1
|
Qin C, Ma H, Hu M, Xu X, Ji C. Performance of artificial intelligence in predicting the prognossis of severe COVID-19: a systematic review and meta-analysis. Front Public Health 2024; 12:1371852. [PMID: 39145161 PMCID: PMC11322443 DOI: 10.3389/fpubh.2024.1371852] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Accepted: 07/18/2024] [Indexed: 08/16/2024] Open
Abstract
Background COVID-19-induced pneumonia has become a persistent health concern, with severe cases posing a significant threat to patient lives. However, the potential of artificial intelligence (AI) in assisting physicians in predicting the prognosis of severe COVID-19 patients remains unclear. Methods To obtain relevant studies, two researchers conducted a comprehensive search of the PubMed, Web of Science, and Embase databases, including all studies published up to October 31, 2023, that utilized AI to predict mortality rates in severe COVID-19 patients. The PROBAST 2019 tool was employed to assess the potential bias in the included studies, and Stata 16 was used for meta-analysis, publication bias assessment, and sensitivity analysis. Results A total of 19 studies, comprising 26 models, were included in the analysis. Among them, the models that incorporated both clinical and radiological data demonstrated the highest performance. These models achieved an overall sensitivity of 0.81 (0.64-0.91), specificity of 0.77 (0.71-0.82), and an overall area under the curve (AUC) of 0.88 (0.85-0.90). Subgroup analysis revealed notable findings. Studies conducted in developed countries exhibited significantly higher predictive specificity for both radiological and combined models (p < 0.05). Additionally, investigations involving non-intensive care unit patients demonstrated significantly greater predictive specificity (p < 0.001). Conclusion The current evidence suggests that artificial intelligence prediction models show promising performance in predicting the prognosis of severe COVID-19 patients. However, due to variations in the suitability of different models for specific populations, it is not yet certain whether they can be fully applied in clinical practice. There is still room for improvement in their predictive capabilities, and future research and development efforts are needed. Systematic review registration https://www.crd.york.ac.uk/prospero/ with the Unique Identifier CRD42023431537.
Collapse
Affiliation(s)
- Chu Qin
- School of Public Health, Zhejiang Chinese Medical University, Hangzhou, China
| | - Huan Ma
- School of Public Health, Zhejiang Chinese Medical University, Hangzhou, China
| | - Mahong Hu
- Department of Critical Care Medicine, Tongde Hospital of Zhejiang Province, Hangzhou, China
| | - Xiujuan Xu
- Department of Critical Care Medicine, Tongde Hospital of Zhejiang Province, Hangzhou, China
| | - Conghua Ji
- School of Public Health, Zhejiang Chinese Medical University, Hangzhou, China
| |
Collapse
|
2
|
Kasim MF, Abbas AM. Evaluation of Olfactory Dysfunction Among COVID-19 Patients in Baghdad, Iraq. Cureus 2024; 16:e53721. [PMID: 38455837 PMCID: PMC10919444 DOI: 10.7759/cureus.53721] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/06/2024] [Indexed: 03/09/2024] Open
Abstract
Background SARS‑CoV‑2 (COVID-19) causes olfactory dysfunction which is characterized by anosmia or hyposmia. Characterization of olfactory dysfunction has added value to the diagnosis and prognosis of the disease. Nevertheless, scarce information exists about COVID-19 patients suffering from olfactory dysfunction in Iraq. This study aimed to identify olfactory dysfunction (anosmia or hyposmia) in Iraqi COVID-19 patients and examine their response to smell exercise at Baghdad Medical City Complex, Baghdad, Iraq. Methodology This case series prospective study involving 300 patients (160 males and 140 females) with COVID-19 infection was conducted from June 1, 2020, to October 1, 2021. We recorded signs and symptoms of COVID-19 among patients by examining olfactory dysfunction, n-butanol olfaction test, and smell test exercise. Results Anosmia and hyposmia were found in 69.3% and 30.7% of the patients, respectively; of these, 65.7% were of sudden onset. The association between olfactory dysfunction and smoking was not significant. The most frequent signs and symptoms of COVID-19 were fatigue, fever, loss of taste, myalgia, headache, sore throat, cough, depressed appetite, dyspnea, nausea, abdominal pain, and diarrhea. The highest frequencies of occurrence of anosmia (30.7%) and hyposmia (13.3%) were in the age group of 31-40 years. The majority (47.7%) of patients with olfactory dysfunction recovered within one month of COVID-19 onset. The rest of the patients recovered within one month to 16 months. The most commonly encountered ear, nose, and throat symptoms were nasal obstruction, rhinorrhea, and facial/ear pain. The percentages of patients with anosmia and hyposmia recovering with smell exercise were significant at 64.7% and 25.3%, respectively. Conclusions The prognosis of olfactory dysfunction in COVID-19 patients was good as most cases recovered within a short period with concomitant smell exercise. Olfactory dysfunction in the majority of COVID-19 patients was self-limiting in young age groups, albeit in association with the non-severity of the disease. Being an important public health issue, examining olfactory dysfunction aspects should be considered in the diagnosis, prognosis, and treatment protocols of COVID-19 patients. In-depth exploration is needed to examine olfactory and gustatory dysfunction in patients suffering from severe COVID-19.
Collapse
Affiliation(s)
| | - Azzam M Abbas
- Otolaryngology, College of Medicine, University of Baghdad and Martyr Ghazi Al-Hariri Teaching Hospital, Baghdad Medical City, Baghdad, IRQ
| |
Collapse
|
3
|
Wu SS, Cabrera CI, Quereshy HA, Kocharyan A, D'Anza B, Otteson T. Olfactory dysfunction incidence and resolution amongst 608 patients with COVID-19 infection. Am J Otolaryngol 2023; 44:103962. [PMID: 37356414 PMCID: PMC10284438 DOI: 10.1016/j.amjoto.2023.103962] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2023] [Revised: 06/09/2023] [Accepted: 06/17/2023] [Indexed: 06/27/2023]
Abstract
PURPOSE Olfactory dysfunction (OD) is a common presenting sign of coronavirus-19 (COVID-19) infection and remains persistent in up to 7 % of patients one year after diagnosis. However, demographic, socioeconomic, and medical risk factors for persistent OD are not well understood. This study aims to determine risk factors for development and persistence of OD amongst patients with COVID-19 infection. MATERIALS AND METHODS This prospective, observational questionnaire study was performed at a tertiary-level, academic center. Patients with history of a positive COVID-19 diagnosis were sent an online questionnaire. Patients' self-reported survey responses for OD and resolution were assessed for associations with demographic variables, socioeconomic factors, and clinical data. RESULTS In total, 608 of 26,094 patients (77.6 % women, mean age 42.7 ± 17.4 years, range 9 months-92 years) completed the survey. OD was reported by 220 (36.2 %) patients, and 139 (63.2 %) patients achieved resolution. Patients with OD were more likely to have other sinonasal and flu-like symptoms, and had a hospitalization rate of 2.7 %. There were no significant differences in age, gender, occupational or residential factors, or medical comorbidities incidence of OD development. Women reported higher rates of persistent OD (88.9 % vs 77.0 %, p = 0.045). The OD recovery rates amongst active and resolved COVID-19 infections was 27.0 % and 70.0 %, respectively (p < 0.001). CONCLUSIONS There was a low hospitalization rate amongst patients reporting OD. One-third of patients with COVID-19 self-reported OD, and two-thirds of patients achieve OD resolution. Survey respondents with active COVID-19 infection and female gender were more likely to report persistent OD.
Collapse
Affiliation(s)
- Shannon S Wu
- Cleveland Clinic Lerner College of Medicine, Cleveland, OH, USA
| | - Claudia I Cabrera
- Department of Otolaryngology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA
| | - Humzah A Quereshy
- Department of Otolaryngology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA
| | - Arminé Kocharyan
- Department of Otolaryngology, University of Iowa Hospitals and Clinics, Iowa City, IA, USA
| | - Brian D'Anza
- Department of Otolaryngology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA
| | - Todd Otteson
- Department of Otolaryngology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA.
| |
Collapse
|
4
|
Lee PI, Hsueh PR. Multisystem inflammatory syndrome in children: A dysregulated autoimmune disorder following COVID-19. JOURNAL OF MICROBIOLOGY, IMMUNOLOGY, AND INFECTION = WEI MIAN YU GAN RAN ZA ZHI 2023; 56:236-245. [PMID: 36720670 PMCID: PMC9841678 DOI: 10.1016/j.jmii.2023.01.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 12/07/2022] [Accepted: 01/09/2023] [Indexed: 01/17/2023]
Abstract
Multisystem inflammatory syndrome in children (MIS-C) is a dysregulated autoimmune-mediated illness in genetically susceptible patients following COVID-19 with an interval of 2-6 weeks. The median age of patients with MIS-C is 6-11 years. Most common manifestations are involvement of gastrointestinal tract, cardiovascular system, hematological system, and mucocutaneous system. Respiratory tract, neurological system, musculoskeletal system, and kidney are less frequently affected. Mucocutaneous manifestations and coronary artery abnormalities characteristic for Kawasaki disease (KD) may be observed in a significant proportion of MIS-C patients that may make the differential diagnosis be difficult for some patients, especially in the post-pandemic era. The mortality rate is 1-3%. Management and prognosis of MIS-C are similar to that of KD. MIS-C and KD may share a common pathogenic process. Based on the observation of MIS-C-like illness in uninfected neonates, i.e. multisystem inflammatory syndrome in neonates, both MIS-C and KD may be a consequence of dysregulated, over-exaggerated humoral immune responses triggered by a specific infectious agent.
Collapse
Affiliation(s)
- Ping-Ing Lee
- Department of Pediatrics, National Taiwan University Children's Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
| | - Po-Ren Hsueh
- Division of Infectious Diseases, Department of Internal Medicine, China Medical University Hospital, China Medical University, Taichung, Taiwan; Department of Laboratory Medicine, China Medical University Hospital, China Medical University, Taichung, Taiwan; Ph.D Program for Aging, School of Medicine, China Medical University, Taichung, Taiwan; Departments of Laboratory Medicine and Internal Medicine, National Taiwan University Hospital, National Taiwan University College of Medicine, Taipei, Taiwan
| |
Collapse
|
5
|
Lai CC, Hsu CK, Yen MY, Lee PI, Ko WC, Hsueh PR. Long COVID: An inevitable sequela of SARS-CoV-2 infection. JOURNAL OF MICROBIOLOGY, IMMUNOLOGY, AND INFECTION = WEI MIAN YU GAN RAN ZA ZHI 2023; 56:1-9. [PMID: 36283919 PMCID: PMC9576029 DOI: 10.1016/j.jmii.2022.10.003] [Citation(s) in RCA: 49] [Impact Index Per Article: 49.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Revised: 09/25/2022] [Accepted: 10/03/2022] [Indexed: 11/06/2022]
Abstract
At present, there are more than 560 million confirmed cases of the coronavirus disease 2019 (COVID-19) worldwide. Although more than 98% of patients with severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) infection can survive acute COVID, a significant portion of survivors can develop residual health problems, which is termed as long COVID. Although severe COVID-19 is generally associated with a high risk of long COVID, patients with asymptomatic or mild disease can also show long COVID. The definition of long COVID is inconsistent and its clinical manifestations are protean. In addition to general symptoms, such as fatigue, long COVID can affect many organ systems, including the respiratory, neurological, psychosocial, cardiovascular, gastrointestinal, and metabolic systems. Moreover, patients with long COVID may experience exercise intolerance and impaired daily function and quality of life. Long COVID may be caused by SARS-CoV-2 direct injury or its associated immune/inflammatory response. Assessment of patients with long COVID requires comprehensive evaluation, including history taking, physical examination, laboratory tests, radiography, and functional tests. However, there is no known effective treatment for long COVID. Based on the limited evidence, vaccines may help to prevent the development of long COVID. As long COVID is a new clinical entity that is constantly evolving, there are still many unknowns, and further investigation is warranted to enhance our understanding of this disease.
Collapse
Affiliation(s)
- Chih-Cheng Lai
- Division of Hospital Medicine, Department of Internal Medicine, Chi Mei Medical Center, Tainan, Taiwan
| | - Chi-Kuei Hsu
- Department of Internal Medicine, E-Da Hospital, Kaohsiung, Taiwan
| | - Muh-Yong Yen
- Division of Infectious Diseases, Cheng Hsin General Hospital, School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Ping-Ing Lee
- Department of Pediatrics, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Wen-Chien Ko
- Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan,Department of Medicine, College of Medicine, National Cheng Kung University, Tainan, Taiwan
| | - Po-Ren Hsueh
- Department of Laboratory Medicine, China Medical University Hospital, Taichung, Taiwan,Department of Internal Medicine, China Medical University Hospital, Taichung, Taiwan,School of Medicine, China Medical University, Taichung, Taiwan,Departments of Laboratory Medicine and Internal Medicine, National Taiwan University Hospital, National Taiwan University College of Medicine, Taipei, Taiwan,Corresponding author. Departments of Laboratory Medicine and Internal Medicine, China Medical University Hospital, China Medical University, No. 2, Yude Road, North District, Taichung 40447, Taiwan
| |
Collapse
|
6
|
Systematic review and meta-analysis of olfactory and gustatory dysfunction in COVID-19. Int J Infect Dis 2022; 117:155-161. [PMID: 35134561 PMCID: PMC8817419 DOI: 10.1016/j.ijid.2022.02.004] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2021] [Revised: 01/31/2022] [Accepted: 02/01/2022] [Indexed: 12/20/2022] Open
Abstract
Background Chemosensory disorders associated with COVID-19 have been widely discussed during the pandemic. We performed a meta-analysis to assess the risk factors for olfactory and gustatory dysfunction in patients with COVID-19. Methods Three databases (PubMed, Embase, and Cochrane Library) were searched for studies published between December 1, 2019, and August 31, 2021. We selected random-effects model or fixed-effects model to pool data based on heterogeneity. The results were reported as odds ratios (ORs) or standardized mean differences (SMDs) and the corresponding 95% confidence intervals (CIs). Heterogeneity was reported as I2. Results Twenty-six studies with a total of 13,813 patients were included. The pooled data indicated that sex (OR 1.47; 95% CI 0.93–2.31), age (SMD −5.80; 95% CI −13.35 to 1.75), smoking (OR 2.04; 95% CI 0.72–5.79), and comorbidity (OR 1.21; 95% CI 0.58–2.53) of patients with COVID-19 had no effect on gustatory dysfunction. Olfactory dysfunction was more likely to occur in older patients with COVID-19 (SMD, −5.22; 95% CI, −8.28 to −2.16). Patients with COVID-19 with nasal congestion (OR 3.41; 95% CI 2.30–5.06) and rhinorrhea (OR 2.35; 95% CI 1.60–3.45) were more prone to olfactory dysfunction. Conclusion These findings emphasize that older patients with COVID-19 are more likely to experience olfactory dysfunction. Symptoms of nasal congestion and rhinorrhea may affect the recognition of olfactory dysfunction.
Collapse
|
7
|
Wei G, Gu J, Gu Z, Du C, Huang X, Xing H, Li L, Zhang A, Hu X, Huo J. Olfactory Dysfunction in Patients With Coronavirus Disease 2019: A Review. Front Neurol 2022; 12:783249. [PMID: 35115994 PMCID: PMC8805677 DOI: 10.3389/fneur.2021.783249] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2021] [Accepted: 12/14/2021] [Indexed: 01/08/2023] Open
Abstract
The coronavirus disease 2019 (COVID-19) pandemic is wreaking havoc on public-health and economic systems worldwide. Among the several neurological symptoms of patients with COVID-19 reported in clinical practice, olfactory dysfunction (OD) is the most common. OD occurs as the earliest or the only clinical manifestation in some patients. Increasing research attention has focused on OD, which is listed as one of the main diagnostic symptoms of severe acute respiratory syndrome-coronavirus-2 infection. Multiple clinical and basic-science studies on COVID-19-induced OD are underway to clarify the underlying mechanism of action. In this review, we summarize the clinical characteristics, mechanisms, evaluation methods, prognosis, and treatment options of COVID-19-induced OD. In this way, we hope to improve the understanding of COVID-19-induced OD to aid early identification and precise intervention.
Collapse
Affiliation(s)
- Guoli Wei
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
- Nanjing Lishui District Hospital of Traditional Chinese Medicine, Nanjing, China
- Department of Oncology, Yangzhou University Medical College, Yangzhou, China
| | - Jialin Gu
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
- The Third Medical College, Nanjing University of Chinese Medicine, Nanjing, China
| | - Zhancheng Gu
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
- The Third Medical College, Nanjing University of Chinese Medicine, Nanjing, China
| | - Cheng Du
- Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China
| | - Xiaofei Huang
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
- The Third Medical College, Nanjing University of Chinese Medicine, Nanjing, China
| | - Haiyan Xing
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
| | - Lingchang Li
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
| | - Aiping Zhang
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
| | - Xingxing Hu
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
- Nanjing Lishui District Hospital of Traditional Chinese Medicine, Nanjing, China
- Department of Oncology, Yangzhou University Medical College, Yangzhou, China
- *Correspondence: Xingxing Hu
| | - Jiege Huo
- Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine, Nanjing, China
- Jiangsu Province Academy of Traditional Chinese Medicine, Nanjing, China
- Jiege Huo
| |
Collapse
|
8
|
Comparison of Brain Activation Patterns during Olfactory Stimuli between Recovered COVID-19 Patients and Healthy Controls: A Functional Near-Infrared Spectroscopy (fNIRS) Study. Brain Sci 2021; 11:brainsci11080968. [PMID: 34439587 PMCID: PMC8391911 DOI: 10.3390/brainsci11080968] [Citation(s) in RCA: 32] [Impact Index Per Article: 10.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Revised: 07/19/2021] [Accepted: 07/20/2021] [Indexed: 12/20/2022] Open
Abstract
Impaired sense of smell occurs in a fraction of patients with COVID-19 infection, but its effect on cerebral activity is unknown. Thus, this case report investigated the effect of COVID-19 infection on frontotemporal cortex activity during olfactory stimuli. In this preliminary study, patients who recovered from COVID-19 infection (n = 6) and healthy controls who never contracted COVID-19 (n = 6) were recruited. Relative changes in frontotemporal cortex oxy-hemoglobin during olfactory stimuli was acquired using functional near-infrared spectroscopy (fNIRS). The area under curve (AUC) of oxy-hemoglobin for the time interval 5 s before and 15 s after olfactory stimuli was derived. In addition, olfactory function was assessed using the Sniffin’ Sticks 12-identification test (SIT-12). Patients had lower SIT-12 scores than healthy controls (p = 0.026), but there were no differences in oxy-hemoglobin AUC between healthy controls and patients (p > 0.05). This suggests that past COVID-19 infection may not affect frontotemporal cortex function, and these preliminary results need to be verified in larger samples.
Collapse
|