The potential clinical utility of an artificial intelligence model for identification of vertebral compression fractures in chest radiographs.

PURPOSE: To assess the ability of the Annalise Enterprise CXR Triage Trauma artificial intelligence model to identify vertebral compression fractures on chest radiographs and its potential to address undiagnosed osteoporosis and its treatment. MATERIALS AND METHODS: This retrospective study used a consecutive cohort of 596 chest radiographs from four U.S. hospitals between 2015 and 2021. Each radiograph included both frontal (anteroposterior or posteroanterior) and lateral projections. These radiographs were assessed for the presence of vertebral compression fracture in a consensus manner by up to three thoracic radiologists. The model then performed inference on the cases. A chart review was also performed for the presence of osteoporosis-related ICD-10 diagnostic codes and medication use for the study period and an additional year of follow up. RESULTS: The model successfully completed inference on 595 cases (99.8%); these cases included 272 positive cases and 323 negative cases. The model performed with area under the receiver operating characteristic curve of 0.955 (95% CI: 0.939 to 0.968), sensitivity 89.3% (95% CI: 85.7 to 92.7%) and specificity 89.2% (95% CI: 85.4 to 92.3%). Out of the 236 true-positive cases (i.e., correctly identified vertebral compression fractures by the model) with available chart information, only 86 (36.4%) had a diagnosis of vertebral compression fracture and 140 (59.3%) had a diagnosis of either osteoporosis or osteopenia; only 78 (33.1%) were receiving a disease modifying medication for osteoporosis. CONCLUSION: The model identified vertebral compression fracture accurately with a sensitivity 89.3% (95% CI: 85.7 to 92.7%) and specificity of 89.2% (95% CI: 85.4 to 92.3%). Its automated use could help identify patients who have undiagnosed osteoporosis and who may benefit from taking disease modifying medications.

Evaluation of an Artificial Intelligence Model for Identification of Mass Effect and Vasogenic Edema on CT of the Head.

BACKGROUND AND PURPOSE: Mass effect and vasogenic edema are critical findings on CT of the head. This study compared the accuracy of an artificial intelligence model (Annalise Enterprise CTB) with consensus neuroradiologists' interpretations in detecting mass effect and vasogenic edema. MATERIALS AND METHODS: A retrospective stand-alone performance assessment was conducted on data sets of noncontrast CT head cases acquired between 2016 and 2022 for each finding. The cases were obtained from patients 18 years of age or older from 5 hospitals in the United States. The positive cases were selected consecutively on the basis of the original clinical reports using natural language processing and manual confirmation. The negative cases were selected by taking the next negative case acquired from the same CT scanner after positive cases. Each case was interpreted independently by up-to-three neuroradiologists to establish consensus interpretations. Each case was then interpreted by the artificial intelligence model for the presence of the relevant finding. The neuroradiologists were provided with the entire CT study. The artificial intelligence model separately received thin (≤1.5 mm) and/or thick (>1.5 and ≤5 mm) axial series. RESULTS: The 2 cohorts included 818 cases for mass effect and 310 cases for vasogenic edema. The artificial intelligence model identified mass effect with a sensitivity of 96.6% (95% CI, 94.9%-98.2%) and a specificity of 89.8% (95% CI, 84.7%-94.2%) for the thin series, and 95.3% (95% CI, 93.5%-96.8%) and 93.1% (95% CI, 89.1%-96.6%) for the thick series. It identified vasogenic edema with a sensitivity of 90.2% (95% CI, 82.0%-96.7%) and a specificity of 93.5% (95% CI, 88.9%-97.2%) for the thin series, and 90.0% (95% CI, 84.0%-96.0%) and 95.5% (95% CI, 92.5%-98.0%) for the thick series. The corresponding areas under the curve were at least 0.980. CONCLUSIONS: The assessed artificial intelligence model accurately identified mass effect and vasogenic edema in this CT data set. It could assist the clinical workflow by prioritizing interpretation of cases with abnormal findings, possibly benefiting patients through earlier identification and subsequent treatment.

Enhanced piezoelectric response in BTO NWs-PVDF composite through tuning of polar phase content.

We have fabricated a flexible, environment friendly piezoelectric nanogenerator (PENG) based on the ferroelectric Polyvinylidene fluoride (PVDF) composite incorporated with Barium titanate (BaTiO3) nanowires (NWs) of piezoelectric coefficientd33 = 308 pm V-1. The single-layered PENG can deliver output power density of 10µW cm-2and an output voltage of 2 V with a nominal mechanical load of 1 kPa. BaTiO3(BTO) NWs of different concentrations were incorporated into PVDF to tune the polar phase content, internal resistance, and optimize the output power. We show that there exists a critical value of BTO NWs loading of 15 wt%, beyond which the piezoelectric energy harvesting characteristics of the PVDF nanocomposites decrease. The oxygen vacancies present in the BTO NWs surface attract the fluorine ions of PVDF chain and favour the formation ofßphase. The enhanced value of dielectric constant and dielectric loss of BTO-PVDF samples in the low frequency region suggest strong interfacial polarization in the composite system. The fabricated PENG can charge a super-capacitor up to 4 V within 35 s. The origin of the high power output from the BTO (15 wt%)-PVDF composite is attributed to the combined effect of enhanced polar phase content, strong interfacial polarization, and reduced internal resistance. This study provides an effective pathway in enhancing the performance of BTO-PVDF based piezoelectric energy harvesters.

Smoking Cessation by Phone Counselling in a Lung Cancer Screening Program: A Retrospective Comparative Cohort Study.

Introduction: Smoking cessation integration within lung cancer screening programs is challenging. Currently, phone counselling is available across Canada for individuals referred by healthcare workers and by self-referral. We compared quit rates after phone counselling interventions between participants who self-refer, those referred by healthcare workers, and those referred by a lung cancer screening program. Methods: This is a retrospective cohort study of participants referred to provincial smoking cessation quit line in contemporaneous cohorts: self-referred participants, healthcare worker referred, and those referred by a lung cancer screening program if they were still actively smoking at the time of first contact. Baseline, covariates (sociodemographic information, smoking history, and history of mental health disorder) and quit intentions (stage of change, readiness for change, previous use of quit programs, and previous quit attempts) were compared among the three cohorts. Our primary outcome was defined as self-reported 30-day abstinence rates at 6 months. Multivariable logistic regression was used to identify whether group assignment was associated with higher quit rates. Results: Participants referred by a lung cancer screening program had low quit rates (12%, 95% CI: 5-19) at six months despite the use of phone counselling. Compared to patients who were self-referred to the smoking cessation phone helpline, individuals referred by a lung cancer screening program were much less likely to quit (adjusted OR 0.37; 95% CI: 0.17-0.8), whereas those referred by healthcare workers were twice as likely to quit (adjusted OR 2.16 (1.3-3.58)) even after adjustment for differences in smoking intensity and quit intentions. Conclusions: Phone counselling alone has very limited benefit in a lung cancer screening program. Participants differ significantly from those who are otherwise referred by healthcare workers. This study underlines the importance of a dedicated and personalized tobacco treatment program within every lung cancer screening program. The program should incorporate best practices and encourage treatment regardless of readiness to quit.

Piezoelectric Nanogenerators based on Lead Zirconate Titanate nanostructures: an insight into the effect of potential barrier and morphology on the output power generation.

The high internal resistance of the perovskite materials used in Nanogenerators (NGs) lowers the power generation. It severely restricts their application for mechanical energy harvesting from the ambient source. In this work, we demonstrate a flexible Piezoelectric NG (PENG) with an improved device structure. Hydrothermally grown one-dimensional Lead Zirconate Titanate (Pb(ZrTi)O3) of different morphologies are used as the generating material. The morphology of the PZT nanostructures, engineered from nanoparticles to needle-shaped nanowires to increase the surface to volume ratio, provides effective mechanical contact with the electrode. The reduction of the internal resistance of the PENG has been achieved by two ways: (i) fabrication of interdigitated electrodes (IDE) to increase the interfacial polarization and (ii) lowering of Schottky barrier height (SBH) at the junction of the PZT nanostructure and the metal electrode by varying the electrode materials of different work functions. We find that lowering of the SBH at the interface contributes to an increased piezo voltage generation. The flexible nano needles-based PENG can deliver output voltage 9.5 V and power density 615µW cm-2on application low mechanical pressure (∼1 kPa) by tapping motion. The internal resistance of the device is ∼0.65 MΩ. It can charge a 35µF super-capacitor up to 5 V within 20 s. This study provides a systematic pathway to solve the bottlenecks in the piezoelectric nanogenerators due to the high internal resistance.

Effect of low temperature structural phase transitions in BaTiO3on electrical transport through a metal-ferroelectric-metal multilayer of AuCr/BaTiO3/Nb:SrTiO3.

In this paper we report an investigation of electronic transport through the metal-ferroelectric-metal (MFM) multilayer consisting of AuCr/BaTiO3/Nb:SrTiO3over a temperature range of 100 K-300 K where BaTiO3(BTO) shows a series of structural phase transitions leading to change of magnitude as well as the orientation of the polarizationP→. We observed that the bias dependent barrier heights associated with the interfaces carry strong signature of the phase transitions in the BTO layer which lead to a strong temperature dependent asymmetric transport, when cooled down below room temperature. Specifically, it is observed that the temperature dependence is closely correlated to low temperature transitions in the BTO layer as revealed through the temperature dependent x-ray diffraction (XRD), capacitance as well as resistivity behavior of the BTO layer. There is substantial enhancement of the asymmetry in the device current that occurs at or close to temperaturesT2∼ 190 K where BTO shows a crystallographic phase change to the low temperature rhombohedral phase. The temperature dependent changes occur due to barrier modulation at the interfaces of AuCr/BaTiO3as well as BaTiO3/Nb:SrTiO3that softens on cooling due to inhomogenities present there. The change in barrier on change of the bias direction has been observed belowT2which arises from alignment of the polarization in-plane or out-of-plane as determined by tensile or compressive character of the in-plane strain in the BTO film. We also discuss the effect of space charge determined by the oxygen vacancies in the interface region, regulated by the applied bias.

ZnO/Si nanowires heterojunction array-based nitric oxide (NO) gas sensor with noise-limited detectivity approaching 10 ppb.

We report a ZnO/Silicon nanowire (ZnO/Si NWs) heterojunction array-based NO gas sensor operating at room temperature with an extremely high response (noise limited response ∼10 ppb). The sensor shows very high selectivity towards NO gas sensing and limited perturbation in response due to the presence of moisture. The sensor has been fabricated by using cost-effective chemical processing that is compatible with wafer-level processing. The vertically aligned Si NWs array has been made by an electroless etching method and the ZnO nanostructure was made by chemical solution deposition and spin-coating. Extensive cross-sectional electron microscopy and composition analysis by line EDS allowed us to make a physical model. The electrical characteristic of the model was to fit the I-V data before and after exposure to gas and essential changes in electrical parameters were obtained. This was then explained based on a proposal for the mechanism of gas sensing. We observe that the heterostructure leads to a synergetic effect where the sensing response is more than the sum total of the individual components, namely the ZnO and the Si NWs. The response is much enhanced in the p-n junction when the n-ZnO nanostructure interfaces with p-Si NW compared to that in the n-n junction formed by ZnO on n-Si NW.