Artificial intelligence to predict in-hospital mortality using novel anatomical injury score

The aim of the study is to develop artificial intelligence (AI) algorithm based on a deep learning model to predict mortality using abbreviate injury score (AIS). The performance of the conventional anatomic injury severity score (ISS) system in predicting in-hospital mortality is still limited. AIS data of 42,933 patients registered in the Korean trauma data bank from four Korean regional trauma centers were enrolled. After excluding patients who were younger than 19 years old and those who died within six hours from arrival, we included 37,762 patients, of which 36,493 (96.6%) survived and 1269 (3.4%) deceased. To enhance the AI model performance, we reduced the AIS codes to 46 input values by organizing them according to the organ location (Region-46). The total AIS and six categories of the anatomic region in the ISS system (Region-6) were used to compare the input features. The AI models were compared with the conventional ISS and new ISS (NISS) systems. We evaluated the performance pertaining to the 12 combinations of the features and models. The highest accuracy (85.05%) corresponded to Region-46 with DNN, followed by that of Region-6 with DNN (83.62%), AIS with DNN (81.27%), ISS-16 (80.50%), NISS-16 (79.18%), NISS-25 (77.09%), and ISS-25 (70.82%). The highest AUROC (0.9084) corresponded to Region-46 with DNN, followed by that of Region-6 with DNN (0.9013), AIS with DNN (0.8819), ISS (0.8709), and NISS (0.8681). The proposed deep learning scheme with feature combination exhibited high accuracy metrics such as the balanced accuracy and AUROC than the conventional ISS and NISS systems. We expect that our trial would be a cornerstone of more complex combination model.

Deep Semi-Supervised Algorithm for Learning Cluster- Oriented Representations of Medical Images Using Partially Observable DICOM Tags and Images

The task of automatically extracting large homogeneous datasets of medical images based on detailed criteria and/or semantic similarity can be challenging because the acquisition and storage of medical images in clinical practice is not fully standardised and can be prone to errors, which are often made unintentionally by medical professionals during manual input. In this paper, we propose an algorithm for learning cluster-oriented representations of medical images by fusing images with partially observable DICOM tags. Pairwise relations are modelled by thresholding the Gower distance measure which is calculated using eight DICOM tags. We trained the models using 30,000 images, and we tested them using a disjoint test set consisting of 8000 images, gathered retrospectively from the PACS repository of the Clinical Hospital Centre Rijeka in 2017. We compare our method against the standard and deep unsupervised clustering algorithms, as well as the popular semi-supervised algorithms combined with the most commonly used feature descriptors. Our model achieves an NMI score of 0.584 with respect to the anatomic region, and an NMI score of 0.793 with respect to the modality. The results suggest that DICOM data can be used to generate pairwise constraints that can help improve medical images clustering, even when using only a small number of constraints.

Addressing the Upper Third of the Nose in Endonasal Rhinoplasty

Effective management of the upper nasal vault is based on a thorough preoperative analysis and detailed understanding of the requisite principles and techniques utilized to modify the anatomic structures in this region. The surgeon must equally consider form and function when performing manipulation of the upper nasal vault. Special considerations apply when managing this anatomic region via an endonasal or closed approach. A review of this topic is presented with a focus on techniques as they apply to the endonasal rhinoplasty patient.

Skin Strain Analysis of the Scapular Region and Wearables Design

Monitoring scapular movements is of relevance in the contexts of rehabilitation and clinical research. Among many technologies, wearable systems instrumented by strain sensors are emerging in these applications. An open challenge for the design of these systems is the optimal positioning of the sensing elements, since their response is related to the strain of the underlying substrates. This study aimed to provide a method to analyze the human skin strain of the scapular region. Experiments were conducted on five healthy volunteers to assess the skin strain during upper limb movements in the frontal, sagittal, and scapular planes at different degrees of elevation. A 6 × 5 grid of passive markers was placed posteriorly to cover the entire anatomic region of interest. Results showed that the maximum strain values, in percentage, were 28.26%, and 52.95%, 60.12% and 60.87%, 40.89%, and 48.20%, for elevation up to 90° and maximum elevation in the frontal, sagittal, and scapular planes, respectively. In all cases, the maximum extension is referred to the pair of markers placed horizontally near the axillary fold. Accordingly, this study suggests interesting insights for designing and positioning textile-based strain sensors in wearable systems for scapular movements monitoring.

Spinal alignment shift between supine and prone CT imaging occurs frequently and regardless of the anatomic region, risk factors, or pathology

Computer-assisted spine surgery based on preoperative CT imaging may be hampered by sagittal alignment shifts due to an intraoperative switch from supine to prone. In the present study, we systematically analyzed the occurrence and pattern of sagittal spinal alignment shift between corresponding preoperative (supine) and intraoperative (prone) CT imaging in patients that underwent navigated posterior instrumentation between 2014 and 2017. Sagittal alignment across the levels of instrumentation was determined according to the C2 fracture gap (C2-F) and C2 translation (C2-T) in odontoid type 2 fractures, next to the modified Cobb angle (CA), plumbline (PL), and translation (T) in subaxial pathologies. One-hundred and twenty-one patients (C1/C2: n = 17; C3-S1: n = 104) with degenerative (39/121; 32%), oncologic (35/121; 29%), traumatic (34/121; 28%), or infectious (13/121; 11%) pathologies were identified. In the subaxial spine, significant shift occurred in 104/104 (100%) cases (CA: *p = .044; T: *p = .021) compared to only 10/17 (59%) cases that exhibited shift at the C1/C2 level (C2-F: **p = .002; C2-T: *p < .016). The degree of shift was not affected by the anatomic region or pathology but significantly greater in cases with an instrumentation length > 5 segments (“∆PL > 5 segments”: 4.5 ± 1.8 mm; “∆PL ≤ 5 segments”: 2 ± 0.6 mm; *p = .013) or in revision surgery with pre-existing instrumentation (“∆PL presence”: 5 ± 2.6 mm; “∆PL absence”: 2.4 ± 0.7 mm; **p = .007). Interestingly, typical morphological instability risk factors did not influence the degree of shift. In conclusion, intraoperative spinal alignment shift due to a change in patient position should be considered as a cause for inaccuracy during computer-assisted spine surgery and when correcting spinal alignment according to parameters that were planned in other patient positions.

Longitudinal study of medical downgrades in the Royal Air Force

IntroductionAs the focus of the Royal Air Force (RAF) shifts from sustained to contingency operations and the number of personnel is reduced, the burden of retained, medically downgraded personnel may affect operational readiness. The main aims were: to define the prevalence of morbidity leading to permanent medical downgrading; to determine at risk populations and identify areas for improvement.MethodDatabase of personnel referred to the RAF Medical Board was analysed from January 2012 to October 2013 and January 2017 to December 2019. Patients were excluded if they did not require a formal medical board; incomplete and duplicate entries were also excluded. The primary reason for medical downgrade was categorised with an ICD-10 code. Further subanalysis compared musculoskeletal disease with age, individual trade groups and anatomic region.Results2% of RAF service personnel were permanently downgraded annually. Musculoskeletal disease was the leading cause for permanent downgrade across both periods: 58% and 49%. Female personnel were at a greater risk of musculoskeletal downgrade compared with males. Spinal and knee pathology were the leading cause for downgrading among ‘high risk’ personnel. Personnel downgraded due to musculoskeletal pathology were often retained in a limited role with 10% and 5% retained as medically fully deployable. 14% and 12% of personnel downgraded due to musculoskeletal pathology were medically discharged.ConclusionMusculoskeletal disease was the leading cause for permanent medical downgrades in the RAF. A greater proportion of downgraded personnel with musculoskeletal conditions were retained in service with medical limitations rather than medically discharged.

68Ga-Prostate-Specific Membrane Antigen Positron Emission Tomography-Computed Tomography-Based Primary Staging and Histological Correlation after Extended Pelvic Lymph Node Dissection in Intermediate-Risk Prostate Cancer

<b><i>Objective:</i></b> The objective of this study is to evaluate prostate-specific membrane antigen positron emission tomography-computed tomography (PSMA PET/CT)-based primary staging in exclusively D′Amico intermediate-risk prostate cancer (PCa) patients. <b><i>Patients and Methods:</i></b> We relied on the Braunschweig institutional database and retrospectively identified D′Amico intermediate-risk PCa patients who were administered to ⁶⁸Ga-PSMA PET/CT-based primary staging prior to consecutive radical prostatectomy and extended lymph node dissection. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for the detection of lymph node metastases were analyzed per-patient (<i>n</i> = 39), per-pelvic side (<i>n</i> = 78), and per-anatomic-region (external iliac artery and vein left/right vs. obturator fossa left/right vs. internal iliac artery left/right) (<i>n</i> = 203), respectively. <b><i>Results:</i></b> Sensitivity, specificity, PPV, and NPV per-patient were 20.0, 94.1, 33.3, and 88.9%, respectively. Sensitivity, specificity, PPV, and NPV per-pelvic-side were 16.7, 97.2, 33.3, and 93.3%, respectively. Sensitivity, specificity, PPV, and NPV per-anatomic-region were 16.7, 99.0, 33.3, and 97.5%, respectively. <b><i>Conclusions:</i></b> We recorded high rates of specificity and NPV for ⁶⁸Ga-PSMA PET/CT-based primary staging in D′Amico intermediate-risk PCa patients. Conversely, the sensitivity and PPV were lower than anticipated. Larger and favorably prospective trials are needed to verify our results and to unravel possible bias from such smaller studies.