Background: Thunderclap headache (TCH) is a sudden headache (SH) with accepted criteria of severe intensity and onset to peak within one minute. It is a well-known presentation for subarachnoid hemorrhage (SAH) but most patients with TCH or SH run a benign course without identifiable causes. Reversible cerebral vasoconstriction syndrome (RCVS), a recently recognized syndrome characterized by recurrent TCH attacks, has been proposed to account for most of these patients.Methods: We recruited consecutive patients presenting with SH at our headache clinic. Computed tomography and/or magnetic resonance imaging with angiography were performed to exclude structural causes and to identify vasoconstriction. Catheter angiography and lumbar puncture were performed with patients consent. Reversibility of vasoconstriction was confirmed by follow-up study.Results: From July 2010 to June 2013, 31 patients with SH were recruited. Twenty-four (72.7%) of these SH patients exhibited headache fulfilling the TCH criteria. The diagnosis of RCVS was confirmed in 14 (45.2%) of patients with SH and 11 (45.8%) of patients with TCH. Other diagnoses were as follows: primary headaches (SH: 41.9%, TCH: 45.8%) and other secondary causes (SH: 12.9%, TCH: 8.3%). Compared with non-RCVS patients, patients with RCVS were older (50.8 ± 9.3 years vs. 40.8 ± 10.0 years,P = 0.006) and less likely to experience short headache duration of < 1 hour (23.1% vs. 78.6%,P = 0.007). Patients with RCVS were more likely to cite bathing (42.9% vs. 0%,P = 0.004) and less likely to cite exertion (0% vs. 29.4%,P = 0.048) as headache triggers.Conclusions: Reversible cerebral vasoconstriction syndrome is a common cause of SH and TCH. Considering the potential mortality and morbidity of RCVS, systemic examination of cerebral vessels should be performed in these patients.

Background: The performance of chest radiography-based age and sex prediction has not been well validated. We used a deep learning model to predict the age and sex of healthy adults based on chest radiographs (CXRs). Methods: In this retrospective study, 66,643 CXRs of 47,060 healthy adults were used for model training and testing. In total, 47,060 individuals (mean age ± standard deviation, 38.7 ± 11.9 years; 22,144 males) were included. By using chronological ages as references, mean absolute error (MAE), root mean square error (RMSE), and Pearson’s correlation coefficient were used to assess the model performance. Summarized class activation maps were used to highlight the activated anatomical regions. The area under the curve (AUC) was used to examine the validity for sex prediction. Results: When model predictions were compared with the chronological ages, the MAE was 2.1 years, RMSE was 2.8 years, and Pearson’s correlation coefficient was 0.97 (p < 0.001). Cervical, thoracic spines, first ribs, aortic arch, heart, rib cage, and soft tissue of thorax and flank seemed to be the most crucial activated regions in the age prediction model. The sex prediction model demonstrated an AUC of >0.99. Conclusion: Deep learning can accurately estimate age and sex based on CXRs.

Delays or misdiagnoses in detecting pneumoperitoneum can significantly increase mortality and morbidity. We developed and validated a deep learning model designed to identify pneumoperitoneum in computed tomography images. The model is trained on abdominal scans from Far Eastern Memorial Hospital (January 2012–December 2021) and evaluated using a simulated test set (14,039 scans) and a prospective test set (6351 scans) collected from the same center between December 2022 and May 2023. External validation included 480 scans from Cedars-Sinai Medical Center. Overall, the model achieves a sensitivity of 0.81–0.83 and a specificity of 0.97–0.99 across retrospective, prospective, and external validation; sensitivity improves to 0.92–0.98 when cases with a small amount of free air (total volume <10 ml) are excluded. These findings suggest that the model can deliver accurate and consistent predictions for pneumoperitoneum in computed tomography scans with segmented masks, potentially accelerating diagnostic and treatment workflows in emergency care.

This study aims to evaluate an AI model designed to automatically classify skull fractures and visualize segmentation on emergent CT scans. The model’s goal is to boost diagnostic accuracy, alleviate radiologists’ workload, and hasten diagnosis, thereby enhancing patient outcomes. Unique to this research, both pediatric and post-operative patients were not excluded, and diagnostic durations were analyzed. Our testing dataset for the observer studies involved 671 patients, with a mean age of 58.88 years and fairly balanced gender representation. Model 1 of our AI algorithm, trained with 1499 fracture-positive cases, showed a sensitivity of 0.94 and specificity of 0.87, with a DICE score of 0.65. Implementing post-processing rules (specifically Rule B) improved the model’s performance, resulting in a sensitivity of 0.94, specificity of 0.99, and a DICE score of 0.63. AI-assisted diagnosis resulted in significantly enhanced performance for all participants, with sensitivity almost doubling for junior radiology residents and other specialists. Additionally, diagnostic durations were significantly reduced (p < 0.01) with AI assistance across all participant categories. Our skull fracture detection model, employing a segmentation approach, demonstrated high performance, enhancing diagnostic accuracy and efficiency for radiologists and clinical physicians. This underlines the potential of AI integration in medical imaging analysis to improve patient care.

Patients with schizophrenia have a high mortality risk, and the role of antipsychotic medications remains inconclusive. In an aging society, older patients with schizophrenia warrant increased attention. This study investigated the association of antipsychotic medication dosages with mortality in patients with schizophrenia by using data from Taiwan’s National Health Insurance Research Database from 2010 to 2014. This study included 102,964 patients with schizophrenia and a subgroup of 6433 older patients in addition to an age- and sex-matched control group. The findings revealed that among patients with schizophrenia, the no antipsychotic exposure group had the highest mortality risk (3.61- and 3.37-fold higher risk for overall and cardiovascular mortality, respectively) in the age- and sex-adjusted model, followed by the high, low, and moderate exposure groups. A similar pattern was observed in the older patients with schizophrenia. High exposure to antipsychotics was associated with the highest risks of overall and cardiovascular mortality (3.01- and 2.95-fold higher risk, respectively). In conclusion, the use of antipsychotics can be beneficial for patients with schizophrenia with recommended exposure levels being low to moderate. In older patients, high antipsychotic exposure was associated with the highest mortality risk, indicating that clinicians should be cautious when administering antipsychotic medications to such patients.

Patients with schizophrenia had higher mortality risks and the role of antipsychotic medications remained inconclusive. In an aging society, elderly schizophrenia patients warrant increased attention. In this study, we aimed to explore medication dosage associations with mortality in schizophrenia patients, using Taiwan's national healthcare database from 2010 to 2014, with 102,964 patients with schizophrenia, and a subgroup of 6,433 elderly patients, compared to an age- and gender-matched control group. The findings revealed that schizophrenia patients with no antipsychotic exposure had the highest mortality risk as compared to the control sample—with a 3.61 and 3.37-fold risk for overall and cardiovascular mortality respectively in age and gender-adjusted model, followed by high, low, and moderate exposure groups. A similar pattern was observed in elderly schizophrenia patients but high exposure to antipsychotics was associated with the highest risk in both overall and cardiovascular mortality in elderly patients, with a 3.01, and 2.95-fold risk), respectively. In conclusion, the use of antipsychotics is beneficial to patients with schizophrenia, with recommended exposure levels being low to moderate. In elderly patients, high antipsychotic exposure was associated with the highest mortality risk. We should pay more attention to antipsychotic dosage in elderly schizophrenia patients.