Mental Health Applications of Generative AI and Large Language Modeling in the United States.

(1) Background: Artificial intelligence (AI) has flourished in recent years. More specifically, generative AI has had broad applications in many disciplines. While mental illness is on the rise, AI has proven valuable in aiding the diagnosis and treatment of mental disorders. However, there is little to no research about precisely how much interest there is in AI technology. (2) Methods: We performed a Google Trends search for "AI and mental health" and compared relative search volume (RSV) indices of "AI", "AI and Depression", and "AI and anxiety". This time series study employed Box-Jenkins time series modeling to forecast long-term interest through the end of 2024. (3) Results: Within the United States, AI interest steadily increased throughout 2023, with some anomalies due to media reporting. Through predictive models, we found that this trend is predicted to increase 114% through the end of the year 2024, with public interest in AI applications being on the rise. (4) Conclusions: According to our study, we found that the awareness of AI has drastically increased throughout 2023, especially in mental health. This demonstrates increasing public awareness of mental health and AI, making advocacy and education about AI technology of paramount importance.

Risk Factors for Symptomatic Atrial Fibrillation-Analysis of an Outpatient Database.

Atrial fibrillation (AF) is the most common sustained arrhythmia encountered in practice and is the leading cause of debilitating strokes with significant economic burden. It is currently not known whether asymptomatic undiagnosed AF should be treated if detected by various screening methods. Currently, United States guidelines have no recommendations for identifying patients with asymptomatic undiagnosed AF due to lack of evidence. The American Heart Association Center for Health Technology & Innovation undertook a plan to identify tools in 3 phases that may be useful in improving outcomes in patients with undiagnosed AF. In phase I we sought to identify AF risk factors that can be used to develop a risk score to identify high-risk patients using a large commercial insurance dataset. The principal findings of this study show that individuals at high risk for AF are those with advanced age, the presence of heart failure, coronary artery disease, hypertension, metabolic disorders, and hyperlipidemia. Our analysis also found that chronic respiratory failure was a significant risk factor for those over 65 years of age and chronic kidney disease for those less than 65 years of age.

Best practices in digital health literacy.

The connection between health literacy and health outcomes includes access and utilization of healthcare services, patient/provider interaction and self-care. Digital approaches can be designed to simplify or expand on a concept, test for understanding, and do not have a time constraint. New technologies, such as artificial intelligence and machine learning, virtual and augmented reality, and blockchain can move the role of technology beyond data collection to a more integrated system. Rather than being a passive participant, digital solutions provide the opportunity for the individual to be an active participant in their health. These solutions can be delivered in a way that builds or enhances the individual's belief that the plan will be successful and more confidence that they can stick with it. Digital solutions allow for the delivery of multi-media education, such as videos, voice, and print, at different reading levels, in multiple languages, using formal and informal teaching methods. By giving the patient a greater voice and empowering them to be active participants in their care, they can develop their decision making and shared decision making skills. The first step in our health literacy instructional model is to address the emotional state of the person. Once the emotional state has been addressed, and an engagement strategy has been deployed the final phase is the delivery of an educational solution. While a clear definition of health literacy and an instructional model are important, further research must be done to continually determine more effective ways to incorporate health technology in the process of improving health outcomes.

Improving health literacy in patients with chronic conditions: A call to action.

Knowledge and education is foundational to an individual receiving care, and health literacy is the ability of patients to understand and act on health information. Cardiovascular disease and diabetes are complex conditions that require active participation on the part of the patient. Lack of understanding on the condition and participation in self-care behaviors limits the effectiveness of treatment. An effective model is needed to better understand how patients with cardiovascular disease and diabetes acquire the knowledge and skills necessary to manage their health. In working together, the authors have created multiple programs that have been delivered at medical offices and corporations, resulting in a model for building functional and critical health literacy skills. This model is a progression that begins with health literacy, including the knowledge and understanding of the condition. Functional literacy includes numeracy, which is the ability to understand and manipulate numbers, and navigation, which is an understanding of what to do with the information. Finally, critical health literacy includes communication skills, including knowing what questions to ask and what information to share, and decision making, which can include shared decision making. These five levels of health literacy form a progression in the ability of the patient to become an active participant in their care, and inform the healthcare provider on effective educational methods.

An exploratory retrospective assessment of a quantitative measure of diabetes risk: medical management and patient impact in a primary care setting.

BACKGROUND: Primary care providers with limited time and resources bear a heavy responsibility for chronic disease prevention or progression. Reliable clinical tools are needed to risk stratify patients for more targeted care. This exploratory study examined the care of patients who had been risk stratified regarding their likelihood of clinically progressing to type 2 diabetes. METHODS: This was a retrospective chart review pilot study conducted to assess a primary care provider's use of a risk screening test. In this quality improvement project, the result of the risk screening was examined in relation to its influence on medical management and clinical impact on patients at risk for diabetes. All providers were board certified in family medicine and had more than 10 years clinical experience in managing diabetes and prediabetes. No specific clinical practice guidelines were mandated for patient care in this pilot study. Physicians in the practice group received an orientation to the diabetes risk measure and its availability for use in a pilot study to be conducted over a 6-month period. We identified the 696 nondiabetic adults in family practices who received a risk screening test (PreDx(®), a multi-marker blood test that estimates the 5-year likelihood of conversion to type 2 diabetes) between June and November 2011 for a 6-month sample. A comparison group of 2,002 patients from a total database of 3.2 million patients who did not receive the risk test was randomly selected from the same clinical database after matching for age, sex, selected diagnoses, and metabolic risk factors. Patient groups were compared for intensity of care provided and clinical impact. RESULTS: Compared to patients with a similar demographic and diagnostic profile, patients who had the risk test received more intensive primary care and had better clinical outcome than comparison patients. Risk-tested patients were more likely to return for follow-up visits, be monitored for relevant cardio-metabolic risk factors, and receive prescription medications with P<0.001. Further, intensity of care was associated with the level of risk test result: patients with moderate or high scores were more likely to return for follow-up visits and receive prescription medications than patients with low scores. All P-values for comparison patients between the low and moderate groups, low and high groups, and moderate and high groups resulted in P<0.001. Risk-tested patients were more likely than their comparison group counterparts to achieve weight reduction, lowered blood pressure, and improved blood glucose and cholesterol as demonstrated by P-values of <0.001. CONCLUSION: Use of a risk stratification test in primary care may help providers to more effectively identify high risk patients, manage diabetes risk, increase patient involvement in diabetes risk management, and improve clinical outcomes. A randomized controlled study is the next step to investigate the impact of diabetes risk stratification in primary care.

The Game of Health©: an innovative lifestyle change program implemented in a family practice.

PURPOSE: The purpose of this clinical pilot project was to evaluate the effectiveness of a 12 week lifestyle change program targeted to patients with chronic disease. DATA SOURCES: Data were collected weekly from participants using individual and group feedback and body composition analysis. CONCLUSIONS: The Game of Health was well received by patients and was effective in modifying behaviors to achieve a healthier lifestyle and to improve body composition. Primary care providers need to consider how to make lifestyle change programs available to their patients to complement clinical interventions.

Influence of age, gender, and race on the efficacy of adding ezetimibe to atorvastatin vs. atorvastatin up-titration in patients at moderately high or high risk for coronary heart disease.

BACKGROUND: Age, gender, and race are factors that influence atherosclerotic coronary heart disease (CHD) risk and may conceivably affect the efficacy of lipid-altering drugs. METHODS: Post hoc analysis of two multicenter, 6-week, double-blind, randomized, parallel-group trials assessed age (<65 and ≥ 65 years), gender, and race (white, black, and other) effects on atorvastatin plus ezetimibe versus up-titration of atorvastatin in hypercholesterolemic patients with CHD risk. High CHD risk subjects with low-density lipoprotein (LDL) cholesterol levels ≥ 70 mg/dL (~1.81 mmol/L) during stable atorvastatin 40 mg therapy were randomized to atorvastatin 40 mg plus ezetimibe 10mg, or up-titrated to atorvastatin 80 mg. Moderately high CHD risk subjects with LDL cholesterol levels ≥ 100 mg/dL (~2.59 mmol/L) with atorvastatin 20mg were randomized to atorvastatin 20mg plus ezetimibe 10mg, or atorvastatin 40 mg. RESULTS: Although some variability existed, age, gender, and race subgroups did not substantially differ from the entire patient population with regard to lipid-altering findings. Ezetimibe plus atorvastatin produced greater percent reductions in LDL cholesterol, total cholesterol, triglycerides, non-high-density lipoprotein (HDL) cholesterol, and apolipoprotein B than up-titration of atorvastatin for all subgroups. HDL cholesterol and apolipoprotein AI changes were small and variable. CONCLUSION: Treatment efficacy in age, gender, and race subgroups did not substantially differ from the entire study population. Ezetimibe combined with atorvastatin generally produced greater incremental reductions in LDL cholesterol and several other key lipid parameters compared with doubling the atorvastatin dose in hypercholesterolemic patients with high or moderately high CHD risk. These results suggest that co-administration of ezetimibe with statins is a useful therapeutic option for treatment of dyslipidemia in differing patient populations.

Are post-treatment low-density lipoprotein subclass pattern analyses potentially misleading?

BACKGROUND: Some patients administered cholesterol-lowering therapies may experience an increase in the proportion of small LDL particles, which may be misinterpreted as a worsening of atherosclerotic coronary heart disease risk. This study assessed the lipid effects of adding ezetimibe to atorvastatin or doubling the atorvastatin dose on low-density lipoprotein cholesterol (LDL-C) levels (and the cholesterol content of LDL subclasses), LDL particle number (approximated by apolipoprotein B), and LDL particle size. This was a multicenter, double-blind, randomized, parallel-group study of hypercholesterolemic, high atherosclerotic coronary heart disease risk patients. After stabilization of atorvastatin 40 mg, 579 patients with LDL-C >70 mg/dL were randomized to 6 weeks of ezetimibe + atorvastatin 40 mg or atorvastatin 80 mg. Efficacy parameters included changes from baseline in LDL-C, apolipoprotein B, non-high-density lipoprotein cholesterol (non-HDL-C), and lipoprotein subclasses (Vertical Auto Profile II) and pattern for the overall population, as well as patient subgroups with baseline triglyceride levels <150 mg/dL or ≥150 mg/dL. RESULTS: Both treatments significantly reduced LDL-C (and the cholesterol content of most LDL subfractions [LDL1-4]) apolipoprotein B, non-HDL-C levels, but did not reduce the proportion of smaller, more dense LDL particles; in fact, the proportion of Pattern B was numerically increased. Results were generally similar in patients with triglyceride levels <150 or ≥150 mg/dL. CONCLUSIONS: When assessing the effects of escalating cholesterol-lowering therapy, effects upon Pattern B alone to assess coronary heart disease risk may be misleading when interpreted without considerations of other lipid effects, such as reductions in LDL-C, atherogenic lipoprotein particle concentration, and non-HDL-C levels. TRIAL REGISTRATION: (Registered at clinicaltrials.gov: Clinical trial # NCT00276484).

Healthcare costs associated with switching from brand to generic levothyroxine.

BACKGROUND: Controversy exists over the true therapeutic equivalence of branded and generic levothyroxine-the drug of choice for treating hypothyroidism-so professional societies recommend against switching between different formulations of the drug and suggest that patients who do switch be monitored. Payers typically encourage switching to generic drugs because of lower drug acquisition costs. OBJECTIVE: To evaluate the impact of switching levothyroxine formulations on actual healthcare costs. METHODS: Patients with hypothyroidism and at least 6 months of branded levothyroxine therapy were identified from a large healthcare claims database. Patients who subsequently switched to another levothyroxine formulation and could be followed for 6 months postswitch were matched to demographically similar patients who were continuous users of branded levothyroxine. Pre- and postswitch healthcare costs for each group were compared. RESULTS: The savings in prescription drug costs after switching from branded to generic levothyroxine are offset by increases in costs for other healthcare services, such that switching is actually associated with an increase, not a decrease, in total healthcare costs. CONCLUSION: In the absence of cost-savings, there is no clear rationale for switching patients from brand to generic levothyroxine.

Efficacy and safety of ezetimibe added on to atorvastatin (20 mg) versus uptitration of atorvastatin (to 40 mg) in hypercholesterolemic patients at moderately high risk for coronary heart disease.

The aim of this study was to evaluate the efficacy and safety of ezetimibe 10 mg added to atorvastatin 20 mg compared with doubling atorvastatin to 40 mg in patients with hypercholesterolemia at moderately high risk for coronary heart disease who did not reach low-density lipoprotein (LDL) cholesterol levels <100 mg/dl with atorvastatin 20 mg. In this 6-week, multicenter, double-blind, randomized, parallel-group study, 196 patients treated with atorvastatin 20 mg received atorvastatin 20 mg plus ezetimibe 10 mg or atorvastatin 40 mg for 6 weeks. Adding ezetimibe 10 mg to atorvastatin 20 mg produced significantly greater reductions in LDL cholesterol than increasing atorvastatin to 40 mg (-31% vs -11%, p <0.001). Significantly greater reductions were also seen in non-high-density lipoprotein cholesterol, total cholesterol, and apolipoprotein B (p <0.001). Significantly more patients reached LDL cholesterol levels <100 mg/dl with atorvastatin 20 mg plus ezetimibe compared with atorvastatin 40 mg (84% vs 49%, p <0.001). The 2 treatment groups had comparable results for high-density lipoprotein cholesterol, triglycerides, apolipoprotein A-I, and high-sensitivity C-reactive protein. The incidences of clinical and laboratory adverse experiences were generally similar between groups. In conclusion, the addition of ezetimibe 10 mg to atorvastatin 20 mg was generally well tolerated and resulted in significantly greater lipid-lowering efficacy compared with doubling atorvastatin to 40 mg in patients with hypercholesterolemia at moderately high risk for coronary heart disease.

Efficacy and safety of ezetimibe added on to atorvastatin (40 mg) compared with uptitration of atorvastatin (to 80 mg) in hypercholesterolemic patients at high risk of coronary heart disease.

The percentage of change from baseline in low-density lipoprotein (LDL) cholesterol after the addition of ezetimibe 10 mg to atorvastatin 40 mg was compared with uptitration to atorvastatin 80 mg. In this multicenter, double-blind, parallel-group study, adult hypercholesterolemic patients using atorvastatin 40 mg/day were randomly assigned to atorvastatin 40 mg plus ezetimibe 10 mg or uptitration to atorvastatin 80 mg. After 6 weeks of treatment, compared with atorvastatin 80 mg, atorvastatin 40 mg plus ezetimibe significantly reduced the primary end point of LDL cholesterol by -27% versus atorvastatin 80 mg by -11% (p <0.001), as well as significantly reduced non-high-density lipoprotein cholesterol, apolipoprotein B, total cholesterol, and triglycerides significantly more than atorvastatin 80 mg (all p <0.001). Percentages of change in high-sensitivity C-reactive protein, high-density lipoprotein cholesterol, and apolipoprotein A-I were similar between groups. Significantly more patients treated with atorvastatin 40 mg plus ezetimibe reached LDL cholesterol <70 mg/dl versus patients treated with atorvastatin 80 mg (74% vs 32%; p <0.001). Safety and tolerability profiles and incidence of liver and muscle adverse experiences were generally similar between groups. In conclusion, these results showed that adding ezetimibe to atorvastatin 40 mg was significantly more effective than uptitrating to atorvastatin 80 mg at lowering LDL cholesterol and other lipid parameters. Both treatments were generally well tolerated (clinical trial no. NCT00276484).