• International Journal of Heart Failure
• /
• v.6 no.1
• /
• pp.11-19
• /
• 2024

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.1
• /
• pp.109-116
• /
• 2016

Objectives : This study aimed to investigate the effects of resilience on posttraumatic stress symptoms and dissociation and whether depression mediates the relationships between resilience and posttraumatic stress symptoms and dissociation. Methods : A total of 115 firefighters participated in the study. Data were collected via the Life Events Checklist, Impact of Event Scale-Revised, Dissociative Experience Scale, Beck Depression Inventory, and Connor-Davidson Resilience Scale. Structural equation modeling and path analysis were applied to estimate the relationships between resilience, depression, posttraumatic stress symptoms, and dissociation. Results : Greater resilience was associated with lower posttraumatic stress symptoms and dissociation, and the relationship between them was fully mediated by depression. Conclusions : Specific aspects of depression may help explain the relationships between resilience and posttraumatic stress symptoms and dissociation. Tailored prevention programs and treatments based on resilience and depression may prevent posttraumatic stress symptoms and dissociation in firefighters and improve treatments outcomes among firefighters with posttraumatic stress symptoms and/or dissociation.

• Korean Journal of Psychosomatic Medicine
• /
• v.28 no.2
• /
• pp.99-107
• /
• 2020

Fibromyalgia is a disorder characterized by the core symptom of chronic widespread pain, along with fatigue, sleep disturbances, mood changes, and cognitive difficulties. The etiology of fibromyalgia involves a combination of biological factors, such as genetic vulnerability, alterations in pain processing and stress response system ; psychological factors, such as anxiety, depression, anger, and perceived stress ; environmental factors, such as infections, febrile diseases, and trauma. Central sensitization, which is amplified in the process of sensory stimulation, has been emphasized as a key etiological factor, as supported by enhanced wind-up, delayed aftersensation, decreased nociceptive flexion reflex threshold and functional imaging studies. Several guidelines recommend that a multimodal approach be used to treat fibromyalgia, including both pharmacological and non-pharmacological treatments, tailored to each individual, and that clinicians should provide an intellectual framework through sufficient education and emphasis on the importance of self-management. The prevalence of mood disorders, anxiety disorders, and other psychiatric problems is 7-9 times higher in patients with fibromyalgia than in the general population ; moreover, the association between fibromyalgia and certain psychopathologies or sleep problems has also been suggested. Since psychiatric problems, with shared vulnerabilities and risk factors, interact with fibromyalgia bidirectionally and also affect the disease course, an integrated management approach is needed to determine the risk of comorbidities.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.309-327
• /
• 2021

Dynamic treatment regimes (DTRs) are decision-making rules designed to provide personalized treatment to individuals in multi-stage randomized trials. Unlike classical methods, in which all individuals are prescribed the same type of treatment, DTRs prescribe patient-tailored treatments which take into account individual characteristics that may change over time. The Q-learning method, one of regression-based algorithms to figure out optimal treatment rules, becomes more popular as it can be easily implemented. However, the performance of the Q-learning algorithm heavily relies on the correct specification of the Q-function for response, especially in observational studies. In this article, we examine a number of double-robust weighted least-squares estimating methods for Q-learning in high-dimensional settings, where treatment models for propensity score and penalization for sparse estimation are also investigated. We further consider flexible ensemble machine learning methods for the treatment model to achieve double-robustness, so that optimal decision rule can be correctly estimated as long as at least one of the outcome model or treatment model is correct. Extensive simulation studies show that the proposed methods work well with practical sample sizes. The practical utility of the proposed methods is proven with real data example.

• Journal of Oral Medicine and Pain
• /
• v.34 no.4
• /
• pp.397-407
• /
• 2009

The aim of the study was to evaluate psychosocial impact of non-dental chronic orofacial pain (OFP) on daily living using the graded chronic pain (GCP) scale. It is also investigated the clinical profile such as demographics, event related to initiation of OFP and prior treatments for patients. During previous 6 months since September 2008, 572 patients (M:F=1:1.5, mean age=34.7 years) with non-dental OFP attended university-based specialist orofacial pain clinic (Dankook University Dental Hospital, Cheonan) to seek care although 63% of them already experienced related treatment for their OFP problem. They visited the most frequently general dental practitioner and orthopedic doctors due to their pain problem and medication was the most commonly employed modality. Most of the patients (89.2%) had TMD and the most common related event to initiation of their pain was trauma, followed by dental treatment. Almost half of the patients (46%) suffered from chronic pain(${\geq}6\;M$) and 40% of them exhibited relatively high disability due to chronic OFP. GCP pain intensity and disability days were significantly different for age and diagnosis (p<0.05) but not for gender and duration. GCP grades were affected by all the factors including gender, age, pain duration and diagnosis.(p=0.000) Female gender, elders, and long lasting pain were closely related to high disability. The patients with neuropathic Pain and mixed OFP rather than TMD were graded as being highly disabled. Conclusively, a considerable percentage of chronic OFP patients reports high pain-related disability in their daily, social and work activity, which suggest a need for psychosocial support and importance of earlier referral for appropriate diagnosis and tailored management.