UNASSIGNED: Artificial intelligence (AI) has the capability to analyze vast amounts of data and has been applied in various healthcare sectors. However, its effectiveness in aiding pharmacotherapy decision-making remains uncertain due to the intricate, patient-specific, and dynamic nature of this field.
UNASSIGNED: This study sought to investigate the potential of AI in guiding pharmacotherapy decisions using clinical data such as diagnoses, laboratory results, and vital signs obtained from routine patient care.
UNASSIGNED: Data of a previous study on medication therapy optimization was updated and adapted for the purpose of this study. Analysis was conducted using R software along with the tidymodels extension packages. The dataset was split into 74% for training and 26% for testing. Decision trees were selected as the primary model due to their simplicity, transparency, and interpretability. To prevent overfitting, bootstrapping techniques were employed, and hyperparameters were fine-tuned. Performance metrics such as areas under the curve and accuracies were computed.
UNASSIGNED: The study cohort comprised 101 elderly patients with multiple diagnoses and complex medication regimens. The AI model demonstrated prediction accuracies ranging from 38% to 100% for various cardiovascular drug classes. Laboratory data and vital signs could not be interpreted, as the effect and dependence were unclear for the model. The study revealed that the issue of AI lag time in responding to sudden changes could be addressed by manually adjusting decision trees, a task not feasible with neural networks.
UNASSIGNED: In conclusion, the AI model exhibited promise in recommending appropriate medications for individual patients. While the study identified several obstacles during model development, most were successfully resolved. Future AI studies need to include the drug effect, not only the drug, if laboratory data is part of the decision. This could assist with interpreting their potential relationship. Human oversight and intervention remain essential for an AI-driven pharmacotherapy decision support system to ensure safe and effective patient care.

BACKGROUND: During the pandemic period, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) mutated, leading to changes in the disease\'s severity and the therapeutic effect of drugs accordingly. This study aimed to present the actual use of therapeutics and clinical outcomes based on the prevalence of each variant using real-world data.
METHODS: We analyzed the electronic medical records of adult patients admitted to Busan Medical Center after confirming coronavirus disease 2019 (COVID-19) from February 1, 2020, to June 30, 2022. Patients with mild-to-moderate COVID-19 who were at a high risk of disease progression were selected as study subjects, and the time period was classified according to the variants as ancestral strain, Delta variant, or Omicron variant. We compared drug use status and clinical outcomes by time period.
RESULTS: Among all 3,091 patients, corticosteroids were the most commonly used therapy (56.0%), being used most frequently in the Delta variant (93.0%), followed by the Omicron variant (42.9%) and ancestral strain (21.2%). Regdanvimab accounted for the majority of therapeutic use in the Delta variant (82.9%) and ancestral strain (76.8%), whereas remdesivir was most frequently used during the Omicron variant period (68.9%). The composite outcomes of death or disease aggravation were ranked in the order of the Delta variant, Omicron variant, and ancestral strain (14.5, 11.9, and 6.0%, respectively, P < 0.001).
CONCLUSIONS: Regdanvimab was primarily used during the ancestral strain period, regdanvimab plus corticosteroids during the Delta variant period, and remdesivir during the Omicron variant period. The rate of death or disease aggravation was highest in the Delta variant, followed by the Omicron variant and the ancestral strain.

OBJECTIVE: This study was conducted to assess the efficacy of daily 2000 mg eicosapentaenoic acid (EPA) supplementation in individuals with chronic migraine.
BACKGROUND: Chronic migraine is characterized by a minimum of 15 headache days/month, necessitating a focus on preventive treatment strategies. EPA, a polyunsaturated fatty acid recognized for its anti-inflammatory properties, is examined for its potential effectiveness in chronic migraine management.
METHODS: A randomized, blinded, placebo-controlled trial of eligible participants with a confirmed diagnosis of chronic migraine were enrolled. The intervention group received 1000 mg of EPA twice daily for 8 weeks, while the control group received two placebo softgels. Symptoms were recorded at 4 and 8 weeks. The primary outcome was assessed using the Headache Impact Test-6 to evaluate changes in patients. Secondary outcomes encompassed migraine headache days, headache severity measured via a visual analog scale, and the number of consumed painkillers. Descriptive analyses were reported in mean (± standard deviation [SD]).
RESULTS: A total of 60 patients were included in the study and finally, 56 patients completed the study according to the protocol, including 47 (84%) females. The data comparison at baseline did not show any significant difference between the two groups except in the number of patients using valproic acid as prophylaxis (21 patients in the EPA group, and 13 in the placebo group; p = 0.037). The results showed after 8 weeks, a mean (SD) difference of Headache Impact Test-6 in the EPA and placebo groups was -6.96 (3.34) and -4.43 (5.24), respectively (p = 0.084). Regarding migraine headache days, participants reported a mean (SD) -9.76 (4.15) and -4.60 (4.87) decline in days with headache, respectively (p < 0.001). The number of attacks per month after 8 weeks was 3.0 (95% confidence interval [CI] 2.0-4.0) and 4.0 (95% CI 3.0-6.0), respectively (p < 0.001). Regarding severity, there was no significant difference between the two groups (mean [SD] difference: -0.76 [1.13] and -0.73 [1.04], respectively; p = 0.906). In terms of adverse events, two patients in the EPA group reported intolerable nausea and vomiting, and one patient in the placebo group reported dizziness.
CONCLUSIONS: This study\'s findings support the potential of a daily 2000 mg EPA as a prophylactic pharmacotherapy in chronic migraine management, specifically in mitigating migraine attacks, migraine headache days, and overall quality of life.

Surgical interventions, like barbed reposition pharyngoplasty (BRP), are a valuable alternative for patients with obstructive sleep apnea (OSA) who are unable to tolerate continuous positive airway pressure (CPAP). However, predicting surgical success remains challenging, partly due to the contribution of non-anatomical factors. Therefore, combined medical treatment with acetazolamide, known to stabilize respiratory drive, may lead to superior surgical results. This double-blind, parallel-group randomized controlled trial evaluates the efficacy of acetazolamide as an add-on therapy to BRP in OSA. A total of 26 patients with moderate to severe OSA undergoing BRP were randomized to receive either acetazolamide or placebo post-surgery for 16 weeks. The group who was treated with BRP in combination with acetazolamide showed a reduction in AHI of 69.4%, significantly surpassing the 32.7% reduction of the BRP + placebo group (p < 0.01). The sleep apnea-specific hypoxic burden also decreased significantly in the group who was treated with BRP + acetazolamide (p < 0.01), but not in the group receiving BRP + placebo (p = 0.28). Based on these results, acetazolamide as an add-on therapy following BRP surgery shows promise in improving outcomes for OSA patients, addressing both anatomical and non-anatomical factors.

OBJECTIVE: Severe chronic insomnia is a common sleep disorder that is mostly persistent and needs to be treated. Pharmacologic treatment options and guidelines are sparse, particularly for long-term treatment. Our study aims to investigate a graduated therapy scheme for moderate to severe chronic insomnia in practice, considering the effects on self-reported sleep quality and quality of life.
METHODS: Patients with moderate to severe chronic insomnia are given appropriate medication according to a graduated therapy scheme, ranging from L-tryptophan (as the first choice, least potent) to Z-drugs and combination therapies (as the last option, most potent). Each step of the graduated therapy scheme was tested for at least 4 weeks. Sleep- and quality of life-related data were collected in questionnaire form (ISI, PSQI, BDI-II, SF-36) at baseline and during the course of the treatment after 1, 3, 6, 9, and 12 months.
RESULTS: Of 86 eligible patients, 60.5% started treatment with L-tryptophan and 8.1% with melatonin. After 3 months, 12.5% were still taking L-tryptophan and 12.5% were taking melatonin. There was a significant decrease in mean ISI, PSQI, BDI-II, and SF-36 scores after 3 months of treatment for all patients in the study (n=64). After 6 months, 22.2% were still taking L-tryptophan, melatonin, or agomelatine, and the remainder had switched to more potent drugs such as antidepressants, hypnotics, daridorexant, or combination therapies.
CONCLUSIONS: A significant number of patients already responded favorably to mild sleep medications, while others demonstrated their need for more potent treatments. Ongoing monitoring will evaluate the long-term effectiveness of both approaches.
BACKGROUND: Registy: German Clinical Trials Register; Title: Schlafqualität und Lebensqualität mit einer medikamentösen Langzeittherapie bei moderater bis schwerer Insomnie; Identifier: DRKS00033175; URL: https://drks.de/search/de/trial/DRKS00033175.

BACKGROUND: In this nationwide register study, we examined the initiation of a second-line antidiabetic medicine (ADM) among new patients receiving regular metformin monotherapy in Finland during 2011-2022. We also reflected the second-line treatment patterns on changes in the reimbursement policy, and the national type 2 diabetes (T2D) care guidelines.
METHODS: Using register data on all reimbursed ADM purchases during 2010-2022, we defined nine annual cohorts of patients initiating regular metformin monotherapy during 2011-2019, each with a three-year follow-up. Descriptive methods were used to study the patterns of metformin monotherapy and second-line intensification over time. Proportional hazards models were used to analyse the take-up of the second-line ADM.
RESULTS: The share of new patients initiating metformin use (11-13% of all metformin users) and regular metformin use (83-85% of all new metformin users) remained stable. In all cohorts, 16-19% of the patients took up a second-line ADM (median time to intensification 1.5 years). With the 2011 cohort as reference, the highest proportion of new regular metformin users taking up a second ADM (hazard ratio 1.12. 95% confidence interval 1.07 ; 1.16, P < .0001) was in the 2019 cohort. In the 2017 cohort, the proportion of patients initiating sodium-glucose cotransporter 2 inhibitors as second-line treatment surpassed those initiating dipeptidyl peptidase-4 inhibitors. The reimbursement policy restricted the use of GLP-1-analogues.
CONCLUSIONS: Second-line treatment intensification patterns over time paralleled the changes in the reimbursement system. Thus, our findings suggest that the reimbursement policy may influence the use of ADMs in Finland.

UNASSIGNED: Monitoring the pharmacotherapy adherence in society is crucial for identifying occurance and causes of potential inadequate use of drugs and inform providers about the need for better customer counceling. It is necessary component of the strategic planning of the quality of healthcare services. This population- based study aimed to assess the medication intake adherence in the Republic of Serbia and the individual factors and health system variables influencing its pattern.
UNASSIGNED: We applied a cross-sectional approach to study medication intake adherence using a secondary analysis of the latest 2019 Serbian National Health Survey data. The statistical modeling of the pharmacotherapy adherence incorporated sociodemographic data, self-reported disease, and lifestyle behavior.
UNASSIGNED: In 2019, in the representative sample of 12,066 adults in Serbia, requiring prescribed medicine, 49.8% did comply with the prescribed drugs, and 50.2% do not. Participants who adhered to prescribed medication were significantly (p < 0.001) older (62.4 ± 14 years), predominantly female (55.3%), had secondary education (48.5%), resided in southern and eastern parts of Serbia (55.5%), and belonged to the lowest income quintile (21.4%). The participants most often take prescribed drugs for hypertension (64.1%) and lower back pain (30.5%), while around 20% take medication for coronary disease, diabetes mellitus, and high blood cholesterol. About 85-92% of participants with financial or general difficulties using prescribed medication.
UNASSIGNED: There is poor medication intake adherence to prescribed medication in Serbia. Gender, age, and region determine the adherence. Also, health-related and healthcare system-related factors impact the use of prescribed medication. Study findings can inform planning the counceling interventions in the target groups where improving medication adherence is necessary, as well as to enhance training of healthcare providers about pharmacotherapy adherence.

BACKGROUND: We assessed the association of prescription data with clinical manifestations and polygenic risk scores (PRS) in patients with bipolar I disorder.
METHODS: We enrolled 1471 individuals with BID and divided them into several groups according to treatment options and clinical manifestations. BD-PRS of each patient was calculated using the Psychiatric Genomics Consortium data. Data on single nucleotide polymorphisms, clinical manifestations, and prescriptions were extracted from BiGS.
RESULTS: Chronicity, suicidality, substance misuse, mixed symptoms, and deterioration of life functioning were significantly more severe in the group that was not prescribed any mood stabilizers (MS). Chronicity, psychotic symptoms, suicidality, and deterioration of life functioning were significantly severe in the group that received two or more antipsychotics (APs). BD-PRS between the group with AP(s) only and that with other treatment options significantly differed. BD-PRS of the group with AP(s) only was significantly lower than that with other treatment options. Our linear regression results showed that high severity of particular clinical aspects, lower BD-PRS, and prescriptions with fewer MSs or more APs were independently associated with poor life functioning.
CONCLUSIONS: This study had a cross-sectional design, without differentiating the bipolar phase, which could influence our results.
CONCLUSIONS: Poor life functioning in patients with BID was associated with a high severity of particular clinical aspects, BD-PRS, and prescriptions including fewer MSs or more APs. BD-PRS was significantly higher in the group receiving only AP(s) than that in the groups receiving other drugs.

BACKGROUND: The development of alcohol use disorder (AUD) is a major concern in public health, and cognitive impairments caused by alcohol are involved in this process. Emerging neurobiological evidence suggests that donepezil, an anticholinesterase agent, may improve AUD treatment outcomes by enhancing neurocognitive functioning. Previous research has also suggested that cognitive remediation therapy (CRT) could potentially improve cognitive function and AUD treatment outcomes. We present the rationale and design of a trial to evaluate the combination of donepezil and cognitive remediation therapy (donepezil + CRT) as an intervention for AUD.
METHODS: We propose a 13-week, randomized, double-blind, placebo-controlled, between-subjects trial comparing 4 groups (donepezil + CRT vs. donepezil alone vs. CRT alone vs. placebos) as an intervention for AUD. The main goal of the study is to evaluate if donepezil + CRT is superior to placebo in reducing heavy drinking days and improving neurocognitive functioning. A total of 160 patients (4 groups, 40 per each group) with AUD between the ages of 18-80 years will be recruited at Yale University and the VA Connecticut Healthcare System. Primary outcome measures include 1) heavy drinking by Timeline Follow Back (TLFB) over 13 weeks and 2) global neurocognitive functioning by a global index of neurocognitive function score at 7 and 13 weeks.
CONCLUSIONS: This protocol paper describes the rationale and proposed methods for the randomized controlled trial for improving AUD treatment outcomes. This project has significant clinical potential to help patients suffering from AUD by improving their cognition and reducing alcohol consumption.
BACKGROUND: NCT05042102.

BACKGROUND: Up to 50% of adolescents who undergo metabolic and bariatric surgery (MBS) have obesity 3 years post-MBS, placing them at continued risk for the consequences of obesity.
OBJECTIVE: We conducted an open-label, 16-week pilot study of liraglutide in adolescents with obesity after sleeve gastrectomy (SG) to investigate liraglutide effects on weight and body mass index (BMI) post-SG.
METHODS: Adolescents aged 12-20.99 years with obesity and a history of SG ≥1 year prior were enrolled. Liraglutide was initiated at 0.6 mg/day, escalated weekly to a maximum of 3 mg/day, with treatment duration 16 weeks. Fasting laboratory assessments and an oral glucose tolerance test were performed at baseline and end-treatment.
RESULTS: A total of 43 participants were screened, 34 initiated liraglutide (baseline BMI 41.2 ± 7.7 kg/m2), and 31 (91%) attended the end-treatment visit. BMI decreased by 4.3% (p < 0.001) with liraglutide. Adolescents who had poor initial response to SG (<20% BMI reduction at BMI nadir) had less weight loss with liraglutide. Fasting glucose and haemoglobin A1C concentrations significantly decreased. There were no serious treatment-emergent adverse events reported.
CONCLUSIONS: Liraglutide treatment was feasible and associated with a BMI reduction of 4.3% in adolescents who had previously undergone SG, quantitatively similar to results obtained in adolescents with obesity who have not undergone MBS.