Lung Ultrasound Findings in Patients With Coronavirus Disease (COVID-19). AJR Am J Roentgenol. 2021;216:80-84. [PMID: 32755198 DOI: 10.2214/ajr.20.23513]

A survey of machine learning-based methods for COVID-19 medical image analysis

The ongoing COVID-19 pandemic caused by the SARS-CoV-2 virus has already resulted in 6.6 million deaths with more than 637 million people infected after only 30 months since the first occurrences of the disease in December 2019. Hence, rapid and accurate detection and diagnosis of the disease is the first priority all over the world. Researchers have been working on various methods for COVID-19 detection and as the disease infects lungs, lung image analysis has become a popular research area for detecting the presence of the disease. Medical images from chest X-rays (CXR), computed tomography (CT) images, and lung ultrasound images have been used by automated image analysis systems in artificial intelligence (AI)- and machine learning (ML)-based approaches. Various existing and novel ML, deep learning (DL), transfer learning (TL), and hybrid models have been applied for detecting and classifying COVID-19, segmentation of infected regions, assessing the severity, and tracking patient progress from medical images of COVID-19 patients. In this paper, a comprehensive review of some recent approaches on COVID-19-based image analyses is provided surveying the contributions of existing research efforts, the available image datasets, and the performance metrics used in recent works. The challenges and future research scopes to address the progress of the fight against COVID-19 from the AI perspective are also discussed. The main objective of this paper is therefore to provide a summary of the research works done in COVID detection and analysis from medical image datasets using ML, DL, and TL models by analyzing their novelty and efficiency while mentioning other COVID-19-based review/survey researches to deliver a brief overview on the maximum amount of information on COVID-19-based existing researches.

Application of Machine Learning and Deep Learning Techniques for COVID-19 Screening Using Radiological Imaging: A Comprehensive Review

Lung, being one of the most important organs in human body, is often affected by various SARS diseases, among which COVID-19 has been found to be the most fatal disease in recent times. In fact, SARS-COVID 19 led to pandemic that spreads fast among the community causing respiratory problems. Under such situation, radiological imaging-based screening [mostly chest X-ray and computer tomography (CT) modalities] has been performed for rapid screening of the disease as it is a non-invasive approach. Due to scarcity of physician/chest specialist/expert doctors, technology-enabled disease screening techniques have been developed by several researchers with the help of artificial intelligence and machine learning (AI/ML). It can be remarkably observed that the researchers have introduced several AI/ML/DL (deep learning) algorithms for computer-assisted detection of COVID-19 using chest X-ray and CT images. In this paper, a comprehensive review has been conducted to summarize the works related to applications of AI/ML/DL for diagnostic prediction of COVID-19, mainly using X-ray and CT images. Following the PRISMA guidelines, total 265 articles have been selected out of 1715 published articles till the third quarter of 2021. Furthermore, this review summarizes and compares varieties of ML/DL techniques, various datasets, and their results using X-ray and CT imaging. A detailed discussion has been made on the novelty of the published works, along with advantages and limitations.

A novel approach for COVID-19 Infection forecasting based on multi-source deep transfer learning

COVID-19 is a contagious disease; so, predicting its future infections in a provincial region requires the consideration of the related data (i.e., rates of infection, mortality and recovery, etc.) over a period of time. Clearly, the COVID-19 data of a particular provincial region can be easily modelled as a time-series. However, predicting the future COVID-19 infections in a particular region is quite challenging when the availability of COVID-19 dataset of the province is of little quantity. Accordingly, ML models when deployed for such tasks usually results in low infection prediction accuracy. To overcome such issues of low variance and high bias in a model due to data scarcity, multi-source transfer learning (MSTL) along with deep learning may be quite useful and effective. Therefore, this paper proposes a novel technique based on multi-source deep transfer learning (MSDTL) to efficiently forecast the future COVID-19 infections in the provinces with insufficient COVID-19 data. The proposed approach is a novel contribution as it considers the fact that future COVID-19 transmission in a region also depends on its population density and economic conditions (GDP) for accurate forecasting of the infections to tackle the pandemic efficiently. The importance of this feature selection is experimentally proved in this paper. Our proposed approach employs the well-known recurrent neural network architecture, the Long-short term memory (LSTM), a popular deep-learning model for history-dependent tasks. A comparative analysis has been performed with existing state-of-art algorithms to portray the efficiency of LSTM. Thus, formation of MSDTL approach enhances the predictive precision capability of the LSTM. We evaluate the proposed methodology over the COVID-19 dataset from sixty-two provinces belonging to different nations. We then empirically evaluate the performance of the proposed approach using two different evaluation metrics, viz. The mean absolute percentage error and the coefficient of determination. We show that our proposed MSDTL based approach is better in terms of the accuracy of the future infection prediction, and produces improvements up to 96% over its without-TL counterpart.

Design and calibration of a Tonpilz transducer for low frequency medical ultrasound tomography

The design and performance of a transducer for low frequency ultrasound tomography is presented, motivated by recent research demonstrating that acoustic waves transmitting at frequencies between 10 kHz and 750 kHz penetrate the lungs and may be useful for thoracic imaging. An adaptation of the traditional Tonpilz design was developed, vibrational amplitude and electrical impedance were measured, and an optimal frequency was determined. The design is found to meet the desired mechanical, electrical, and safety specifications. Thus, it was considered a promising option for the target application of pulmonary imaging with ultrasound computed tomography between 50 and 200 kHz; highest efficiency achieved around 125 kHz and 156 kHz, and beam divergence of 40°.

From the Triage to the Intermediate Area: A Simple and Fast Model for COVID-19 in the Emergency Department

Introduction: The early identification of patients with SARS-CoV-2 infection is still a real challenge for emergency departments (ED). First, we aimed to develop a score, based on the use of the lung ultrasonography (LUS), in addition to the pre-triage interview, to correctly address patients; second, we aimed to prove the usefulness of a three-path organization (COVID-19, not-COVID-19 and intermediate) compared to a two-path organization (COVID-19, non-COVID-19). Methods: We retrospectively analysed 292 patients admitted to our ED from 10 April to 15 April 2020, with a definite diagnosis of positivity (93 COVID-19 patients) or negativity (179 not-COVID-19 patients) for SARS-COV-2 infection. Using a logistic regression, we found a set of predictors for infection selected from the pre-triage interview items and the LUS findings, which contribute with a different weight to the final score. Then, we compared the organization of two different pathways. Results: The most informative factors for classifying the patient are known nasopharyngeal swab positivity, close contact with a COVID-19 patient, fever associated with respiratory symptoms, respiratory failure, anosmia or dysgeusia, and the ultrasound criteria of diffuse alveolar interstitial syndrome, absence of B-lines and presence of pleural effusion. Their sensitivity, specificity, accuracy, and AUC-ROC are, respectively, 0.83, 0.81, 0.82 and 0.81. The most significant difference between the two pathways is the percentage of not-COVID-19 patients assigned to the COVID-19 area, that is, 10.6% (19/179) in the three-path organization, and 18.9% (34/179) in the two-path organization (p = 0.037). Conclusions: Our study suggests the possibility to use a score based on the pre-triage interview and the LUS findings to correctly manage the patients admitted to the ED, and the importance of an intermediate area to limit the spread of SARS-CoV-2 in the ED and, as a consequence, in the hospital.

Review of Machine Learning in Lung Ultrasound in COVID-19 Pandemic

Ultrasound imaging of the lung has played an important role in managing patients with COVID-19-associated pneumonia and acute respiratory distress syndrome (ARDS). During the COVID-19 pandemic, lung ultrasound (LUS) or point-of-care ultrasound (POCUS) has been a popular diagnostic tool due to its unique imaging capability and logistical advantages over chest X-ray and CT. Pneumonia/ARDS is associated with the sonographic appearances of pleural line irregularities and B-line artefacts, which are caused by interstitial thickening and inflammation, and increase in number with severity. Artificial intelligence (AI), particularly machine learning, is increasingly used as a critical tool that assists clinicians in LUS image reading and COVID-19 decision making. We conducted a systematic review from academic databases (PubMed and Google Scholar) and preprints on arXiv or TechRxiv of the state-of-the-art machine learning technologies for LUS images in COVID-19 diagnosis. Openly accessible LUS datasets are listed. Various machine learning architectures have been employed to evaluate LUS and showed high performance. This paper will summarize the current development of AI for COVID-19 management and the outlook for emerging trends of combining AI-based LUS with robotics, telehealth, and other techniques.

Ultrasound findings of lung ultrasonography in COVID-19: A systematic review

PURPOSE

To identify the defining lung ultrasound (LUS) findings of COVID-19, and establish its association to the initial severity of the disease and prognostic outcomes.

METHOD

Systematic review was conducted according to the PRISMA guidelines. We queried PubMed, Embase, Web of Science, Cochrane Database and Scopus using the terms ((coronavirus) OR (covid-19) OR (sars AND cov AND 2) OR (2019-nCoV)) AND (("lung ultrasound") OR (LUS)), from 31st of December 2019 to 31st of January 2021. PCR-confirmed cases of SARS-CoV-2 infection, obtained from original studies with at least 10 participants 18 years old or older, were included. Risk of bias and applicability was evaluated with QUADAS-2.

RESULTS

We found 1333 articles, from which 66 articles were included, with a pooled population of 4687 patients. The most examined findings were at least 3 B-lines, confluent B-lines, subpleural consolidation, pleural effusion and bilateral or unilateral distribution. B-lines, its confluent presentation and pleural abnormalities are the most frequent findings. LUS score was higher in intensive care unit (ICU) patients and emergency department (ED), and it was associated with a higher risk of developing unfavorable outcomes (death, ICU admission or need for mechanical ventilation). LUS findings and/or the LUS score had a good negative predictive value in the diagnosis of COVID-19 compared to RT-PCR.

CONCLUSIONS

The most frequent ultrasound findings of COVID-19 are B-lines and pleural abnormalities. High LUS score is associated with developing unfavorable outcomes. The inclusion of pleural effusion in the LUS score and the standardisation of the imaging protocol in COVID-19 LUS remains to be defined.

Acute management of COVID-19 in the emergency department: An evidence-based review

Coronavirus disease (COVID-19) has been relentlessly battering the world wave after wave in different countries at different rates and times. Emergency departments (EDs) around the globe have had to constantly adapt to this ever-changing influx of information and recommendations by various national and international health agencies. This review compiles the available evidence on the guidelines for triaging, evaluation, and management of critically ill patients with COVID-19 presenting to the ED and in need of emergency resuscitation. The quintessential components of resuscitation focus on airway, breathing, and circulation with good supportive care as the cornerstone of acute management of critically ill COVID-19 patients. Irrational investigations and therapeutics must be avoided during these times of medical uncertainty and antibiotic stewardship should be diligently followed.

Lung Ultrasound Findings in Patients Hospitalized With COVID-19

OBJECTIVES

Lung ultrasound (LUS) can accurately diagnose several pulmonary diseases, including pneumothorax, effusion, and pneumonia. LUS may be useful in the diagnosis and management of COVID-19.

METHODS

This study was conducted at two United States hospitals from 3/21/2020 to 6/01/2020. Our inclusion criteria included hospitalized adults with COVID-19 (based on symptomatology and a confirmatory RT-PCR for SARS-CoV-2) who received a LUS. Providers used a 12-zone LUS scanning protocol. The images were interpreted by the researchers based on a pre-developed consensus document. Patients were stratified by clinical deterioration (defined as either ICU admission, invasive mechanical ventilation, or death within 28 days from the initial symptom onset) and time from symptom onset to their scan.

RESULTS

N = 22 patients (N = 36 scans) were included. Eleven (50%) patients experienced clinical deterioration. Among N = 36 scans, only 3 (8%) were classified as normal. The remaining scans demonstrated B-lines (89%), consolidations (56%), pleural thickening (47%), and pleural effusion (11%). Scans from patients with clinical deterioration demonstrated higher percentages of bilateral consolidations (50 versus 15%; P = .033), anterior consolidations (47 versus 11%; P = .047), lateral consolidations (71 versus 29%; P = .030), pleural thickening (69 versus 30%; P = .045), but not B-lines (100 versus 80%; P = .11). Abnormal findings had similar prevalences between scans collected 0-6 days and 14-28 days from symptom onset.

DISCUSSION

Certain LUS findings may be common in hospitalized COVID-19 patients, especially for those that experience clinical deterioration. These findings may occur anytime throughout the first 28 days of illness. Future efforts should investigate the predictive utility of these findings on clinical outcomes.

Lung Ultrasound for Identification of Patients Requiring Invasive Mechanical Ventilation in COVID-19

OBJECTIVES

Indication for invasive mechanical ventilation in COVID-19 pneumonia has been a major challenge. This study aimed to evaluate if lung ultrasound (LUS) can assist identification of requirement of invasive mechanical ventilation in moderate to severe COVID-19 pneumonia.

MATERIALS AND METHODS

Between April 23 and November 12, 2020, hospitalized patients with moderate to severe COVID-19 (oxygen demand ≥4 L/min) were included consecutively. Lung ultrasound was performed daily until invasive mechanical ventilation (IMV-group) or spontaneous recovery (non-IMV-group). Clinical parameters and lung ultrasound findings were compared between groups, at intubation (IMV-group) and highest oxygen demand (non-IMV-group). A reference group with oxygen demand <4 L/min was examined at hospital admission.

RESULTS

Altogether 72 patients were included: 50 study patients (IMV-group, n = 23; non-IMV-group, n = 27) and 22 reference patients. LUS-score correlated to oxygen demand (SpO₂ /FiO₂ -ratio) (r = 0.728; p < .0001) and was higher in the IMV-group compared to the non-IMV-group (20.0 versus 18.0; p = .026). Based on receiver operating characteristic analysis, a LUS-score of 19.5 was identified as cut-off for requirement of invasive mechanical ventilation (area under the curve 0.68; sensitivity 56%, specificity 74%). In 6 patients, LUS identified critical coexisting conditions. Respiratory rate and oxygenation index ((SpO₂ /FiO₂ )/respiratory rate) ≥4.88 identified no requirement of invasive mechanical ventilation with a positive predictive value of 87% and negative predictive value of 100%.

CONCLUSIONS

LUS-score had only a moderate diagnostic value for requirement of invasive mechanical ventilation in moderate to severe COVID-19. However, LUS proved valuable as complement to respiratory parameters in guidance of disease severity and identifying critical coexisting conditions.

Management of COVID-19 Patients in the Emergency Department

COVID-19 is an emerging disease of global public health concern. As the pandemic overwhelmed emergency departments (EDs), a restructuring of emergency care delivery became necessary in many hospitals. Furthermore, with more than 2000 papers being published each week, keeping up with ever-changing information has proven to be difficult for emergency physicians. The aim of the present review is to provide emergency physician with a summary of the current literature regarding the management of COVID-19 patients in the emergency department.

Canadian Internal Medicine Ultrasound (CIMUS) Expert Consensus Statement on the Use of Lung Ultrasound for the Assessment of Medical Inpatients With Known or Suspected Coronavirus Disease 2019

OBJECTIVES

To develop a consensus statement on the use of lung ultrasound (LUS) in the assessment of symptomatic general medical inpatients with known or suspected coronavirus disease 2019 (COVID-19).

METHODS

Our LUS expert panel consisted of 14 multidisciplinary international experts. Experts voted in 3 rounds on the strength of 26 recommendations as "strong," "weak," or "do not recommend." For recommendations that reached consensus for do not recommend, a fourth round was conducted to determine the strength of those recommendations, with 2 additional recommendations considered.

RESULTS

Of the 26 recommendations, experts reached consensus on 6 in the first round, 13 in the second, and 7 in the third. Four recommendations were removed because of redundancy. In the fourth round, experts considered 4 recommendations that reached consensus for do not recommend and 2 additional scenarios; consensus was reached for 4 of these. Our final recommendations consist of 24 consensus statements; for 2 of these, the strength of the recommendations did not reach consensus.

CONCLUSIONS

In symptomatic medical inpatients with known or suspected COVID-19, we recommend the use of LUS to: (1) support the diagnosis of pneumonitis but not diagnose COVID-19, (2) rule out concerning ultrasound features, (3) monitor patients with a change in the clinical status, and (4) avoid unnecessary additional imaging for patients whose pretest probability of an alternative or superimposed diagnosis is low. We do not recommend the use of LUS to guide admission and discharge decisions. We do not recommend routine serial LUS in patients without a change in their clinical condition.

Prevalence and significance of pulmonary disease on lung ultrasonography in outpatients with SARS-CoV-2 infection

BACKGROUND

The majority of patients with SARS-CoV-2 infection are diagnosed and managed as outpatients; however, little is known about the burden of pulmonary disease in this setting. Lung ultrasound (LUS) is a convenient tool for detection of COVID-19 pneumonia. Identifying SARS-CoV-2 infected outpatients with pulmonary disease may be important for early risk stratification.

OBJECTIVES

To investigate the prevalence, natural history and clinical significance of pulmonary disease in outpatients with SARS-CoV-2.

METHODS

SARS-CoV-2 PCR positive outpatients (CV(+)) were assessed with LUS to identify the presence of interstitial pneumonia. Studies were considered positive based on the presence of B-lines, pleural irregularity and consolidations. A subset of patients underwent longitudinal examinations. Correlations between LUS findings and patient symptoms, demographics, comorbidities and clinical outcomes over 8 weeks were evaluated.

RESULTS

102 CV(+) patients underwent LUS with 42 (41%) demonstrating pulmonary involvement. Baseline LUS severity scores correlated with shortness of breath on multivariate analysis. Of the CV(+) patients followed longitudinally, a majority showed improvement or resolution in LUS findings after 1-2 weeks. Only one patient in the CV(+) cohort was briefly hospitalised, and no patient died or required mechanical ventilation.

CONCLUSION

We found a high prevalence of LUS findings in outpatients with SARS-CoV-2 infection. Given the pervasiveness of pulmonary disease across a broad spectrum of LUS severity scores and lack of adverse outcomes, our findings suggest that LUS may not be a useful as a risk stratification tool in SARS-CoV-2 in the general outpatient population.

Medical imaging and computational image analysis in COVID-19 diagnosis: A review

Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus. The disease presents with symptoms such as shortness of breath, fever, dry cough, and chronic fatigue, amongst others. The disease may be asymptomatic in some patients in the early stages, which can lead to increased transmission of the disease to others. This study attempts to review papers on the role of imaging and medical image computing in COVID-19 diagnosis. For this purpose, PubMed, Scopus and Google Scholar were searched to find related studies until the middle of 2021. The contribution of this study is four-fold: 1) to use as a tutorial of the field for both clinicians and technologists, 2) to comprehensively review the characteristics of COVID-19 as presented in medical images, 3) to examine automated artificial intelligence-based approaches for COVID-19 diagnosis, 4) to express the research limitations in this field and the methods used to overcome them. Using machine learning-based methods can diagnose the disease with high accuracy from medical images and reduce time, cost and error of diagnostic procedure. It is recommended to collect bulk imaging data from patients in the shortest possible time to improve the performance of COVID-19 automated diagnostic methods.

Imaging of Coronavirus Disease 2019 Infection From Head to Toe: A Primer for the Radiologist

Coronavirus Disease 2019 (COVID-19) disease has rapidly spread around the world after initial identification in Wuhan, China, in December 2019. Most common presentation is mild or asymptomatic disease, followed by pneumonia, and rarely- multiorgan failure and Acute Respiratory Distress Syndrome (ARDS). Knowledge about the pathophysiology, imaging and treatment of this novel virus is rapidly evolving due to ongoing worldwide research. Most common imaging modalities utilized during this pandemic are chest radiography and HRCT with findings of bilateral peripheral, mid and lower zone GGO and/or consolidation, vascular enlargement and crazy paving. HRCT is also useful for prognostication and follow-up of severely ill COVID-19 patients. Portable radiography allows follow-up of ICU patients & obviates the need of shifting critically ill patients and disinfection of CT room. As the pandemic has progressed, numerous neurologic manifestations have been described in COVID-19 including stroke, white matter hyperintensities and demyelination on MRI. Varying abdominal presentations have been described, which on imaging either show evidence of COVID-19 pneumonia in lung bases or show abdominal findings including bowel thickening and vascular thrombosis. Numerous thrombo-embolic and cardiovascular complications have also been described in COVID-19 including arterial and venous thrombosis, pulmonary embolism and myocarditis. It is imperative for radiologists to be aware of all the varied faces of this disease on imaging, as they may well be the first physician to suspect the disease. This article aims to review the multimodality imaging manifestations of COVID-19 disease in various organ systems from head to toe.

Thoracic imaging outcomes in COVID-19 survivors

The coronavirus disease 2019 (COVID-19) pandemic presents a significant global public health challenge. One in five individuals with COVID-19 presents with symptoms that last for weeks after hospital discharge, a condition termed "long COVID". Thus, efficient follow-up of patients is needed to assess the resolution of lung pathologies and systemic involvement. Thoracic imaging is multimodal and involves using different forms of waves to produce images of the organs within the thorax. In general, it includes chest X-ray, computed tomography, lung ultrasound and magnetic resonance imaging techniques. Such modalities have been useful in the diagnosis and prognosis of COVID-19. These tools have also allowed for the follow-up and assessment of long COVID. This review provides insights on the effectiveness of thoracic imaging techniques in the follow-up of COVID-19 survivors who had long COVID.

Comprehensive Survey of Using Machine Learning in the COVID-19 Pandemic

Since December 2019, the global health population has faced the rapid spreading of coronavirus disease (COVID-19). With the incremental acceleration of the number of infected cases, the World Health Organization (WHO) has reported COVID-19 as an epidemic that puts a heavy burden on healthcare sectors in almost every country. The potential of artificial intelligence (AI) in this context is difficult to ignore. AI companies have been racing to develop innovative tools that contribute to arm the world against this pandemic and minimize the disruption that it may cause. The main objective of this study is to survey the decisive role of AI as a technology used to fight against the COVID-19 pandemic. Five significant applications of AI for COVID-19 were found, including (1) COVID-19 diagnosis using various data types (e.g., images, sound, and text); (2) estimation of the possible future spread of the disease based on the current confirmed cases; (3) association between COVID-19 infection and patient characteristics; (4) vaccine development and drug interaction; and (5) development of supporting applications. This study also introduces a comparison between current COVID-19 datasets. Based on the limitations of the current literature, this review highlights the open research challenges that could inspire the future application of AI in COVID-19.

M-BLUE protocol for coronavirus disease-19 (COVID-19) patients: interobserver variability and correlation with disease severity

AIM

To retrospectively evaluate the interobserver variability of intensive care unit (ICU) practitioners and radiologists who used the M-BLUE (modified bedside lung ultrasound in emergency) protocol to assess coronavirus disease-19 (COVID-19) patients, and to determine the correlation between total M-BLUE protocol score and three different scoring systems reflecting disease severity.

MATERIALS AND METHODS

Institutional review board approval was obtained and informed consent was not required. Ninety-six lung ultrasonography (LUS) examinations were performed using the M-BLUE protocol in 79 consecutive COVID-19 patients. Two ICU practitioners and three radiologists reviewed video clips of the LUS of eight different regions in each lung retrospectively. Each observer, who was blind to the patient information, described each clip with M-BLUE terminology and assigned a corresponding score. Interobserver variability was assessed using intraclass correlation coefficient. Spearman's correlation coefficient analysis (R-value) was used to assess the correlation between the total score of the eight video clips and disease severity.

RESULTS

For different LUS signs, fair to good agreement was obtained (ICC = 0.601, 0.339, 0.334, and 0.557 for 0-3 points respectively). The overall interobserver variability was good for both the five different readers and consensus opinions (ICC = 0.618 and 0.607, respectively). There were good correlations between total LUS score and scores from three systems reflecting disease severity (R=0.394-0.660, p<0.01).

CONCLUSION

In conclusion, interobserver agreement for different signs and total scores in LUS is good and justifies its use in patients with COVID-19. The total scores of LUS are useful to indicate disease severity.

Lessons learned in transitioning to AI in the medical imaging of COVID-19

The coronavirus disease 2019 (COVID-19) pandemic has wreaked havoc across the world. It also created a need for the urgent development of efficacious predictive diagnostics, specifically, artificial intelligence (AI) methods applied to medical imaging. This has led to the convergence of experts from multiple disciplines to solve this global pandemic including clinicians, medical physicists, imaging scientists, computer scientists, and informatics experts to bring to bear the best of these fields for solving the challenges of the COVID-19 pandemic. However, such a convergence over a very brief period of time has had unintended consequences and created its own challenges. As part of Medical Imaging Data and Resource Center initiative, we discuss the lessons learned from career transitions across the three involved disciplines (radiology, medical imaging physics, and computer science) and draw recommendations based on these experiences by analyzing the challenges associated with each of the three associated transition types: (1) AI of non-imaging data to AI of medical imaging data, (2) medical imaging clinician to AI of medical imaging, and (3) AI of medical imaging to AI of COVID-19 imaging. The lessons learned from these career transitions and the diffusion of knowledge among them could be accomplished more effectively by recognizing their associated intricacies. These lessons learned in the transitioning to AI in the medical imaging of COVID-19 can inform and enhance future AI applications, making the whole of the transitions more than the sum of each discipline, for confronting an emergency like the COVID-19 pandemic or solving emerging problems in biomedicine.

COVID-19: persistence of symptoms and lung alterations after 3-6 months from hospital discharge

PURPOSE

Few data are currently available on persistent symptoms and late organ damage in patients who have suffered from COVID-19. This prospective study aimed to evaluate the results of a follow-up program for patients discharged from a nonintensive COVID-19 ward.

METHODS

3-6 months after hospital discharge, 59 of 105 COVID-19 patients (31 males, aged 68.2 ± 12.8 years) were recruited in the study. Forty-six patients were excluded because of nontraceability, refusal, or inability to provide informed consent. The follow-up consisted of anamnesis (including a structured questionnaire), physical examination, blood tests, ECG, lower limb compression venous ultrasound (US), thoracic US, and spirometry with diffusion lung capacity for carbon monoxide (DLCO).

RESULTS

22% of patients reported no residual symptoms, 28.8% 1 or 2 symptoms and 49.2% 3 or more symptoms. The most frequently symptoms were fatigue, exertional dyspnea, insomnia, and anxiety. Among the inflammatory and coagulation parameters, only the median value of fibrinogen was slightly above normal. A deep vein thrombosis was detected in 1 patient (1.7%). Thoracic US detected mild pulmonary changes in 15 patients (25.4%), 10 of which reported exertional dyspnea. DLCO was mildly or moderately reduced in 19 patients (37.2%), 13 of which complained of exertional dyspnea.

CONCLUSION

These results highlight that a substantial percentage of COVID-19 patients (77.8%) continue to complain of symptoms 3-6 months after hospital discharge. Exertional dyspnea was significantly associated with the persistence of lung US abnormalities and diffusing capacity alterations. Extended follow-up is required to assess the long-term evolution of postacute sequelae of COVID-19.