Background: There are significant variabilities in guideline-concordant documentation in asthma care. However, assessing clinician’s documentation is not feasible using only structured data but requires labor-intensive chart review of electronic health records (EHRs). A certain guideline element in asthma control factors, such as review inhaler techniques, requires context understanding to correctly capture from EHR free text.Methods: The study data consist of two sets: (1) manual chart reviewed data—1039 clinical notes of 300 patients with asthma diagnosis, and (2) weakly labeled data (distant supervision)—27,363 clinical notes from 800 patients with asthma diagnosis. A context-aware language model, Bidirectional Encoder Representations from Transformers (BERT) was developed to identify inhaler techniques in EHR free text. Both original BERT and clinical BioBERT (cBERT) were applied with a cost-sensitivity to deal with imbalanced data. The distant supervision using weak labels by rules was also incorporated to augment the training set and alleviate a costly manual labeling process in the development of a deep learning algorithm. A hybrid approach using post-hoc rules was also explored to fix BERT model errors. The performance of BERT with/without distant supervision, hybrid, and rule-based models were compared in precision, recall, F-score, and accuracy.Results: The BERT models on the original data performed similar to a rule-based model in F1-score (0.837, 0.845, and 0.838 for rules, BERT, and cBERT, respectively). The BERT models with distant supervision produced higher performance (0.853 and 0.880 for BERT and cBERT, respectively) than without distant supervision and a rule-based model. The hybrid models performed best in F1-score of 0.877 and 0.904 over the distant supervision on BERT and cBERT.Conclusions: The proposed BERT models with distant supervision demonstrated its capability to identify inhaler techniques in EHR free text, and outperformed both the rule-based model and BERT models trained on the original data. With a distant supervision approach, we may alleviate costly manual chart review to generate the large training data required in most deep learning-based models. A hybrid model was able to fix BERT model errors and further improve the performance.

Emerging literature suggests that delayed identification of childhood asthma results in an increased risk of long-term and various morbidities compared to those with timely diagnosis and intervention, and yet this risk is still overlooked. Even when children and adolescents have a history of recurrent asthma-like symptoms and risk factors embedded in their medical records, this information is sometimes overlooked by clinicians at the point of care. Given the rapid adoption of electronic health record (EHR) systems, early identification of childhood asthma can be achieved utilizing (1) asthma ascertainment criteria leveraging relevant clinical information embedded in EHR and (2) innovative informatics approaches such as natural language processing (NLP) algorithms for asthma ascertainment criteria to enable such a strategy. In this review, we discuss literature relevant to this topic and introduce recently published informatics algorithms (criteria-based NLP) as a potential solution to address the current challenge of early identification of childhood asthma.

Kwon JH, et al. Allergy Asthma Immunol Res. 2021 Sep;13(5):697-718. https://doi.org/10.4168/aair.2021.13.5.697

Background: Detection of the epidermal growth factor receptor (EGFR) T790M mutation using plasma samples has been considered simple and non-invasive, but the relatively high false negative results lead to additional tissue sampling in some patients. Until now, the characteristics of patients who prefer liquid biopsy have not yet been established. Methods: To evaluate the favorable conditions for the detection of T790M mutations using plasma samples, a multicenter retrospective study was performed between May 2018 and December 2021. Patients whose T790M mutation was detected in a plasma sample were classified as the plasma positive group. Study subjects with a T790M mutation not detected in a plasma sample but only in a tissue sample were grouped as the plasma false negative group. Results: Plasma positive and plasma false negative groups were found in 74 and 32 patients, respectively. As a result, 40% of patients with one or two metastatic organs at the time of re-biopsy had false negative plasma sample results, and 69% of patients with three or more metastatic organs at the time of re-biopsy had positive plasma results. In multivariate analysis, three or more metastatic organs at initial diagnosis were independently associated with the detection of a T790M mutation using plasma samples. Conclusion: Our results demonstrated that the detection rate of a T790M mutation using plasma samples was related to the tumor burden, particularly to the number of metastatic organs.

Despite the significant implications of doctors’ strikes for public health, little research has been done on the effects of doctors’ strike on patient mortality. In this study, we attempted to assess the effects on patient mortality of a strike that was carried out by doctors in South Korea in June 2000. The data for this study came from Statistic Korea (KOSTAT)’s ‘Causes of Death Statistics’ for the period 1997 to 2003. The data was analyzed with the four methods most commonly used in international studies on doctor strikes. The analysis shows that there is no significant difference between the disease-related death rate for June 2000 and that for the same month in other analyzed years. Similarly, there is no significant difference between the disease-related death rate for June 2000 and the rates for May and July, either in 2000 or in other analyzed years. However, the disease-related death rate during the strike in June 2000 is slightly lower than the rates for the sixday period immediately prior to and immediately following the strike. This suggests that, contrary to what many people believe, the disease-related death rate did not increase during the doctor’s strike in June 2000. This study is the first to provide statistical evidence concerning the effects of doctors’ strikes on hospital mortality rates in South Korea.

Rehabilitation during extracorporeal membrane oxygenation (ECMO) has become a promising intervention to mitigate the profound physical and functional decline that occurs with prolonged critical illness. With the wider adoption of ECMO, interest has grown in integrating early mobilization into routine care practices to preserve muscle mass, reduce intensive care unit-acquired weakness, and improve long-term patient outcomes. Emerging observational data indicate that structured rehabilitation protocols—including passive and active mobilization—are feasible and safe, including for individuals undergoing femoral cannulation. Nevertheless, multiple obstacles, including patient instability, technical constraints, staffing limitations, and gaps in clinical knowledge, impede broader implementation. Although the theoretical rationale and initial data are compelling, further robust randomized controlled trials are essential to establish the definitive efficacy, best-practice protocols, and cost-effectiveness of rehabilitation interventions in ECMO-supported patients.