Abstract Cetuximab is remarkable for the relatively high rate and severity of hypersensitivity reactions ( HR ) being reported in the literature. Screening for cetuximab‐specific IgE in serum via immunoassay has been found to be useful in preventing HR ; however, these tests are known to have a low positive predictive rate. In an attempt to remedy this, we evaluated the interaction between cetuximab and IgE on basophils for predicting severe cetuximab‐induced HR . Twelve head and neck cancer patients were enrolled in this single‐institution study: four with a history of cetuximab‐induced HR and eight with no such history. Cetuximab‐specific and galactose‐ α ‐1,3‐galactose ( α ‐gal) specific IgEs in serum were measured in vitro using an enzyme‐linked immunosorbent assay ( ELISA ). IgE‐cetuximab binding on basophils was also analyzed to evaluate the decrease in cetuximab molecules on basophils after dissociation of IgE from Fcε RI . The positive predictive value associated with the presence of cetuximab‐ or α ‐gal‐specific IgE in serum was found to be only 0.67, whereas the negative predictive value was 1.00. On the other hand, in all four patients who developed HR , the cetuximab molecules on basophils were decreased significantly due to the dissociation of IgE from basophils ( P < 0.05). However, this was not the case in patients who did not develop HR . In conclusion, our results strongly imply that the IgE‐cetuximab interaction on basophils may be key to developing improved methods for predicting severe cetuximab‐induced HR .
Introduction The predominance of English in scientific research has created hurdles for “non-native speakers” of English. Here we present a novel application of native language identification (NLI) for the assessment of medical-scientific writing. For this purpose, we created a novel classification system whereby scoring would be based solely on text features found to be distinctive among native English speakers (NS) within a given context. We dubbed this the “Genuine Index” (GI). Methodology This methodology was validated using a small set of journals in the field of pediatric oncology. Our dataset consisted of 5,907 abstracts, representing work from 77 countries. A support vector machine (SVM) was used to generate our model and for scoring. Results Accuracy, precision, and recall of the classification model were 93.3%, 93.7%, and 99.4%, respectively. Class specific F-scores were 96.5% for NS and 39.8% for our benchmark class, Japan. Overall kappa was calculated to be 37.2%. We found significant differences between countries with respect to the GI score. Significant correlation was found between GI scores and two validated objective measures of writing proficiency and readability. Two sets of key terms and phrases differentiating NS and non-native writing were identified. Conclusions Our GI model was able to detect, with a high degree of reliability, subtle differences between the terms and phrasing used by native and non-native speakers in peer reviewed journals, in the field of pediatric oncology. In addition, L1 language transfer was found to be very likely to survive revision, especially in non-Western countries such as Japan. These findings show that even when the language used is technically correct, there may still be some phrasing or usage that impact quality.
Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, SMILES, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, SMILES has several shortcomings -- most pertinently, most combinations of symbols lead to invalid results with no valid chemical interpretation. To overcome this issue, a new language for molecules was introduced in 2020 that guarantees 100\% robustness: SELFIES (SELF-referencIng Embedded Strings). SELFIES has since simplified and enabled numerous new applications in chemistry. In this manuscript, we look to the future and discuss molecular string representations, along with their respective opportunities and challenges. We propose 16 concrete Future Projects for robust molecular representations. These involve the extension toward new chemical domains, exciting questions at the interface of AI and robust languages and interpretability for both humans and machines. We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.
Abstract Annual emergence of West Nile virus depends on a complex transmission chain. Predictive efforts are consequently confounded by time-varying associations and scale-dependent effect variability. SHAP (SHaply Additive Explanation) is a novel AI-driven solution with potential to overcome this. SHAP takes a high-performance XGBoost model and deductively imputes the marginal contribution of each feature with respect to the log relative risk associated with the local XGBoost prediction (an additive model). The resulting effect matrix is dimensionally identical to the original data but IID and homogenized in terms of units, scale, and interpretation. Such “synthetic data” can therefore serve as surrogate to allow for high-power statistical analyses. Here, we applied SHAP to a database consisting of high-resolution data from various domains – climate, environment, economic, sociodemographic, vector and host distribution – to derive an effect matrix of WNV outbreak risk determinants in Europe. This effect data proved superior to the original, nominal data in predictive tasks and delivered qualitatively compelling, domain-specific risk mappings. Further applications are discussed and others are invited to experiment.
Although mature clinical decision support technology is readily available, the medical community continues to exhibit the most remarkable difference between the diligent, professional attitude towards care of patients and the puberal, oftentimes neglectful attitude towards the value of the data generated by this process (1). This professional dissonance has been attributed to many causes (2,3); however, most would agree that the impact, in terms of patient care (4) and development of improved diagnostic and treatment options (5,6), is far from benign (7). This editorial confronts the sobering reality that we are far from reaching any declaration of victory in this regard—serious efforts are required (8). Take a seat; we trust the questions raised might trigger some introspection!
A usual practice in observational studies is the comparison of baseline characteristics of participants between study groups. The overall population can be grouped by clinical outcome or exposure status. A combined table reporting baseline characteristics is usually displayed, for the overall population and then separately for each group. The last column usually gives the P value for the comparison between study groups. In the conventional research model, the variables for which data are collected are limited in number. It is thus feasible to calculate descriptive data one by one and to manually create the table. The availability of EHR and big data mining techniques makes it possible to explore a far larger number of variables. However, manual tabulation of big data is particularly error prone; it is exceedingly time-consuming to create and revise such tables manually. In this paper, we introduce an R package called CBCgrps, which is designed to automate and streamline the generation of such tables when working with big data. The package contains two functions, twogrps() and multigrps(), which are used for comparisons between two and multiple groups, respectively.
Recent studies have shown that International medical graduates (IMG) comprise a substantial and increasingly larger share of the medical workforce, internationally. IMGs wishing to work in English-speaking countries face many challenges. And overcoming such challenges plays an important role in ensuring a more comfortable transition and improved outcomes for patients. This study addresses one such area of concern: the efficient acquisition of advanced language competence for use in the medical workplace. This research also addresses the needs of medical students and practitioners in other countries, where English is not the primary language. Medical terminology and phrasing is based on a tradition spanning more than 2500 years—a tradition that cuts across typical linguistic and cultural boundaries. Indeed, as is commonly understood, the language required by doctors and other medical professionals varies substantially from the norm. In the present study, this dynamic is exploited to identify and characterize the language and patterns of usage specific to medical English, as it is used in practice and reporting. Overall, constructions comprised of preposition-dependent nouns, verbs and adjectives were found to be most prevalent (38%), followed by prepositional phrases (33%). The former includes constructions such as “present with”, “present to”, and “present in”; while constructions such as “of … patient”, “in … group”, and “with … disease” comprise the latter. Preposition-independent noun and verb-based constructions were far less prevalent overall (18% and 5%, respectively). Up to now, medical language reference and learning material has focused on relatively uncommon, but essential, Greek and Latin terminology. This research challenges this convention, by demonstrating that medical language fluency would be acquired more efficiently by focusing on prepositional phrases or preposition-dependent verbs, nouns, and adjectives in context. This work should be of high interest to anyone interested in improved communication competence within the English-speaking medical workplace and beyond. What is already known on this subject : * International medical graduates make up a substantial portion of the medical workforce * Imperfect medical English creates challenges for international medical graduates * Subideal language impacts credibility and has been associated with increased risk to patients What this paper adds : * Preposition-dependent terms, following Germanic usage patterns, dominate medical English * Complex terms derived from Greek and Latin are far less prevalent than assumed * Medical English learning expected to be expedited by focus on preposition-dependent terms
Patients cannot always share all necessary relevant information with doctors during medical consultations. Regardless, in order to ensure the best quality consultation and care, it is imperative that a doctor clearly understands each patient's agenda. The purpose of this study was to analyze the process of developing a shared-agenda during family physician consultations in Japan.We interviewed 15 first time patients visiting the outpatient clinic of the Department of Family Medicine in the hospital chosen for the investigation, and the 8 family physicians who examined them. In total we observed 16 consultations. We analyzed both patients' and doctors' narratives using a modified grounded theory approach.For patients, we found four main factors that influenced the process of making a shared-agenda: past medical experiences, undisclosed but relevant information, relationship with the family physician, and the patient's own explanatory model. In addition, we found five factors that influenced the shared agenda making process for family physicians: understanding the patient's explanatory model, constructing the patient-doctor relationship, physical examination centered around the patient's explanatory model, discussion-styled explanation, and self-reflection on action.The findings suggest that patient satisfaction would be increased if family physicians are proactive in considering these factors with respect to both the patient's agenda, and their own.
To evaluate the effectiveness of a vein visualization display system using near-infrared light ("Vein Display") for the safe and proper selection of venipuncture sites for indwelling needle placement in the forearm.Ten second year nursing students were recruited to apply an indwelling needle line with and without Vein Display. Another ten participants were recruited from various faculty to serve as patients. The quality of the venipuncture procedure at various selected sites was evaluated according to a scale developed by the authors. Time, scores and patterns of puncture-site selection were compared with respect to three different methods: [1] attempt 1 (tourniquet only), [2] attempt 2 (Vein Display only) and [3] attempt 3 (both). To validate the effectiveness of Vein Display, 52 trials were conducted in total.We found that venipuncture site selection time was significantly improved with the Vein Display, particularly in the case of difficult to administer venipuncture sites. Overall, we found no significant difference with respect to venipuncture quality, as determined by our scale.These results suggest that equipment such as the Vein Display can contribute immensely to the improvement of practical skills, such as venipuncture, especially in the context of elderly patients.
Abstract West Nile virus disease is a growing issue with devastating outbreaks and linkage to climate. It’s a complex disease with many factors contributing to emergence and spread. High-performance machine learning models, such as XGBoost, hold potential for development of predictive models which performs well with complex diseases like West Nile virus disease. Such models furthermore allow for expanded ability to discover biological, ecological, social and clinical associations as well as interaction effects. In 1951, a deductive method based on cooperative game theory was introduced: Shapley values. The Shapley method has since been shown to be the only way to derive “true” effect estimations from complex systems. Up till recently, however, wide-scale application has been computationally prohibitive. Herein, we present a novel implementation of the Shapley method applied to machine learning to derive high-quality effect estimations. We set out to apply this method to study the drivers of and predict West Nile virus in Europe. Model validity was furthermore tested using observed information in the time periods following the prospective prediction window. We furthermore benchmarked results of XGBoost models against equivalently specified logistic regression models. High predictive performance was consistently observed. All models were statistically equivalent in terms of AUC performance (96.3% average). The top features across models were found to be vapor pressure, the autoregressive past year’s feature, maximum temperature, wind speed, and local GNP. Moreover, when aggregated across quarters, we found that the effect of these features are broadly consistent across model configurations. We furthermore confirmed that for an equivalent level of model sophistication, XGBoost and logistic regressions performed similarly, with an advantage to XGBoost as model complexity increased. Our findings highlight the importance of ecological factors, such as climate, in determining outbreak risk of West Nile virus in Europe. We conclude by demonstrating the feasibility of same-year prospective early warning models that combine same-year observed climate with autoregressive geospatial covariates and long-term bioclimatic features. Scenario-based forecasts could likely be developed using similar methods, to provide for long-term intervention and resource planning, therefore increasing public health preparedness and resilience. Highlights For geospatial analysis, XGBoost’s high-powered predictions are not always empirically sound SHAP, an AI-driven enhancement to XGBoost, resolves this issue by: 1) deriving empirically-valid models for each individual case-region, and 2) setting classification thresholds accordingly SHAP therefore allows for predictive consistency across models and improved generalizeability Aggregate effect estimations produced by SHAP are consistent across model configurations AI-driven methods improve model validity with respect to predicted range and determinants
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)