment of depression in CLE patients may reduce total health care expenditures and utilization in this population.

Sulfonylurea use and the risk of hospital readmission in patients with type 2 diabetes

BACKGROUND

Hospital inpatient care for patients with diabetes was estimated to cost $76 billion in 2012. Substantial expense resulted from those patients having multiple hospitalizations. The objective was to compare the risk for diabetes-related hospital readmission in patients with type 2 diabetes treated with sulfonylureas (SUs) compared to those treated with other oral antihyperglycemic agents (AHAs).

METHODS

A retrospective cohort analysis was conducted using two-year panels, from 1999 to 2010, from the Medical Expenditure Panel Survey. The study included patients with type 2 diabetes taking an oral AHA who experienced a diabetes-related hospitalization. A Cox proportional hazard regression predicting time to readmission was used to estimate and compare the risks of readmission for SU-monotherapy versus other-AHA-monotherapy patients. Covariates included age, gender, marital status, cardiovascular disease, kidney disease, and eye disease, along with a propensity score to control for selection bias. The lack of clinical data on disease severity and progression limited our ability to estimate causal relationships between drug use and risk of hospital readmission.

RESULTS

From 1999 to 2010, an estimated 13.5 million patients experienced a diabetes-related hospital admission and subsequent AHA treatment. While 23.2 % (n = 746,579) of patients in the SU monotherapy cohort had a readmission, only 16.1 % (n = 881,984) in the other-AHA monotherapy group were readmitted. Average readmission expenditure for readmitted SU users (in 2010 dollars) was $11,148 (±$1,558) compared to $7,673 (±$763) for users of other oral AHAs. The estimated readmission hazard ratio was 1.29 (95 % CI: 1.01-1.65; p-value = 0.04) for SU monotherapy users. If a patient's first hospital admission was during the time period 2008-2010, a readmission was significantly less likely (HR 0.49, 95 % CI: 0.31-0.78; p = 0.003) relative to 2004-2007.

CONCLUSIONS

Among patients with type 2 diabetes, SU use was associated with an approximately 30 % increased risk for readmission compared to other-AHA use, while each readmission for an SU user cost on average 45 % more than one for an other-AHA patient. Because of the rapidly rising prevalence of diabetes in the U.S. and the large number of patients with prediabetes, preventing hospital readmissions will continue to be an important cost-saving strategy in the future.

Chronic condition combinations and health care expenditures and out-of-pocket spending burden among adults, Medical Expenditure Panel Survey, 2009 and 2011

INTRODUCTION

Little is known about how combinations of chronic conditions in adults affect total health care expenditures. Our objective was to estimate the annual average total expenditures and out-of-pocket spending burden among US adults by combinations of conditions.

METHODS

We conducted a cross-sectional study using 2009 and 2011 data from the Medical Expenditure Panel Survey. The sample consisted of 9,296 adults aged 21 years or older with at least 2 of the following 4 highly prevalent chronic conditions: arthritis, diabetes mellitus, heart disease, and hypertension. Unadjusted and adjusted regression techniques were used to examine the association between chronic condition combinations and log-transformed total expenditures. Logistic regressions were used to analyze the relationship between chronic condition combinations and high out-of-pocket spending burden.

RESULTS

Among adults with chronic conditions, adults with all 4 conditions had the highest average total expenditures ($20,016), whereas adults with diabetes/hypertension had the lowest annual total expenditures ($7,116). In adjusted models, adults with diabetes/hypertension and hypertension/arthritis had lower health care expenditures than adults with diabetes/heart disease (P < .001). In adjusted models, adults with all 4 conditions had higher expenditures compared with those with diabetes and heart disease. However, the difference was only marginally significant (P = .04).

CONCLUSION

Among adults with arthritis, diabetes, heart disease, and hypertension, total health care expenditures differed by type of chronic condition combinations. For individuals with multiple chronic conditions, such as heart disease and diabetes, new models of care management are needed to reduce the cost burden on the payers.