Diagnostic capabilities of artificial intelligence as an additional reader in a breast cancer screening program.

OBJECTIVES: We aimed to evaluate the early-detection capabilities of AI in a screening program over its duration, with a specific focus on the detection of interval cancers, the early detection of cancers with the assistance of AI from prior visits, and its impact on workload for various reading scenarios. MATERIALS AND METHODS: The study included 22,621 mammograms of 8825 women within a 10-year biennial two-reader screening program. The statistical analysis focused on 5136 mammograms from 4282 women due to data retrieval issues, among whom 105 were diagnosed with breast cancer. The AI software assigned scores from 1 to 100. Histopathology results determined the ground truth, and Youden's index was used to establish a threshold. Tumor characteristics were analyzed with ANOVA and chi-squared test, and different workflow scenarios were evaluated using bootstrapping. RESULTS: The AI software achieved an AUC of 89.6% (86.1-93.2%, 95% CI). The optimal threshold was 30.44, yielding 72.38% sensitivity and 92.86% specificity. Initially, AI identified 57 screening-detected cancers (83.82%), 15 interval cancers (51.72%), and 4 missed cancers (50%). AI as a second reader could have led to earlier diagnosis in 24 patients (average 29.92 ± 19.67 months earlier). No significant differences were found in cancer-characteristics groups. A hybrid triage workflow scenario showed a potential 69.5% reduction in workload and a 30.5% increase in accuracy. CONCLUSION: This AI system exhibits high sensitivity and specificity in screening mammograms, effectively identifying interval and missed cancers and identifying 23% of cancers earlier in prior mammograms. Adopting AI as a triage mechanism has the potential to reduce workload by nearly 70%. CLINICAL RELEVANCE STATEMENT: The study proposes a more efficient method for screening programs, both in terms of workload and accuracy. KEY POINTS: • Incorporating AI as a triage tool in screening workflow improves sensitivity (72.38%) and specificity (92.86%), enhancing detection rates for interval and missed cancers. • AI-assisted triaging is effective in differentiating low and high-risk cases, reduces radiologist workload, and potentially enables broader screening coverage. • AI has the potential to facilitate early diagnosis compared to human reading.

A NEW DANGER OF BEHAVIORAL ADDICTION: CRYPTOCURRENCY WITH MOBILE INVESTING.

BACKGROUND: Cryptocurrencies are a popular investment tool today. However, some studies highlight the investing behavior of cryptocurrencies similar to pathological gambling. Investing behavior becomes risky when it is not based on proper and adequate analysis and carries the possibility of big losses as well as big gains. For this reason, we aimed to determine the potential risky investor profile by age, gender, personality traits and impulsivity levels. SUBJECTS AND METHODS: Six hundred and fifty-four cryptocurrencies investors (529 was male, 125 was female, their mean age was 35.6 ± 9.0) participated in this study between June 2022 - August 2022. Participants were administered the Sociodemographic Data Form, the South OAKS Gambling Screen Test - revised (SOGS-r), the Big Five Inventory (BFI-10), and Barratt Impulsiveness Scale-11 (BIS-11). RESULTS: We found higher neuroticism and impulsivity in possible problematic crypto investors. In addition, extraversion, agreeableness and conscientiousness scores were lower. Additionally, in our regression analyzes we found that younger age and male gender predicted SOGS-r scores. After controlling for age and gender, extraversion negatively and motor impulsivity positively predicted SOGS-r scores. DISCUSSION: Investing in cryptocurrencies can become a behavioral addiction, similar to pathological gambling. It is important to identify profiles in which investment behavior is risky. CONCLUSION: Personality traits and impulsivity may have a significant impact on identifying risky crypto investors and in the treatment process.

Diagnostic Performance of AI for Cancers Registered in A Mammography Screening Program: A Retrospective Analysis.

Purpose: To evaluate the performance of an artificial intelligence (AI) algorithm in a simulated screening setting and its effectiveness in detecting missed and interval cancers. Methods: Digital mammograms were collected from Bahcesehir Mammographic Screening Program which is the first organized, population-based, 10-year (2009-2019) screening program in Turkey. In total, 211 mammograms were extracted from the archive of the screening program in this retrospective study. One hundred ten of them were diagnosed as breast cancer (74 screen-detected, 27 interval, 9 missed), 101 of them were negative mammograms with a follow-up for at least 24 months. Cancer detection rates of radiologists in the screening program were compared with an AI system. Three different mammography assessment methods were used: (1) 2 radiologists' assessment at screening center, (2) AI assessment based on the established risk score threshold, (3) a hypothetical radiologist and AI team-up in which AI was considered to be the third reader. Results: Area under curve was 0.853 (95% CI = 0.801-0.905) and the cut-off value for risk score was 34.5% with a sensitivity of 72.8% and a specificity of 88.3% for AI cancer detection in ROC analysis. Cancer detection rates were 67.3% for radiologists, 72.7% for AI, and 83.6% for radiologist and AI team-up. AI detected 72.7% of all cancers on its own, of which 77.5% were screen-detected, 15% were interval cancers, and 7.5% were missed cancers. Conclusion: AI may potentially enhance the capacity of breast cancer screening programs by increasing cancer detection rates and decreasing false-negative evaluations.

Assessment of psychometric characteristics of the Coronavirus Anxiety Scale in patients with preexisting psychiatric disorders.

This study aimed to evaluate the psychometric characteristics of the Turkish version of the CAS in a Turkish psychiatric outpatient setting. A total of 198 patients with a preexisting psychiatric disorder completed the CAS scale. The scale's validity and reliability were evaluated using convergent and concurrent validity, internal consistency, exploratory and confirmatory factor analyses, and ROC analysis. The Turkish version of CAS might help physicians assess the COVID-19 associated anxiety in patients with psychiatric comorbidities.

The Effect of COVID-19 Outbreak on the Mental Status of Health Care Professionals in the Pediatric Intensive Care Unit.

BACKGROUND: Coronavirus disease 2019 (COVID-19) may affect the mental status of health care professionals. The purpose of our study is to evaluate the mental health effects of the COVID-19 epidemic on health care professionals in the pediatric intensive care units (PICUs). SUBJECTS AND METHODS: Our study was conducted prospectively between 01.04.20 and 10.04.20. The created questionnaire was applied to health care professionals through online platforms. Thus it was involved in 5 different institutions that participated from different regions of Turkey. With the questionnaire, we applied; the participants' age, gender, the general status of contamination and the level of COVID-19 knowledge were questioned. Besides; Beck Anxiety Scale, Acute Stress Scale (PCL-5), STAI-1 and STAI-2 (State and Trait Anxiety Inventory 1-2) scales were used to determine the anxiety levels. RESULTS: A survey of 210 participants, 86 (41%) doctors, 124 (59%) nurses, were included in our study. When we evaluate the Beck anxiety levels, the majority of the participants (44%) were normal, while about one third had mild anxiety. When we evaluated the acute stress scale, all participants had a certain amount of stress levels. The majority (80 people each (38%)) experienced mild and moderate acute stress. Being female and having chronic disease poses a high risk for anxiety (OR, 0.330; 95% CI, 0.087-1.250, p<0.05 and OR, 0.246; 95% CI, 0.068-1.116, p<0.05), preoccupation (OR, 0.603; 95% CI 0.261-1.395, p<0.05 and OR, 0.433; 95% CI, 0.122-1.538, p<0.05) and acute stress (OR, 0.294; 95% CI, 0.033-2.649, p<0.05 and OR, 0.317; 95% CI 0.060-1.679, p<0.05). Professional definition, marital status and having a child do not pose any risk factors. CONCLUSION: Our study has shown that the COVID-19 outbreak affects the mental status of health care professionals working at PICU at various levels.

Thalamic and Cerebellar Gray Matter Volume Reduction in Synthetic Cannabinoids Users.

BACKGROUND: Synthetic cannabinoids are compounds that bind cannabinoid receptors with a high potency and have been used widely in Europe by young people. However, little is known about the pharmacology and morphological effects of this group of substances in the brain. This study is aimed at investigating the morphological differences among synthetic cannabinoids users and healthy controls. METHODS: Voxel-based morphometry was used to investigate the differences in brain tissue composition in 20 patients with synthetic cannabinoids use and 20 healthy controls. All participants were male. RESULTS: Compared to healthy controls, voxel of interest analyses showed that regional grey matter volume in both left and right thalamus and left cerebellum was significantly reduced in synthetic cannabinoids users (p < 0.05). No correlation has been found between the age of first cannabis use, duration of use, frequency of use and grey matter volume. DISCUSSION: These preliminary results suggest an evidence of some structural differences in the brain of synthetic cannabinoids users, and point the need for further investigation of morphological effects of synthetic cannabinoids in the brain.

Atomoxetine Induced Hypothermia: A Case Report.

Adverse drug reactions are common in drugs used during childhood and adolescence. Atomoxetine, a selective reuptake inhibitor, was introduced as a safe non-stimulant alternative treatment for attention deficit hyperactivity disorder. Described common side effects of atomoxetine include: headache, abdominal pain, decreased appetite, fatigue, nausea, vomiting and dizziness. In our case, we present an adolescent male who developed hypothermia under atomoxetine treatment. To our knowledge, this is the first report of a causal connection between atomoxetine intake and hypothermia. Because hypothermia is a life-threatening condition and can be treated when interfered immediately, clinicians should be aware of this adverse effect of atomoxetine.

Enhancement of spike and wave discharges by microinjection of bicuculline into the reticular nucleus of rats with absence epilepsy.

The aim of this study was to demonstrate the effect of administration of gamma-aminobutyric acid (GABA)(A) receptor antagonist, bicuculline, into the reticular nucleus of the thalamus (nRt) on spike and wave discharges (SWD) and cardiovascular regulation in conscious rats with genetic absence epilepsy. Rats were instrumented with guide cannulas for drug injection and extradural electrodes for electroencephalogram recording. After a 1 week recovery period, iliac arterial catheters were inserted for direct measurement of blood pressure and heart rate. Administration of bicuculline into the nRt produced increases in spontaneous SWD and failed to alter blood pressure and heart rate. These data suggest that GABA(A) receptors located within the nRt are involved in the incidence of SWD, whereas they do not seem to be involved in cardiovascular regulation of rats with genetic absence epilepsy.