BACKGROUND: The ability to predict rheumatoid arthritis (RA) flares between clinic visits based on real-time, longitudinal patient-generated data could potentially allow for timely interventions to avoid disease worsening.
OBJECTIVE: This exploratory study aims to investigate the feasibility of using machine learning methods to classify self-reported RA flares based on a small data set of daily symptom data collected on a smartphone app.
METHODS: Daily symptoms and weekly flares reported on the Remote Monitoring of Rheumatoid Arthritis (REMORA) smartphone app from 20 patients with RA over 3 months were used. Predictors were several summary features of the daily symptom scores (eg, pain and fatigue) collected in the week leading up to the flare question. We fitted 3 binary classifiers: logistic regression with and without elastic net regularization, a random forest, and naive Bayes. Performance was evaluated according to the area under the curve (AUC) of the receiver operating characteristic curve. For the best-performing model, we considered sensitivity and specificity for different thresholds in order to illustrate different ways in which the predictive model could behave in a clinical setting.
RESULTS: The data comprised an average of 60.6 daily reports and 10.5 weekly reports per participant. Participants reported a median of 2 (IQR 0.75-4.25) flares each over a median follow-up time of 81 (IQR 79-82) days. AUCs were broadly similar between models, but logistic regression with elastic net regularization had the highest AUC of 0.82. At a cutoff requiring specificity to be 0.80, the corresponding sensitivity to detect flares was 0.60 for this model. The positive predictive value (PPV) in this population was 53%, and the negative predictive value (NPV) was 85%. Given the prevalence of flares, the best PPV achieved meant only around 2 of every 3 positive predictions were correct (PPV 0.65). By prioritizing a higher NPV, the model correctly predicted over 9 in every 10 non-flare weeks, but the accuracy of predicted flares fell to only 1 in 2 being correct (NPV and PPV of 0.92 and 0.51, respectively).
CONCLUSIONS: Predicting self-reported flares based on daily symptom scorings in the preceding week using machine learning methods was feasible. The observed predictive accuracy might improve as we obtain more data, and these exploratory results need to be validated in an external cohort. In the future, analysis of frequently collected patient-generated data may allow us to predict flares before they unfold, opening opportunities for just-in-time adaptative interventions. Depending on the nature and implication of an intervention, different cutoff values for an intervention decision need to be considered, as well as the level of predictive certainty required.

Throughout the COVID-19 pandemic, many hospitals conducted routine testing of hospitalized patients for SARS-CoV-2 infection upon admission. Some of these patients are admitted for reasons unrelated to COVID-19 and incidentally test positive for the virus. Because COVID-19-related hospitalizations have become a critical public health indicator, it is important to identify patients who are hospitalized because of COVID-19 as opposed to those who are admitted for other indications.
We compared the performance of different computable phenotype definitions for COVID-19 hospitalizations that use different types of data from electronic health records (EHRs), including structured EHR data elements, clinical notes, or a combination of both data types.
We conducted a retrospective data analysis, using clinician chart review-based validation at a large academic medical center. We reviewed and analyzed the charts of 586 hospitalized individuals who tested positive for SARS-CoV-2 in January 2022. We used LASSO (least absolute shrinkage and selection operator) regression and random forests to fit classification algorithms that incorporated structured EHR data elements, clinical notes, or a combination of structured data and clinical notes. We used natural language processing to incorporate data from clinical notes. The performance of each model was evaluated based on the area under the receiver operator characteristic curve (AUROC) and an associated decision rule based on sensitivity and positive predictive value. We also identified top words and clinical indicators of COVID-19-specific hospitalization and assessed the impact of different phenotyping strategies on estimated hospital outcome metrics.
Based on a chart review, 38.2% (224/586) of patients were determined to have been hospitalized for reasons other than COVID-19, despite having tested positive for SARS-CoV-2. A computable phenotype that used clinical notes had significantly better discrimination than one that used structured EHR data elements (AUROC: 0.894 vs 0.841; P<.001) and performed similarly to a model that combined clinical notes with structured data elements (AUROC: 0.894 vs 0.893; P=.91). Assessments of hospital outcome metrics significantly differed based on whether the population included all hospitalized patients who tested positive for SARS-CoV-2 or those who were determined to have been hospitalized due to COVID-19.
These findings highlight the importance of cause-specific phenotyping for COVID-19 hospitalizations. More generally, this work demonstrates the utility of natural language processing approaches for deriving information related to patient hospitalizations in cases where there may be multiple conditions that could serve as the primary indication for hospitalization.

Even though various types of suicidality are observed in clinical practice, suicidality is still considered a uniform concept. To distinguish different types of suicidality and consequently improve detection and management of suicidality, we developed a clinical differentiation model for suicidality. We believe that the model allows for a more targeted assessment of suicidal conditions and improves the use of evidence-based treatment strategies. The differentiation model is based on the experience with suicidality that we have encountered in clinical practice. This model distinguishes 4 subtypes of entrapment leading to suicidality. The earliest description of this model and a proposal for usability research has been previously presented in a book chapter.
In this study, we present the most recent version of the 4-type differentiation model of suicidality and a protocol for a study into the usability of the proposed model.
The 4-type differentiation model of suicidality distinguishes the following subtypes: (1) perceptual disintegration, (2) primary depressive cognition, (3) psychosocial turmoil, and (4) inadequate coping or communication. We plan to test the usability of the 4 subtypes in a pilot study of 25 cases, and subsequently, we will include 75 cases in a follow-up study. We looked at the case notes of 100 anonymized patients with suicidality who presented to mental health care emergency service in The Hague International Center. The summary and conclusions of the letters sent to the patients\' general practitioners after suicide risk assessment will be independently rated by 3 psychiatrists and 3 nurse-scientists for absolute and dimensional scores. The Suicidality Differentiation version 2 (SUICIDI-II) instrument, developed for this study, is used for rating all the cases. Intraclass correlation coefficients for absolute and dimensional scores will be calculated to examine type agreement between raters to examine the usability of the model and the feasibility of the SUICIDI-II instrument.
We consider the model tentatively valid if the intraclass correlation coefficients are ≥0.70. Subsequently, if the model turns out to be valid, we plan to rate 75 other cases in a follow-up study, according to a similar or adjusted procedure. Study results are expected to be published by the end of 2023.
The theoretical roots of the differentiation model stem from classic and contemporary theoretical models of suicidality and from our clinical practice experiences with suicidal behaviors. We believe that this model can be used to adjust the diagnosis, management, treatment, and research of suicidality, in addition to distinguishing different dynamics between practitioners and patients with suicidality and their families.
DERR1-10.2196/45438.

There are variable presentations of complications of rhinosinusitis, which may be subtle especially due to use of antibiotics. Thus the classical picture as described by Chandler is rarely seen and threshold for diagnosing and treating a complication should be low. To identify possible risk factors for development of complications in acute bacterial rhinosinusitis (ABRS) and suggest a new method of reporting/classifying the complications. We conducted a retrospective study and observed the clinical presentation and risk factors of 9 patients who presented with complications of ABRS in our OPD during a period of 6 years, and then tried to formulate a reporting method based on the risk factors. We identified certain risk factors which include age, gender, sinus involved, extension beyond sinus, history of trauma, anatomical variations, and duration of symptoms. There are possible risk factors for development of complications. These factors can be studied in further details to ascertain their causal relationship in causing these complications. We also suggest a new method of reporting the complications. Such a reporting system would help in accurately identifying the exact severity of the disease, prognosticating the disease and guide treatment.

BACKGROUND: A convolutional neural network (CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition.
OBJECTIVE: To automatically identify the invasion depth and origin of esophageal lesions based on a CNN.
METHODS: A total of 1670 white-light images were used to train and validate the CNN system. The method proposed in this paper included the following two parts: (1) Location module, an object detection network, locating the classified main image feature regions of the image for subsequent classification tasks; and (2) Classification module, a traditional classification CNN, classifying the images cut out by the object detection network.
RESULTS: The CNN system proposed in this study achieved an overall accuracy of 82.49%, sensitivity of 80.23%, and specificity of 90.56%. In this study, after follow-up pathology, 726 patients were compared for endoscopic pathology. The misdiagnosis rate of endoscopic diagnosis in the lesion invasion range was approximately 9.5%; 41 patients showed no lesion invasion to the muscularis propria, but 36 of them pathologically showed invasion to the superficial muscularis propria. The patients with invasion of the tunica adventitia were all treated by surgery with an accuracy rate of 100%. For the examination of submucosal lesions, the accuracy of endoscopic ultrasonography (EUS) was approximately 99.3%. Results of this study showed that EUS had a high accuracy rate for the origin of submucosal lesions, whereas the misdiagnosis rate was slightly high in the evaluation of the invasion scope of lesions. Misdiagnosis could be due to different operating and diagnostic levels of endoscopists, unclear ultrasound probes, and unclear lesions.
CONCLUSIONS: This study is the first to recognize esophageal EUS images through deep learning, which can automatically identify the invasion depth and lesion origin of submucosal tumors and classify such tumors, thereby achieving good accuracy. In future studies, this method can provide guidance and help to clinical endoscopists.

BACKGROUND: The emergency department (ED) triage system to classify and prioritize patients from high risk to less urgent continues to be a challenge.
OBJECTIVE: This study, comprising 80,433 patients, aims to develop a machine learning algorithm prediction model of critical care outcomes for adult patients using information collected during ED triage and compare the performance with that of the baseline model using the Korean Triage and Acuity Scale (KTAS).
METHODS: To predict the need for critical care, we used 13 predictors from triage information: age, gender, mode of ED arrival, the time interval between onset and ED arrival, reason of ED visit, chief complaints, systolic blood pressure, diastolic blood pressure, pulse rate, respiratory rate, body temperature, oxygen saturation, and level of consciousness. The baseline model with KTAS was developed using logistic regression, and the machine learning model with 13 variables was generated using extreme gradient boosting (XGB) and deep neural network (DNN) algorithms. The discrimination was measured by the area under the receiver operating characteristic (AUROC) curve. The ability of calibration with Hosmer-Lemeshow test and reclassification with net reclassification index were evaluated. The calibration plot and partial dependence plot were used in the analysis.
RESULTS: The AUROC of the model with the full set of variables (0.833-0.861) was better than that of the baseline model (0.796). The XGB model of AUROC 0.861 (95% CI 0.848-0.874) showed a higher discriminative performance than the DNN model of 0.833 (95% CI 0.819-0.848). The XGB and DNN models proved better reclassification than the baseline model with a positive net reclassification index. The XGB models were well-calibrated (Hosmer-Lemeshow test; P>.05); however, the DNN showed poor calibration power (Hosmer-Lemeshow test; P<.001). We further interpreted the nonlinear association between variables and critical care prediction.
CONCLUSIONS: Our study demonstrated that the performance of the XGB model using initial information at ED triage for predicting patients in need of critical care outperformed the conventional model with KTAS.

Autonomous sensory meridian response (ASMR) describes an atypical multisensory experience of calming, tingling sensations that originate in the crown of the head in response to a specific subset of audio-visual triggers. There is currently no tool that can accurately classify both ASMR-Responders and non-responders, while simultaneously identifying False-Positive cases that are similar sensory-emotional experiences. This study sought to fill this gap by developing a new online psychometric tool - the ASMR-Experiences Questionnaire (AEQ). Participants watched a series of short ASMR videos and answered sensory-affective questions immediately afterwards. Using a k-means clustering approach, we identified five data-driven groupings, based on tingle- and affect-related scores. ASMR-Responders differentiate based on ASMR propensity and intensity (ASMR-Strong; ASMR-Weak); non-responders differentiate based on response valence (Control+; Control-; False-Positive). Recommendations for how the AEQ and the respective output groups can be best utilized to enhance ASMR research are discussed.

Saponins constitute an important class of secondary metabolites of the plant kingdom. Here, we present a mass spectrometry-based database for rapid and easy identification of saponins henceforth referred to as saponin mass spectrometry database (SMSD). With a total of 4196 saponins, 214 of which were obtained from commercial sources. Through liquid chromatography-tandem high-resolution/mass spectrometry (HR/MS) analysis under negative ion mode, the fragmentation behavior for all parent fragment ions almost conformed to successive losses of sugar moieties, α-dissociation and McLafferty rearrangement of aglycones in high-energy collision induced dissociation. The saccharide moieties produced sugar fragment ions from m/z (monosaccharide) to m/z (polysaccharides). The parent and sugar fragment ions of other saponins were predicted using the above mentioned fragmentation pattern. The SMSD is freely accessible at http://47.92.73.208:8082/ or http://cpu-smsd.com (preferrably using google). It provides three search modes (\"CLASSIFY\", \"SEARCH\" and \"METABOLITE\"). Under the \"CLASSIFY\" function, saponins are classified with high predictive accuracies from all metabolites by establishment of logistic regression model through their mass data from HR/MS input as a csv file, where the first column is ID and the second column is mass. For the \"SEARCH\" function, saponins are searched against parent ions with certain mass tolerance in \"MS Ion Search\". Then, daughter ions with certain mass tolerance are input into \"MS/MS Ion Search\". The optimal candidates were screened out according to the match count and match rate values in comparison with fragment data in database. Additionally, another logistic regression model completely differentiated between parent and sugar fragment ions. This function designed in front web is conducive to search and recheck. With the \"METABOLITE\" function, saponins are searched using their common names, where both full and partial name searches are supported. With these modes, saponins of diverse chemical composition can be explored, grouped and identified with a high degree of predictive accuracy. This specialized database would aid in the identification of saponins in complex matrices particular in the study of traditional Chinese medicines or plant metabolomics.

OBJECTIVE: To identify and explore the various classification systems that have been proposed for anterior urethral stricture disease (AUSD) and to identify the advantages and disadvantages of each.
METHODS: A comprehensive systematic review was conducted in MEDLINE, EMBASE, SCOPUS and COCHRANE databases with a search strategy created appropriately. Titles and abstracts of search results were screened by two authors and selected for full-text review. Studies exploring urethral stricture classification, clinical scoring or staging systems used in men over the age of 18 with benign anterior urethral stricture disease were included.
RESULTS: The search identified 3113 articles, of which 10 were selected for inclusion after scrutiny. Four classification systems were identified. These include ULTRA score, urethral stricture score, cystoscopy-based staging system and Gombe Urethrographic score. These were based on various modalities, including cystoscopy, retrograde urethrogram (RUG) and sonourethrogram (SUG). From the scoring systems identified, the urethral stricture scoring system has multiple external validation studies and is predictive of operative complexity, operative time, recurrence and postoperative complications.
CONCLUSIONS: Several classification systems have been proposed for AUSD. Each has its advantages and disadvantages. The urethral stricture score has been externally validated and shown to been predictive of surgical outcomes and recurrence. There are no scores that incorporate patient-related outcome measures (PROMs). Many classification systems have yet to provide sufficient external validation. Further external validation studies are needed before the general adoption of a particular system.

ATP-binding cassette (ABC) proteins play important roles in a wide variety of species. These proteins are involved in absorbing nutrients, exporting toxic substances, and regulating potassium channels, and they contribute to drug resistance in cancer cells. Therefore, the identification of ABC transporters is an urgent task. The present study used 188D as the feature extraction method, which is based on sequence information and physicochemical properties. We also visualized the feature extracted by t-Distributed Stochastic Neighbor Embedding (t-SNE). The sample based on the features extracted by 188D may be separated. Further, random forest (RF) is an efficient classifier to identify proteins. Under the 10-fold cross-validation of the model proposed here for a training set, the average accuracy rate of 10 training sets was 89.54%. We obtained values of 0.87 for specificity, 0.92 for sensitivity, and 0.79 for MCC. In the testing set, the accuracy achieved was 89%. These results suggest that the model combining 188D with RF is an optimal tool to identify ABC transporters.