Can Computers Outperform Humans in Detecting User Zone-Outs? Implications for Intelligent Interfaces

The ability to identify whether a user is “zoning out” (mind wandering) from video has many HCI (e.g., distance learning, high-stakes vigilance tasks). However, it remains unknown how well humans can perform this task, how they compare to automatic computerized approaches, and how a fusion of the two might improve accuracy. We analyzed videos of users’ faces and upper bodies recorded 10s prior to self-reported mind wandering (i.e., ground truth) while they engaged in a computerized reading task. We found that a state-of-the-art machine learning model had comparable accuracy to aggregated judgments of nine untrained human observers (area under receiver operating characteristic curve [AUC] = .598 versus .589). A fusion of the two (AUC = .644) outperformed each, presumably because each focused on complementary cues. Furthermore, adding more humans beyond 3–4 observers yielded diminishing returns. We discuss implications of human–computer fusion as a means to improve accuracy in complex tasks.

Blood-Based Biomarker Panel for Personalized Lung Cancer Risk Assessment

PURPOSE To investigate whether a panel of circulating protein biomarkers would improve risk assessment for lung cancer screening in combination with a risk model on the basis of participant characteristics. METHODS A blinded validation study was performed using prostate lung colorectal ovarian (PLCO) Cancer Screening Trial data and biospecimens to evaluate the performance of a four-marker protein panel (4MP) consisting of the precursor form of surfactant protein B, cancer antigen 125, carcinoembryonic antigen, and cytokeratin-19 fragment in combination with a lung cancer risk prediction model (PLCOm2012) compared with current US Preventive Services Task Force (USPSTF) screening criteria. The 4MP was assayed in 1,299 sera collected preceding lung cancer diagnosis and 8,709 noncase sera. RESULTS The 4MP alone yielded an area under the receiver operating characteristic curve of 0.79 (95% CI, 0.77 to 0.82) for case sera collected within 1-year preceding diagnosis and 0.74 (95% CI, 0.72 to 0.76) among the entire specimen set. The combined 4MP + PLCOm2012 model yielded an area under the receiver operating characteristic curve of 0.85 (95% CI, 0.82 to 0.88) for case sera collected within 1 year preceding diagnosis. The benefit of the 4MP in the combined model resulted from improvement in sensitivity at high specificity. Compared with the USPSTF2021 criteria, the combined 4MP + PLCOm2012 model exhibited statistically significant improvements in sensitivity and specificity. Among PLCO participants with ≥ 10 smoking pack-years, the 4MP + PLCOm2012 model would have identified for annual screening 9.2% more lung cancer cases and would have reduced referral by 13.7% among noncases compared with USPSTF2021 criteria. CONCLUSION A blood-based biomarker panel in combination with PLCOm2012 significantly improves lung cancer risk assessment for lung cancer screening.

Prediction of extubation failure in the paediatric cardiac ICU using machine learning and high-frequency physiologic data

Background: Cardiac intensivists frequently assess patient readiness to wean off mechanical ventilation with an extubation readiness trial despite it being no more effective than clinician judgement alone. We evaluated the utility of high-frequency physiologic data and machine learning for improving the prediction of extubation failure in children with cardiovascular disease. Methods: This was a retrospective analysis of clinical registry data and streamed physiologic extubation readiness trial data from one paediatric cardiac ICU (12/2016-3/2018). We analysed patients’ final extubation readiness trial. Machine learning methods (classification and regression tree, Boosting, Random Forest) were performed using clinical/demographic data, physiologic data, and both datasets. Extubation failure was defined as reintubation within 48 hrs. Classifier performance was assessed on prediction accuracy and area under the receiver operating characteristic curve. Results: Of 178 episodes, 11.2% (N = 20) failed extubation. Using clinical/demographic data, our machine learning methods identified variables such as age, weight, height, and ventilation duration as being important in predicting extubation failure. Best classifier performance with this data was Boosting (prediction accuracy: 0.88; area under the receiver operating characteristic curve: 0.74). Using physiologic data, our machine learning methods found oxygen saturation extremes and descriptors of dynamic compliance, central venous pressure, and heart/respiratory rate to be of importance. The best classifier in this setting was Random Forest (prediction accuracy: 0.89; area under the receiver operating characteristic curve: 0.75). Combining both datasets produced classifiers highlighting the importance of physiologic variables in determining extubation failure, though predictive performance was not improved. Conclusion: Physiologic variables not routinely scrutinised during extubation readiness trials were identified as potential extubation failure predictors. Larger analyses are necessary to investigate whether these markers can improve clinical decision-making.

Significant Physical and Exercise-Related Variables for Exercise-Centred Lifestyle: Big Data Analysis for Gynaecological Cancer Patients

This study investigated the characteristics of gynaecological cancers and is aimed at identifying significant risk variables using the National Health Insurance Sharing Service database to develop practical interventions for affected patients. Data regarding patients with uterine and ovarian cancer from the National Health Insurance Sharing Service database were collected and analysed using Student’s t -test, logistic regression, and receiver operating characteristic curve analyses. Student’s t -test analyses revealed that age, body mass index, blood pressure, and waist variables differed significantly among patients with uterine cancer. Gamma-glutamyl transpeptidase levels were higher in patients with ovarian cancer than in patients with uterine cancer. Physical fitness function tests reflected the status of patients with cancer. Moreover, physical disability was associated with an increased incidence of ovarian cancer. Intensive exercise for 20 min more than 1 time per week must be avoided to prevent uterine cancer. Receiver operating characteristic curve analyses showed that the optimal cutoff value for one-leg standing time, a prognostic and preventive factor in ovarian cancer, was 9.50 s (sensitivity, 94.9%; specificity, 96.9%). Controlling significant variables for each gynaecological cancer type in an individualised and optimised manner is recommended, including by maintenance of an adjusted exercise-centred lifestyle.

Posterior National Institutes of Health Stroke Scale Improves Prognostic Accuracy in Posterior Circulation Stroke

Background and Purpose: The National Institutes of Health Stroke Scale (NIHSS) underestimates clinical severity in posterior circulation stroke and patients presenting with low NIHSS may be considered ineligible for reperfusion therapies. This study aimed to develop a modified version of the NIHSS, the Posterior NIHSS (POST-NIHSS), to improve NIHSS prognostic accuracy for posterior circulation stroke patients with mild-moderate symptoms. Methods: Clinical data of consecutive posterior circulation stroke patients with mild-moderate symptoms (NIHSS <10), who were conservatively managed, were retrospectively analyzed from the Basilar Artery Treatment and Management registry. Clinical features were assessed within 24 hours of symptom onset; dysphagia was assessed by a speech therapist within 48 hours of symptom onset. Random forest classification algorithm and constrained optimization were used to develop the POST-NIHSS in the derivation cohort. The POST-NIHSS was then validated in a prospective cohort. Poor outcome was defined as modified Rankin Scale score ≥3 at 3 months. Results: We included 202 patients (mean [SD] age 63 [14] years, median NIHSS 3 [interquartile range, 1–5]) in the derivation cohort and 65 patients (mean [SD] age 63 [16] years, median NIHSS 2 [interquartile range, 1–4]) in the validation cohort. In the derivation cohort, age, NIHSS, abnormal cough, dysphagia and gait/truncal ataxia were ranked as the most important predictors of functional outcome. POST-NIHSS was calculated by adding 5 points for abnormal cough, 4 points for dysphagia, and 3 points for gait/truncal ataxia to the baseline NIHSS. In receiver operating characteristic analysis adjusted for age, POST-NIHSS area under receiver operating characteristic curve was 0.80 (95% CI, 0.73–0.87) versus NIHSS area under receiver operating characteristic curve, 0.73 (95% CI, 0.64–0.83), P =0.03. In the validation cohort, POST-NIHSS area under receiver operating characteristic curve was 0.82 (95% CI, 0.69–0.94) versus NIHSS area under receiver operating characteristic curve 0.73 (95% CI, 0.58–0.87), P =0.04. Conclusions: POST-NIHSS showed higher prognostic accuracy than NIHSS and may be useful to identify posterior circulation stroke patients with NIHSS <10 at higher risk of poor outcome.

Diagnostic Value of CD4/CD8 in Scrub Typhus

Scrub typhus is often misdiagnosed in febrile patients, leading to antibiotic abuse and multiple complications. We conducted a retrospective record review at the Fourth Affiliated Hospital of Guangxi Medical University in China. Data were collected on 52 patients with a confirmed diagnosis of scrub typhus and complete clinical data. In addition, data were collected on 52 patients with bloodstream infection, 25 patients with HIV infection, 112 patients with common community-acquired pneumonia (CCAP), and 36 patients with severe community-acquired pneumonia (SCAP) to serve as control groups. The peripheral blood CD4 and CD8 counts, CD4/CD8 ratio, C-reactive protein, procalcitonin, alanine aminotransferase, aspartate aminotransferase, creatinine, and β2 microglobulin levels; and the white blood cell count and neutrophil percentage were compared between the scrub typhus and the control groups. The value of these biomarkers in the diagnosis of scrub typhus was assessed using receiver–operating characteristic curve analysis. The scrub typhus group had a significantly lower CD4 count and CD4/CD8 ratio than the bloodstream infection, CCAP, and SCAP groups, and a significantly greater CD4 count and CD4/CD8 ratio than the HIV infection group. In contrast, the scrub typhus group had a significantly greater CD8 count than the bloodstream infection and CCAP and SCAP groups, and it had a lower level of CD8 than the HIV infection group. The areas under the curve of CD4/CD8 were more than 0.93 in the receiver–operating characteristic curve analysis. These findings suggest that the CD4/CD8 ratio is a useful ancillary test for diagnosing scrub typhus.

Premio de Investigación SCHOT 2020: desarrollo y validación de un modelo multivariables de predicción de estadía hospitalaria en pacientes mayores de 65 años sometidos artroplastia total de cadera electiva en Chile utilizando aprendizaje de máquinas

Resumen Introducción La predicción de la estadía hospitalaria luego de una artroplastia total de cadera (ATC) electiva es crucial en la evaluación perioperatoria de los pacientes, con un rol determinante desde el punto de vista operacional y económico. Internacionalmente, se han empleado macrodatos (big data, en inglés) e inteligencia artificial para llevar a cabo evaluaciones pronósticas de este tipo. El objetivo del presente estudio es desarrollar y validar, con el empleo del aprendizaje de máquinas (machine learning, en inglés), una herramienta capaz de predecir la estadía hospitalaria de pacientes chilenos mayores de 65 años sometidos a ATC por artrosis. Material y Métodos Empleando los registros electrónicos de egresos hospitalarios anonimizados del Departamento de Estadísticas e Información de Salud (DEIS), se obtuvieron los datos de 8.970 egresos hospitalarios de pacientes sometidos a ATC por artrosis entre los años 2016 y 2018. En total, 15 variables disponibles en el DEIS, además del porcentaje de pobreza de la comuna de origen del paciente, fueron incluidos para predecir la probabilidad de que un paciente presentara una estadía acortada (< 3 días) o prolongada (> 3 días) luego de la cirugía. Utilizando técnicas de aprendizaje de máquinas, 8 algoritmos de predicción fueron entrenados con el 80% de la muestra. El 20% restante se empleó para validar las capacidades predictivas de los modelos creados a partir de los algoritmos. La métrica de optimización se evaluó y ordenó en un ranking utilizando el área bajo la curva de característica operativa del receptor (area under the receiver operating characteristic curve, AUC-ROC, en inglés), que corresponde a cuan bien un modelo puede distinguir entre dos grupos. Resultados El algoritmo XGBoost obtuvo el mejor desempeño, con una AUC-ROC promedio de 0,86 (desviación estándar [DE]: 0,0087). En segundo lugar, observamos que el algoritmo lineal de máquina de vector de soporte (support vector machine, SVM, en inglés) obtuvo una AUC-ROC de 0,85 (DE: 0,0086). La importancia relativa de las variables explicativas demostró que la región de residencia, el servicio de salud, el establecimiento de salud donde se operó el paciente, y la modalidad de atención son las variables que más determinan el tiempo de estadía de un paciente. Discusión El presente estudio desarrolló algoritmos de aprendizaje de máquinas basados en macrodatos chilenos de libre acceso, y logró desarrollar y validar una herramienta que demuestra una adecuada capacidad discriminatoria para predecir la probabilidad de estadía hospitalaria acortada versus prolongada en adultos mayores sometidos a ATC por artrosis. Conclusión Los algoritmos creados a traves del empleo del aprendizaje de máquinas permiten predecir la estadía hospitalaria en pacientes chilenos operado de artroplastia total de cadera electiva.

Risk factors of early postoperative bowel obstruction for patients undergoing selective colorectal surgeries

Objective Postoperative bowel obstruction was one of the most severe complications in patients who received colorectal surgeries. This study aimed to explore risk factors of early postoperative obstruction and to construct a nomogram to predict the possibility of occurrence. Methods The records of 1437 patients who underwent elective colorectal surgery in Peking University People’s Hospital from 2015 to 2020 were retrospectively collected. Risk factors of early postoperative bowel obstruction were identified by logistic regression analysis and a nomogram was then constructed. Bootstrap was applied to verify the stability of the model. Results COPD, hypothyroidism, probiotic indications, duration of antibiotics, and time to postoperative feeding were identified as independent risk factors and were put into a nomogram for predicting early postoperative bowel obstruction. The nomogram showed robust discrimination, with the area under the receiver operating characteristic curve was 0.894 and was well-calibrated. Conclusion A nomogram including independent risk factors of COPD, hypothyroidism, probiotic indications, duration of antibiotics, and time to postoperative feeding were established to predict the risk of early postoperative bowel obstruction.

Correlation Between Extent of Lacrimal Gland Prolapse and Clinical Features of Thyroid- Associated Ophthalmopathy: A Retrospective Observational Study

Background: Studies on the factors related to lacrimal gland prolapse (LGP) in patients with thyroid-associated ophthalmopathy (TAO) are limited. This study aimed to assess the ability of abnormal location of the lacrimal gland on magnetic resonance images to predict disease activity in patients with TAO.Methods: Thirty-six patients (72 orbits) with inactive TAO (43 orbits, Clinical Activity Score [CAS] <3) or active TAO (29 orbits, CAS ≥3) were investigated retrospectively. All patients underwent ophthalmic evaluation and orbital magnetic resonance imaging. The severity of LGP and proptosis and the extraocular muscle (EOM) volume were measured. LGP and related factors were assessed by correlational and linear regression analyses. The value of LGP for discriminating the activity of TAO was evaluated by receiver-operating characteristic curve analysis.Results: The mean LGP was significantly higher in the active TAO group than in the inactive TAO group (P<0.001). There were significant positive correlations between LGP severity and the CAS (r=0.51, P<0.001), proptosis (r=0.72, P<0.001), and EOM volume (superior rectus [r=0.49, P<0.001], inferior rectus [r=0.47, P<0.001], lateral rectus [r=0.59, P<0.001], medial rectus [r=0.62, P<0.001], superior oblique [r=0.48, P<0.001], and all EOMs [r=0.59, P<0.001]). Receiver-operating characteristic curve analysis revealed an LGP of 13.65 mm (area under the curve, 0.824; sensitivity, 79.3%; specificity, 81.4%) to be the cut-off value that differentiated active and inactive TAO.Conclusions: LGP measurements obtained from orbital magnetic resonance images were positively correlated with CAS, proptosis and EOM volum. The extent of LGP appears to be a good indicator of disease activity in patients with TAO.