Automatic intracranial abnormality detection and localization in head CT scans by learning from free-text reports

Computed tomography of the head as a screening examination for facial fractures

Purpose: The purpose of our study was to combine differences in radiomic features extracted from lung regions in the computed tomography (CT) scans of patients diagnosed with idiopathic pulmonary fibrosis (IPF) to identify associations with genetic variations and patient survival. Approach: A database of CT scans and genomic data from 169 patients diagnosed with IPF was collected retrospectively. Six region-of-interest pairs (three per lung, positioned posteriorly, anteriorly, and laterally) were placed in each of three axial CT sections for each patient. Thirty-one features were used in logistic regression to classify patients' genetic mutation status; classification performance was evaluated through the area under the receiver operating characteristic (ROC) curve [average area under the ROC curve (AUC)]. Kaplan-Meier (KM) survival curve models quantified the ability of each feature to differentiate between survival curves based on feature-specific thresholds. Results: Nine first-order texture features and one fractal feature were correlated with TOLLIP-1 (rs4963062) mutations (AUC: 0.54 to 0.74), and five Laws' filter features were correlated with TOLLIP-2 (rs5743905) mutations (AUC: 0.53 to 0.70). None of the features analyzed were found to be correlated with MUC5B mutations. First-order and fractal features demonstrated the greatest discrimination between KM curves. Conclusions: A radiomics approach for the correlation of patient genetic mutations with image texture features has potential as a biomarker. These features also may serve as prognostic indicators using a survival curve modeling approach in which the combination of radiomic features and genetic mutations provides an enhanced understanding of the interaction between imaging phenotype and patient genotype on the progression and treatment of IPF.

Prediction Value of the Canadian CT Head Rule and the New Orleans Criteria for Positive Head CT Scan and Acute Neurosurgical Procedures in Minor Head Trauma: A Multicenter External Validation Study

To the Editor: Chronic subdural hematomas (CSDHs) are encapsulated collections of blood breakdown products and fluid between the dura mater and the arachnoid.1 Their global incidence is estimated to be about 5/100 000/yr in patients younger than 65 yr,2 increasing to 58/100 000/yr in patients over 65 yr.1 Surgery usually allows a good outcome even in elderly. The clinical outcome of CSDH is conditioned by comorbidities including pulmonary diseases. Nowadays, we are facing a new possible condition related to coronavirus disease 2019 (COVID-19) that could affect the outcome. The spread of this infection started in 2019, December 31st when China alerted WHO about cases of unusual amount of interstitial pneumonia (IP) in Wuhan. After 7 d, on January 7th, scientists announced they had identified a new virus named COVID-19 similar to SARS-CoV. Italy is dealing with pandemic spread of COVID-19. As a matter of fact, on 19th March, it became the country with the highest number of confirmed deaths in the world. On March 23rd 2020 Italy was the world's centre of the epidemic with 69.176 confirmed cases, 6.820 deaths, and 21.137 recoveries.3 Clinically COVID-19 could lead to a severe IP and acute respiratory distress syndrome (ARDS), especially in older patients with multiple comorbidities.4 No studies about surgery in COVID-19 patients have been reported so far. We aim to describe our surgical experience with CSDH in a COVID-19 neurosurgical center. We admitted 5 patients with CSDH to the Neurosurgical Department of Brescia University Hospital between February 21, 2020 (first COVID-19 case reported in Italy) and March 23, 2020. The patients were positive for COVID-19 real-time polymerase chain reaction obtained by nasopharyngeal swab.5,6 We gathered the following data for each patient: age and sex, Cumulative Illness Rating Scale,7 antithrombotic therapy and perioperative mortality (within 30 d). All the patients had signed a consent form approved by the Local Ethic Committee regarding the use of their clinical data. We compared the mortality rate of this new cohort with the data extracted from our pre-COVID-19 CSDH case series. All the patients underwent pre-operative chest X-Ray (CXR) or computed tomography (CT) and routine blood test. An anesthesiological evaluation was performed for each patient. We cohortized our neurosurgical ward to separate COVID-19 positive from negative cases. COVID-19 positive patients started anti-retroviral therapy with lopinavir/ritonavir and hydroxychloroquine. Daily arterial blood gas analysis and CXR were performed. Surgery or endovascular treatment were indicated when the CSDH was symptomatic (presence of focal neurological deficits or mental status changes) and the maximum thickness was greater than 1 cm (Figures 1-4). One case did not present severe neurological impairment and was treated conservatively (Figure 5). No preoperative respiratory impairment was observed.FIGURE 1.: A and B, Head CT scan, axial view: pre- and postoperative CDSH. C, CXR showing bilateral and diffuse IP.FIGURE 2.: A, Head CT scan, axial view: bilateral CSDH. B, CXR showing bilateral and diffuse IP. C and D, MMA embolization procedure.FIGURE 3.: A, Head CT scan, axial view: preoperative CSDH. B, Head CT scan, axial view: postoperative CSDH with signs of recent rebleeding. C, CXR showing bilateral and IP. D, Chest CT scan, axial view, showing ground glass opacity.FIGURE 4.: A, Head CT scan, axial view: preoperative left CSDH. B, Head CT scan, axial view: postoperative CSDH with signs of recent rebleeding. C, CXR showing bilateral IP.FIGURE 5.: A, Head CT scan, axial view: left CSDH. B, normal CXR.We treated all the CSDH patients under general anesthesia. Three patients were operated (2 through craniotomy and 1 with a burr hole). Endovascular occlusion of the middle meningeal artery (MMA) was performed in 1 case (Figure 2). In the surgical cases we placed a subdural drainage for 48 h. After its removal patients underwent a CT head scan (Figures 1, 3, and 4). Afterwards the patients started low-molecular-weight heparin at prophylactic dose before mobilization. The cases are reported in the supplementary material section (Supplemental Digital Content). CSDHs mostly occur in elderly, with an average age of 63.1 Head trauma is the major risk factor, identified in less than 50% (often minor head trauma).8 Other risk factors are described like alcohol abuse, seizures, CSF shunts and coagulopathies, including therapeutic anticoagulation. CSDHs are bilateral in 20% to 25% of cases.9 At present there is no scientific experience regarding surgical outcome of COVID-19 patients. We compared the recent cohort of COVID-19 CSDH patients with our historical series. Between May 2018 and September 2019, we operated 142 patients for CSDH and we observe 5 death at our Institution. Our mortality rate was 3.7% according to the literature.10 In our recent experience, we observed 4 death in 5 COVID-19 patients suffering from CSDH. Therefore, we observed a mortality rate of 80% about 21,6 times greater than our control data. HEMATOLOGICAL DISORDERS We observed 2 cases of mild thrombocytopenia (Table). In these cases, we observed a re-bleeding (Figures 3 and 4) that led from a rapid neurological worsening to death within 5 d. This condition could be related to COVID-19 infection, as reported in literature.11 Independently from the hemorrhagic risk, Lippi et al12 showed that low platelet count is associated with increased risk of severe disease and mortality in patients with COVID-19, and this should serve as clinical indicator of worsening illness during hospitalization.12 In our series, we suppose that thrombocytopenia led to re-bleeding and was associated with poor outcome. TABLE. - Clinical Features of our Cohort Sex Age CIRS AT Side COVID-19 IP TP* Surgery Time to death(d) M 82 13 Yes Left + + No Burr-hole 14 M 86 18 No Bilateral + + No MMA embolization 10 M 77 20 No Right + + Yes Craniotomy 5 M 85 22 Yes Left + + Yes Burr-hole 5 M 78 19 Yes Left + – No NO Alive *TP (Thrombocytopenia): 100.000<PLTs<150.000All patients developed IP after surgery. Thrombocytopenia was observed in 2 cases (40%). The patients suffered rebleeding and showed a shorter time to death. CIRS (Cumulative Illness Rating Scale), AT (antithrombotic drugs), IP (Interstitial Pneumonia), COVID-19 (Coronavirus Disease 2019). INTERSTITIAL PNEUMONIA Dyspnoea and fatigue occurred in all our patients within 48 hours from surgery. CXR revealed severe IP (Figures 1-4). Ground glass opacity and bilateral patchy shadowing were observed on the chest CT (Figure 3).5,13 All our patients had COVID-19 infection without pre-operative respiratory symptoms. Immune system could be impaired following surgical procedures and this may have unmasked a subclinical infection.14,15 On the other hand no respiratory failure was observed in the conservative-treated case (Figure 5). In our experience IP occurred in all cases after treatment and worsened the outcome. This evenience represents a possible complication, often fatal, of COVID-19 infection.5 HEALTH EMERGENCY Nowadays, Italian health care system is the most afflicted in the pandemic scenario.16 The overload of the intensive care units in Lombardy, despite the efforts made, has necessarily influenced the resuscitation possibilities of elderly patients.17 Therefore, we cannot exclude that our results could be affected by the health emergency status. Seung et al. reported good bleeding control from CSDH membrane with MMA embolization, prevention of further growth of hematoma and even spontaneous resolution without surgery.18 Anyway our endovascular treated patient showed the same poor outcome of the surgical cases. Although statistical analysis of these preliminary data is not possible, COVID-19 patients appear to suffer from a negative surgical outcome. It is our belief that conservative treatment should be preferred whenever surgery could be postponed. Disclosures The authors have no personal, financial, or institutional interest in any of the drugs, materials, or devices described in this article.

BackgroundThe hydration status can be indicated by biomarkers in the urine. However, the sensitivity and specificity of single measurements of biomarkers in morning urine and spot urine samples to quantify previous and current daily water ingestion is unclear.MethodsThe water content of food and liquid consumed by 20 volunteers (mean age 42 years) was calculated daily for two weeks. The volunteers increased their consumption of water by approximately 30% during the second week. They measured their excreted urine volume and sampled the morning urine and 24-h collections of urine for analysis of osmolality and creatinine during the first four days of both weeks (N = 157). The same biomarkers of hydration were measured in spot samples taken at every voiding on the other days (N = 762). Receiver operating characteristic (ROC) curves were used to study the ability of pre-specified ranges of biomarkers to quantify the water intake.ResultsThe biomarkers in the morning urine obtained during normal fluid intake quantified the water consumption with an average area under the ROC curve (AUC) of 0.72 for osmolality and 0.66 for creatinine. Spot urine yielded an AUC of 0.74 for osmolality and 0.70 for creatinine. The AUCs obtained for days of increased fluid intake were approximately 10% lower. Large intakes (3–4 L daily) were identified with a sensitivity of 50–80% and low intakes (< 1.5–2 L) with a sensitivity of 20–50%, while false positives occurred in approximately 10%.ConclusionBiomarkers in morning urine and spot urine samples distinguished between large and small daily water intakes. Osmolality was slightly superior to creatinine. The indications were less useful during days of increased fluid intake.

Studies have documented increased advanced radiography use in U.S. emergency departments (EDs) for injured patients over the past decade. The authors explored trends in recent years (2007 through 2010) in advanced radiography use, specifically head computed tomography (CT) and nonhead CT scans. This was a retrospective analysis of ED visits conducted using data from the National Hospital Ambulatory Medical Care Survey (NHAMCS), a representative sample of the U.S. ED visits from 2007 through 2010. All patients designated by the NHAMCS as "related to injury" were included in analyses. CT use was examined by head and nonhead use. Trends, predictors of utilization, and diagnostic yield for head and nonhead CT scans in injured ED patients were analyzed using survey-weighted logistic regression. Diagnostic yield was defined as the proportion of injury-related visits where patients imaged with CT received International Classification of Diseases, 9th Revision (ICD-9), code diagnoses of a severe head or nonhead injury. Among injured ED patients, head CT use increased from 9.6% in 2007 to 11.6%, a relative increase of 20.8% (p<0.001), and nonhead CT from 5.5% to 7.3%, a relative increase of 47.3% (p<0.001). Diagnostic yield for head CT was unchanged (4.9% in 2007 vs. 3.4% in 2010, p=0.093), but fell for nonhead CT from 6.4% in 2007 to 3.3% in 2010 (p=0.04. Advanced radiography use has continued to increase since 2007 in injured patients, and diagnostic yield for nonhead CT has continued to fall. Head CT is more common than CTs of other body areas and may represent an opportunity for reduction given validated clinical decision rules.

Introduction: Rhegmatogenous retinal detachment (RRD) is one of the most common fundus diseases. Many rural areas of China have few ophthalmologists, and ophthalmologic ultrasound examination is of great significance for remote diagnosis of RRD. Therefore, this study aimed to develop and evaluate a deep learning (DL) model, to be used for automated RRD diagnosis based on ophthalmologic ultrasound images, in order to support timely diagnosis of RRD in rural and remote areas. Methods: A total of 6,000 ophthalmologic ultrasound images from 1,645 participants were used to train and verify the DL model. A total of 5,000 images were used for training and validating DL models, and an independent testing set of 1,000 images was used to test the performance of eight DL models trained using four different DL model architectures (fully connected neural network, LeNet5, AlexNet, and VGG16) and two preprocessing techniques (original, original image augmented). Receiver operating characteristic (ROC) curves were used to analyze their performance. Heatmaps were generated to visualize the process of the best DL model in the identification of RRD. Finally, five ophthalmologists were invited to diagnose RRD independently on the same test set of 1,000 images for performance comparison with the best DL model. Results: The best DL model for identifying RRD achieved an area under the ROC curve (AUC) of 0.998 with a sensitivity and specificity of 99.2% and 99.8%, respectively. The best preprocessing method in each model architecture was the application of original image augmentation (average AUC = 0.982). The best model architecture in each preprocessing method was VGG16 (average AUC = 0.998). Conclusion: The best DL model determined in this study has higher accuracy, sensitivity, and specificity than the ophthalmologists’ diagnosis in identifying RRD based on ophthalmologic ultrasound images. This model may provide support for timely diagnosis in locations without access to ophthalmologic care.

PurposeThe present study introduced the half-dose method (HDM), which halves the radiation dose for conventional head computed tomography (CT), for postoperative hydrocephalus and follow-up for craniosynostosis at a children’s hospital. This study aimed to evaluate the contribution of selective head CT scanning optimization towards the overall reduction of radiation exposure.Materials and methodsWe retrospectively assessed 1227 and 1352 head CT examinations acquired before and after the introduction of the HDM, respectively, in children aged 0–15 years. The radiation exposure was evaluated using the CT dose index volume (CTDI-vol), dose-length product (DLP), rate of HDM introduction, and effect of reducing in-hospital radiation dose before and after the introduction of the HDM. For an objective evaluation of the image quality, head CT scans acquired with HDM and full-dose method (FDM) were randomly selected, and the image noise standard deviation (SD) was measured for each scan. In addition, some HDM images were randomly selected and independently reviewed by two radiologists.ResultsThe HDM was introduced in 27.9% of all head CTs. The mean CTDI-vol of all head CTs was 21.5 ± 6.9 mGy after the introduction, a 14.9% reduction. The mean DLP was 418.4 ± 152.9 mGy.cm after the introduction, a 17.2% reduction. Compared to the FDM images, the noise SD of the HDM ones worsened by almost 0.9; however, none of the images were difficult or impossible to evaluate.ConclusionThe HDM yielded diagnostically acceptable images. In addition, a change in protocol for only two diseases successfully reduced the patients’ overall radiation exposure by approximately 15%. Introducing and optimizing the HDM for frequently performed target diseases will be useful in reducing the exposure dose for the hospital’s patient population.

Two hundred sixty-six of 374 consecutive blunt trauma patients underwent emergency computed tomographic (CT) scanning during evaluation at a level I trauma center. The purpose of this study was to develop guidelines for use of CT scanning in the initial evaluation of blunt trauma patients. Of the 131 CT scans of the head obtained, 20 (15%) had positive results. Seven patients whose initial neurologic examinations were normal had abnormal results on head CT scans; none required emergent treatment of their head injury. This suggests that, in the presence of a normal neurologic examination, head CT scans can safely be delayed until other more serious injuries are addressed. Twenty-six CT scans of the chest were performed and ten (38%) were interpreted as abnormal. Chest CT scans provided information about the extent of the injury but did not alter the initial management of any patient and therefore are rarely indicated in the acute evaluation of trauma patients. A total of 110 abdominopelvic CT scans were performed and 20 (19%) were interpreted as positive. Seventy-five percent of those patients with positive CT scans were treated successfully in a nonsurgical fashion.

An 86-year-old Japanese man presented with altered mental status (AMS) for several weeks and recent dyspnea and anorexia. He had been unwell for several weeks for an unknown reason, when 10 days before the presentation, he developed dyspnea, anorexia, and general malaise. In the late morning of the presentation day, when the patient saw his primary doctor on schedule, the doctor found him lethargic and referred him for further evaluation and treatment. The patient lived home with his wife. Per the patient's family and home-visit care worker, the patient had a cognitive decline over the last several weeks, and he became to make frequent phone calls for help because he “does not know what to do.” The patient is an older gentleman and therefore is at high vascular risk. Age-related cellular immunodeficiency and malignancy risks also need to be mentioned. This patient's main problem is AMS that progressed in several weeks and dyspnea that started sometime later. AMS in this patient is primarily of content dysfunction rather than arousal dysfunction. Hence, a widespread cortical involvement should be considered. Considering that dyspnea occurred in subacute AMS context involving diffuse cortical involvement, disorders with the respiratory control system stemming from central pathologies are concerned. I would list infectious or limbic encephalitis, Creutzfeldt-Jakob disease (CJD), and hypothalamic-pituitary-adrenal (HPA) axis dysregulation, type A subacute aortic dissection affecting the anterior circulatory system with subsequent cardiac tamponade or aortic insufficiency, primary lung cancer with the anterior lobe metastasis, and ischemia on the anterior lobe of the brain. On the other hand, I also argue systemic pathologies affecting the cardiopulmonary system, the hematologic system, in search of the causes of dyspnea. These pathologies encompass metabolic disorders causing brain function and cardiac dysfunction (uremia, hypothyroidism, and syndrome of inappropriate antidiuresis (SIAD) based on intrathoracic pathology), toxic drug effect affecting both of central nervous and of cardiopulmonary vasculature, subacute infiltrative etiologies affecting multiple organs such as syphilis, HIV, lymphoma, or tuberculosis, indolent infective endocarditis (IE) with subsequent valvular destruction and systemic embolization, cardiac myxoma, and pulmonary tumor thromboembolic microangiopathy (PTTM). Meanwhile, since the patient is older, one may consider Hickam's dictum, an aphorism referring that a patient's clinical presentation is caused by more than one pathology: That is, AMS and dyspnea would be derived from different causes, respectively. Multiple medical conditions cause AMS with predominant content abnormality. Many of them are critical and require urgent diagnosis and intervention. Checking basic metabolic panel for abnormal blood glucose, uremia, and electrolyte abnormalities is the first test as it is quick and simple to pick up the critical and treatable condition. Other treatable causes of AMS include hypothyroidism, adrenal insufficiency, central causes such as encephalopathy, encephalitis, epilepsy, subdural hematomas, and depression, and insidious infectious diseases such as syphilis, tuberculosis, and HIV, and brain metastasis of the malignant neoplasm. All these conditions were already mentioned above. The differential diagnoses of dyspnea alone in this patient include heart failure of any cause, pneumonia, pneumonitis, pulmonary embolism (arterial or venous), pneumothorax, pleural effusion of any cause, anemia of any cause, thoracic problems, neuromuscular diseases (paraneoplastic neuromuscular syndrome, phrenic nerve paralysis, and brainstem infarction), psychiatric conditions causing dyspnea (anxiety and panic disorders), or the compensation of metabolic acidosis. The patient's past medical history included chronic obstructive pulmonary disease (COPD) with an episode of acute exacerbation 9 months before, pulmonary tuberculosis, chronic hepatitis C, hypertension, constipation, and insomnia. He had not had any history of pet or animal contact. He had not been exposed to any inhalant antigen as far as the family knew. He did not undertake home oxygen therapy because he did not show hypoxemia when taking a rest. He spent most of his day sitting on his chair or lying down on his bed and seldom went out or walked up and downstairs. His regular medication included tiotropium (2.5 µg/puff) 2 puff/d, slow-release theophylline 400 mg/d, carbocisteine 1000 mg/d, verapamil 120 mg/d, magnesium oxide 660 mg/d, and zolpidem 10 mg/d. He seldom drank alcohol. He quitted smoking several days before. The patient had COPD, usually because of smoking. Smoking is a significant risk factor for vascular diseases and malignant neoplasms, raising the possibility of these patients’ pathologies. It is interesting to note that he quitted smoking several days before. I would like to know what made the patient quit smoking. If he could not smoke because of his cognitive impairment or dyspnea, the patient's condition may indicate a severe condition. Malignancy-related conditions and tuberculosis are of great concern. Paraneoplastic syndrome, lymphomas, lung or brain tumors, and PTTM should be ruled out. His tuberculosis history raises concerns about the reactivation of tuberculosis in the context of immunosuppression, causing dyspnea (pulmonary tuberculosis) and cognitive impairment (tuberculosis meningoencephalitis). In such an immobile patient with vascular risks, pulmonary embolism should be considered until proven otherwise. The patient also had a recent episode of acute COPD exacerbation. This medical history increased the possibility that the patient developed COPD exacerbation again. Triggers of COPD exacerbation include pneumonia and other infections, heart failure with or without acute coronary syndrome, pulmonary embolism, asthma, smoking, environmental factors, and drug nonadherence. However, there was no clinical information so far indicating preceding pneumonia, heart failure, pulmonary embolism, asthma, or substance inhalation before the development of dyspnea. Patients with COPD are vulnerable to hypercapnic narcosis resulting in a stupor, but it usually occurs in patients on oxygen therapy. Considering the patient's age and progressive cognitive decline, medication noncompliance may have been possible. If he recently forgot to inhale the powders or take medicines for COPD, he might develop dyspnea. If the patient failed to take verapamil for hypertension because of the cognitive decline, this might develop dyspnea from hypertensive heart failure. The patient may also be at risk of medication overuse because of cognitive decline. He was on theophylline, which is notorious for its potential toxicity. Theophylline poisoning in cognitively impaired older people is well known and common. It is also known that quitting smoking may elevate the theophylline concentration, sometimes leading to intoxication. The poisoning symptoms become severe and prolonged, especially with a single large dose or use of extended-release agents. Adverse symptoms are diverse, affecting cardiac, pulmonary, metabolic, hematopoietic, and neuropsychiatric systems. Magnesium oxide may cause AMS due to hypermagnesemia, especially when a patient has chronic kidney disease. Zolpidem may also cause hypersomnolence. If the cognitive decline itself was due to medication poisoning, it is essential to check the prescription history. Besides, detailed history of the patient's current volume status is also necessary because medication intoxication is caused by elevated blood levels complicated by acute volume depletion, whatever the drug is. The patient had chronic hepatitis C. If the patient's hepatitis developed into cirrhosis, hepatic encephalopathy with hepatopulmonary syndrome should be considered. The patient had constipation, one of the most common triggers of developing an elevation of ammonia. Cirrhosis is sometimes overlooked and underdiagnosed because it often lacks specific symptoms until uncompensated. Astute physicians may notice some characteristic physical signs, including palmar erythema, gynecomastia, spider angiomata, splenomegaly, nail and finger change (Muehrcke's nail, Terry's nail, clubbed finger, and hypertrophic osteoarthropathy), and testicular atrophy. His hypertension raises concerns about heart failure and aortic disorders (aortic dissection), which sometimes impair brain circulation, resulting in cognitive impairment in a subacute or chronic case. His constipation and insomnia might be from autonomic, metabolic, or endocrine dysregulation, including hypothyroidism, uremia, HPA axis dysfunction, or electrolyte disorders. The aforementioned other possibilities, including indolent IE, limbic encephalitis, CJD, presence of anemia, other intrathoracic pathologies, and neuropsychiatric disorders, should still be on the list. On physical examination, the patient looked emaciated and lethargic with a Glasgow Coma Scale of 12 (E3, V4, M5). His body temperature was 37.0℃, blood pressure 128/70 mm Hg, pulse rate 88 bpm and regular, respiratory rate 28/min, and oxygen saturation 96% while breathing ambient air. There was no conjunctival pallor or icterus. Respiratory sounds were diffusely diminished, and fine crackles were heard on the upper chest bilaterally. No wheezes were heard. The intercostal space moved inwardly during inspiration. Heart sounds were normal without murmurs, rubs, and gallops. His abdomen was flat and soft, and there was no hepatosplenomegaly. His legs were not swollen without clubbing and cyanosis. The patient did not obey simple commands because of AMS. Pupillary light reflex was normal. Deep tendon reflexes were normal. Pathological reflexes, including Babinski's reflex, Hoffmann's sign, and Trömner's reflex, were not seen. There was no asterixis. Any apparent paralysis was not seen. There was no rigidity, coarse tremor, dystonia, or myoclonus. On examination, the patient also had problems with arousal in addition to the problem of the contents. However, the differential listed so far does not change significantly at this moment. The patient's oxygen saturation seemed not too low despite his COPD. Tachypnea was the most prominent finding among his vital signs. The combination of seemingly normal oxygen saturation and tachypnea yields some clinical hypotheses. First, the patient may develop respiratory failure, and increasing respiratory rates may conceal hypoxemia due to pulmonary diseases (pneumonia and pneumonitis), pleural diseases (pleuritis, pneumothorax, and pleural effusion), or pulmonary vasculature disorders (pulmonary embolism and PTTM). Second, there may exist some extra-pulmonary conditions causing tachypnea, including metabolic acidosis encompassing sepsis, uremia, drug intoxication, thoracic cage restriction due to pleural effusion, neuromuscular dysfunction, or pleurisy. Third, carbon monoxide intoxication may develop dyspnea with normal oxygen saturation. The most notable finding on examination is lung sounds. Considering that the breath sounds were attenuated in almost all lung fields and crackles can be heard in both upper lung fields, there are several possibilities. First, it is reasonable to assume that most alveoli have been replaced by the liquid, except for a few alveoli in both upper lungs. The second likely interpretation is a situation in which both lung spaces are replaced by pleural fluid, and only the lungs of both upper lungs are functioning. Another possibility is that most of both lungs have emphysematous changes, and only both upper lungs are audible. Percussion is useful to differentiate whether the decreased breath sounds are due to liquid or air and should be performed after that. Chest retraction signs in this patient showed respiratory distress. Heart sounds are normal, and therefore, it indicates that heart failure was less likely. There was no edema in the extremities, so elevated hydrostatic pressure (heart failure and volume overload) and findings of hypoproteinemia (cirrhosis, nephrosis, and cachexia) are not strongly suspected. Considering if massive pleural effusion exists in both lungs without anasarca, diseases limited to lung or pleura causing massive pleural effusion should be considered, such as tuberculosis, fungal infection, lymphoma, pleuritic malignancies, and chylothorax due to malignancy. If pleural effusion exists, thoracocentesis should be performed to examine the fluid. A computed tomography (CT) scan also clarifies the existence of mass lesions, pleural involvement, and other intrathoracic disorders, which are still not ruled out. Intravenous contrast CT will uncover vascular disorders, including pulmonary and aortic vessels, which are still concerning. Infective endocarditis should not be ruled out even without a heart murmur. Blood culture should be at least obtained. An echocardiogram is a good test of choice because this test elucidates valvular vegetation and regurgitation, pericardiac effusion, and sometimes dissecting flap in the aortic vessel. Lacking in focal neurological findings lowers the likelihood of developing focal cerebral damages, including cerebral infarction and hemorrhage except for the frontal lobe involvement. Encephalitis and encephalopathy still should not be ruled out. Lumbar puncture should be performed if no other etiologies are explaining declined cognitive function. There seemed to be no evidence of anemia that would cause dyspnea. Since there was no jaundice appreciated, severe diseases of the hepatobiliary system were unlikely. Blood tests should rule out HPA axis dysfunction, hypothyroidism, and electrolyte dysfunctions. Adverse drug reactions are still concerning. Verapamil noncompliance is less likely because of his normal blood pressure. Laboratory data (Table 1) revealed the white blood cell count of 9090/µL, hemoglobin level of 12.8 g/dL, platelet level of 31.8 × 104/µL, serum creatinine level of 0.69 mg/dL, blood urea nitrogen level of 30.8 mg/dL, serum sodium level of 134 mEq/L, serum potassium level of 2.7 mEq/L, serum chloride level of 94 mEq/L, blood glucose level of 267 mg/dL, and serum D-dimer level of 3.1 µg/mL (normal range, 0-1.0 µg/mL). Aspartate aminotransferase level, alanine aminotransferase level, lactate dehydrogenase level, γ-glutamyl transpeptidase level, creatinine kinase level, C-reactive protein level, plasma ammonia level, and hemoglobin A1c level were within normal ranges. Arterial blood gas analysis data revealed a pH of 7.56, PaCO2 of 35.1 Torr, PaO2 of 110 Torr, and HCO3 of 31.5 mEq/L on ambient air. On urinalysis, neither pyuria nor bacteriuria was not seen. The electrocardiogram revealed a prolonged QT interval (QTc interval: 0.468 ms). Any arrhythmia was not seen. A chest CT scan showed emphysematous changes at the whole lung with reticular marking and bilateral slight pleural effusions, both of which had already been detected before. A head CT scan only showed mild atrophy of the frontal lobes. Transthoracic echocardiography revealed no abnormal findings. Laboratory results showed low hemoglobin, normal kidney function, and normal liver enzyme, suggesting that the patient had no anemia, uremia, or hepatic encephalopathy. His blood glucose was high, but not high enough to explain the overall abnormality. The patient had no history of diabetes. If blood glucose rises despite the absence of diabetes, the common causes are acute physical stress and drug-induced hyperglycemia with or without beta-receptor stimulation. In the present case, it is not difficult to imagine that the patient is under acute stress, but as another possibility, theophylline's side effect should be investigated. Electrolytes were normal except for low potassium. Serum magnesium level was not obtained, it should have been obtained though. Hypokalemia causes intake loss, excessive loss from the gastrointestinal tract or urine, or intracellular shift. Checking urine potassium is the first step to determine the cause. Considering the patient's history, intake loss and elevated beta-adrenergic activity with theophylline can be suspected. The high D-dimer indicates intravascular thrombus formation, suggesting intravascular or systemic inflammation. His head CT scan was negative for hematoma or old stroke. There was an evidence of frontal lobe atrophy, which might have contributed to his cognitive decline. His chest CT revealed that the bilaterally diminished lung sounds were from emphysema, so the discussion of pleural effusion should be abandoned. At this point, there were no cytopenia, no abnormal lactate dehydrogenase level, little evidence of inflammation, and no explicit findings on imaging, making infiltrative diseases (lymphoma and tuberculosis) less likely. Other malignancies could not be ruled out completely, but there were no suggestive clinical findings. His blood gas analysis unexpectedly showed metabolic alkalosis as the main component, probably from hypokalemia. There was concomitant respiratory alkalosis, which was probably due to tachypnea. The information I would need to know at this point includes history information suggesting psychiatric disorders, and history of medication compliance. I would suggest to add blood tests for thyroid function, cortisol, corticotropin, theophylline level, and blood culture. If these investigations do not reveal the cause, lumbar puncture and contrast-enhanced magnetic resonance imaging were performed for detecting intracranial lesions that cannot be detected by noncontrast head CT. Besides, a whole-body contrast-enhanced CT with or without 18F-fluorodeoxyglucose positron emission tomography for neoplastic lesions or intravascular lesions may be considered. Based on his symptoms, data, and a history of taking theophylline, he was tentatively diagnosed with theophylline intoxication. Two sets of blood cultures were obtained to rule out bacteremia. The patient did not develop seizures or significant electrocardiography changes, and administration of activated charcoal or hemodialysis was not performed. Fluid repletion with potassium was initiated, and theophylline intake was discontinued. The patient was admitted for further evaluation and treatment. Additional diagnostic tests were planned to perform if the patient's AMS did not improve even on the next day. The patient's constellation of symptoms including general malaise, loss of appetite, cognitive decline, tachypnea with acute respiratory alkalosis, hypokalemia, and hyperglycemia was attributed to theophylline intoxication, possibly triggered by recent quitting of smoking. Declining cognitive impairment might also have accelerated to worsen the medication misusage, resulting in the poisoning. For the management of theophylline intoxication, the strategy of lowering the circulating concentration of theophylline includes gastrointestinal decontamination (an administration of activated charcoal 1 g/kg by mouth or nasogastric tube) and hemodialysis. Most intoxicated patients are, however, successfully managed with supportive care. The patient should be kept in close monitoring for at least 2 days because the half-time of slow-release theophylline is about 15 hours in healthy young adults. On the second day in the hospital, serum theophylline level showed 44.2 µg/mL (reference range, 5.0-15.0 µg/mL). This level was high enough to develop various symptoms due to theophylline toxicity. Bacterial culture turned out to be negative. On the third day, the patient's mental status and respiratory rates turned utterly normal, and he did not complain of dyspnea or general malaise. His cognitive decline was also improved. An electrocardiogram revealed a normal QT interval. The patient was undertaken in-hospital rehabilitation. On day 29, the patient was discharged to the nursing home, where nursing staff helped him inhale a long-acting beta-agonist plus long-acting muscarinic antagonist. The chronology of this case is as follows. Several weeks before, chronic mild intoxication caused cognitive decline and feeling unwell. Ten days before, dyspnea and anorexia were developed and the patient quitted smoking, which unfortunately increased theophylline concentration to over 40 µg/mL. In the subsequent few days, acute exacerbation on chronic intoxication occurred and AMS was developed. This time course is also supported by the findings of hypokalemia, hyperglycemia, and respiratory alkalosis, which were more typical in acute theophylline poisoning rather than chronic. This case illustrates an older patient with AMS, tachypnea without hypoxemia, hypokalemia, and hyperglycemia. These findings turned out to be a manifestation of theophylline intoxication. The patient's cognitive decline was improved after stopping theophylline intake. In most of the healthcare facilities, it takes several times to turn out serum theophylline concentration. Suspecting theophylline intoxication based on history taking and nonspecific systemic abnormalities is therefore important. Dyspnea is “the result of a complex interaction of physiological, psychosocial, social, and environmental factors.”1 In this case, dyspnea was probably caused by multiple factors, including tachypnea due to theophylline intoxication, AMS, and other psychological disturbance due to intoxication, baseline COPD condition, and growing anxiety of the patient and his wife. Theophylline was formerly used for asthma and COPD because it antagonizes adenosine receptors and functions as a bronchodilator. Its various side effects lie in the wide distribution of adenosine receptors throughout the body.2 Besides, theophylline also activates catecholamine release indirectly.2 Because of its side effects and a broad acceptance of inhaled beta-agonist and muscarinic antagonist, theophylline now plays a minimal role in treating asthma3 or COPD.4 However, theophylline is still widely used to treat asthma and COPD, especially in developing countries.5 Japan is another country in which theophylline is widely prescribed. One study revealed that about 15% of patients with asthma were The concentration of theophylline for asthma or COPD from 10 to µg/mL. theophylline has a and poisoning symptoms or signs may develop at the serum concentration of µg/mL. It is that serum of µg/mL in acute and µg/mL in chronic are with Theophylline concentration may by various factors, one of which is smoking. Theophylline is a hepatic smoke of smoking and theophylline as in this case. should know theophylline intoxication presentation and even if do not this drug Theophylline is a drug that is in like a Adverse drug is common in older and physicians should conditions in when older of and to to is one of the various for drug and these may be useful in clinical in older that theophylline as for COPD should not be If the patient had a medication this drug might have been In this case First, physicians should drug reactions when older patients taking multiple taking any inappropriate or dysfunction. should be that are to especially older of and of Second, as theophylline intoxication syndrome symptoms, patients taking theophylline with any should be at least of developing the intoxication. In tachypnea without hypoxemia and slight AMS may be overlooked physicians do not theophylline in history information is also because smoking may to theophylline poisoning. Third, theophylline should not be used in older Theophylline is now not strongly for patients with asthma or COPD. theophylline for some should the concentration and close to drug interaction including The for about clinical course and The have that there are no of in with this

Introduction:A seemingly large percentage of geriatric patients with isolated low-energy femur fractures undergo a head computed tomography (CT) scans during initial work up in the emergency department. This study aimed to evaluate the pertinent clinical variables that are associated with positive CT findings with the objective to decrease the number of unnecessary CT scans performed.Methods:A retrospective review performed at a level II trauma center including 713 patients over the age of 65 sustaining a femur fracture following a low-energy fall. The main outcome measure was pertinent clinical variables that are associated with CT scans that yielded positive findings.Results:A total of 713 patients over the age of 65 were included, with a low-energy fall, of which 76.2% (543/713) underwent a head CT scan as part of their evaluation. The most common presenting symptom reported was the patient hitting their head, 13% (93/713), and 1.8% (13/713) were unsure if they had hit their head. Of those evaluated with a head CT scan, only 3 (0.4%) had acute findings and none required acute neurosurgical intervention. All three patients with acute changes on the head CT scan had an Injury Severity Score (ISS) greater than 9, Glasgow Coma Scale (GCS) less than 15, and evidence of trauma above the clavicles.Discussion:None of the patients with a traumatic injury required a neurosurgical intervention after sustaining a low-energy fall (0/713).Conclusion:Head CT scans should have a limited role in the workup of this patient population and should be reserved for patients with a history and physical exam findings that support head trauma, an ISS > 9 and GCS < 15.

Findings of computed tomography in stage IIB and IIC melanoma: A six-year retrospective study in the South-East of Scotland

Matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has recently become a useful analytical approach for microbial identification. The presence and absence of specific peaks on MS spectra are commonly used to identify the bacterial species and predict antibiotic-resistant strains. However, the conventional approach using few single peaks would result in insufficient prediction power without using complete information of whole MS spectra. In the past few years, machine learning algorithms have been successfully applied to analyze the MALDI-TOF MS peaks pattern for rapid strain typing. In this study, we developed a convolutional neural network (CNN) method to deal with the complete information of MALDI-TOF MS spectra for detecting Enterococcus faecium, which is one of the leading pathogens in the world. We developed a CNN model to rapidly and accurately predict vancomycin-resistant Enterococcus faecium (VREfm) samples from the whole mass spectra profiles of clinical samples. The CNN models demonstrated good classification performances with the average area under the receiver operating characteristic curve (AUROC) of 0.887 when using external validation data independently. Additionally, we employed the score-class activation mapping (CAM) method to identify the important features of our CNN models and found some discriminative signals that can substantially contribute to detecting the ion of resistance. This study not only utilized the complete information of MALTI-TOF MS data directly but also provided a practical means for rapid detection of VREfm using a deep learning algorithm.

Chronic kidney disease (CKD) is a progressive loss in kidney function. Early detection of patients who will progress to late-stage CKD is of paramount importance for patient care. To address this, we develop a pipeline to process longitudinal electronic heath records (EHRs) and construct recurrent neural network (RNN) models to predict CKD progression from stages II/III to stages IV/V. The RNN model generates predictions based on time-series records of patients, including repeated lab tests and other clinical variables. Our investigation reveals that using a single variable, the recorded estimated glomerular filtration rate (eGFR) over time, the RNN model achieves an average area under the receiver operating characteristic curve (AUROC) of 0.957 for predicting future CKD progression. When additional clinical variables, such as demographics, vital information, lab test results, and health behaviors, are incorporated, the average AUROC increases to 0.967. In both scenarios, the standard deviation of the AUROC across cross-validation trials is less than 0.01, indicating a stable and high prediction accuracy. Our analysis results demonstrate the proposed RNN model outperforms existing standard approaches, including static and dynamic Cox proportional hazards models, random forest, and LightGBM. The utilization of the RNN model and the time-series data of previous eGFR measurements underscores its potential as a straightforward and effective tool for assessing the clinical risk of CKD patients concerning their disease progression.

Metastatic disease is detected infrequently by computed tomography (CT) in early stage melanoma. The diagnostic yield of routine CT for stage III melanoma is less established, despite extensive use in clinical practice. Charts from 347 asymptomatic patients with stage III melanoma were reviewed. Findings suggestive of metastatic melanoma identified by head or body CT, chest radiography, bone scan, or liver function studies were confirmed histologically or by progression of disease. Individual CT scans identified 33/788 (4.2%) instances of metastatic melanoma, with 66/788 (8.4%) false positive studies. No metastases were identified among 104 head CT scans. Chest CT had the highest yield in patients with cervical adenopathy (7/35, 20%), and the lowest yield with groin adenopathy (1/50, 2%). Pelvic CT diagnosed metastases in 7/94 (7.4%) patients with groin adenopathy, but no patients with palpable axillary (n = 76) or cervical (n = 21) nodes. Metastatic melanoma was diagnosed in 11/136 (8.1%) patients having complete body CT imaging (chest, abdomen, and pelvis), including six patients (4.4%) identified by CT alone. Routine CT in patients with clinical stage III melanoma infrequently identifies metastatic disease. Head CT in the asymptomatic patient, chest CT in patients with groin adenopathy, and pelvic CT in the presence of axillary or cervical adenopathy are not indicated. Selective use of chest CT in patients with cervical adenopathy or pelvic CT in the presence of groin disease may be useful.