Review

Theory and application of artificial intelligence in financial industry

  • Artificial Intelligence (AI) is deemed to be the commanding point of science and technology in the next era. In recent years, with the enhancement of computer computing power, the improvement of the quantity and quality of big data, and the important breakthroughs in many research fields such as machine learning and speech recognition, AI technology has developed rapidly and has been widely used in all walks of life. In the financial industry, the application of AI technology in risk control, marketing, customer service, transaction, operation, and product optimization of financial institutions is becoming increasingly mature, and some new business models have been created. Starting from the application status and significance of AI in the international financial field, this paper expounds on the application, status quo, and development trend of AI in the financial industry. Then, in view of the risks and practical challenges existing in the development process of AI, based on the reality of international financial development, this paper summarizes the measures to promote the in-depth, healthy, and sustainable development of AI in the financial market. This paper aims to let readers understand the development status of AI in the financial field, and also provide theoretical reference for scholars in this field.

    Citation: Yuxin Li, Jizheng Yi, Huanyu Chen, Duanxiang Peng. Theory and application of artificial intelligence in financial industry[J]. Data Science in Finance and Economics, 2021, 1(2): 96-116. doi: 10.3934/DSFE.2021006

    Related Papers:

    [1] Fan He, Minru Li, Xinyu Wang, Lu Hua, Tingting Guo . Numerical investigation of quantitative pulmonary pressure ratio in different degrees of stenosis. Mathematical Biosciences and Engineering, 2024, 21(2): 1806-1818. doi: 10.3934/mbe.2024078
    [2] Zhenshuang Du, Qingwei Yang, Hefan He, Mingxia Qiu, Zhiyao Chen, Qingfu Hu, Qingmao Wang, Ziping Zhang, Qionghua Lin, Liuyue Huang, Yajiao Huang . A comprehensive health classification model based on support vector machine for proseal laryngeal mask and tracheal catheter assessment in herniorrhaphy. Mathematical Biosciences and Engineering, 2020, 17(2): 1838-1854. doi: 10.3934/mbe.2020097
    [3] K. Maqbool, S. Shaheen, A. M. Siddiqui . Effect of nano-particles on MHD flow of tangent hyperbolic fluid in a ciliated tube: an application to fallopian tube. Mathematical Biosciences and Engineering, 2019, 16(4): 2927-2941. doi: 10.3934/mbe.2019144
    [4] Urszula Ledzewicz, Behrooz Amini, Heinz Schättler . Dynamics and control of a mathematical model for metronomic chemotherapy. Mathematical Biosciences and Engineering, 2015, 12(6): 1257-1275. doi: 10.3934/mbe.2015.12.1257
    [5] Khaphetsi Joseph Mahasa, Rachid Ouifki, Amina Eladdadi, Lisette de Pillis . A combination therapy of oncolytic viruses and chimeric antigen receptor T cells: a mathematical model proof-of-concept. Mathematical Biosciences and Engineering, 2022, 19(5): 4429-4457. doi: 10.3934/mbe.2022205
    [6] Ruohan Li, Jinzhi Lei . Optimal therapy schedule of chimeric antigen receptor (CAR) T cell immunotherapy. Mathematical Biosciences and Engineering, 2025, 22(7): 1653-1679. doi: 10.3934/mbe.2025061
    [7] Yangjin Kim, Seongwon Lee, You-Sun Kim, Sean Lawler, Yong Song Gho, Yoon-Keun Kim, Hyung Ju Hwang . Regulation of Th1/Th2 cells in asthma development: A mathematical model. Mathematical Biosciences and Engineering, 2013, 10(4): 1095-1133. doi: 10.3934/mbe.2013.10.1095
    [8] Li Cai, Yu Hao, Pengfei Ma, Guangyu Zhu, Xiaoyu Luo, Hao Gao . Fluid-structure interaction simulation of calcified aortic valve stenosis. Mathematical Biosciences and Engineering, 2022, 19(12): 13172-13192. doi: 10.3934/mbe.2022616
    [9] Alexandre Cornet . Mathematical modelling of cardiac pulse wave reflections due to arterial irregularities. Mathematical Biosciences and Engineering, 2018, 15(5): 1055-1076. doi: 10.3934/mbe.2018047
    [10] B. Wiwatanapataphee, D. Poltem, Yong Hong Wu, Y. Lenbury . Simulation of Pulsatile Flow of Blood in Stenosed Coronary Artery Bypass with Graft. Mathematical Biosciences and Engineering, 2006, 3(2): 371-383. doi: 10.3934/mbe.2006.3.371
  • Artificial Intelligence (AI) is deemed to be the commanding point of science and technology in the next era. In recent years, with the enhancement of computer computing power, the improvement of the quantity and quality of big data, and the important breakthroughs in many research fields such as machine learning and speech recognition, AI technology has developed rapidly and has been widely used in all walks of life. In the financial industry, the application of AI technology in risk control, marketing, customer service, transaction, operation, and product optimization of financial institutions is becoming increasingly mature, and some new business models have been created. Starting from the application status and significance of AI in the international financial field, this paper expounds on the application, status quo, and development trend of AI in the financial industry. Then, in view of the risks and practical challenges existing in the development process of AI, based on the reality of international financial development, this paper summarizes the measures to promote the in-depth, healthy, and sustainable development of AI in the financial market. This paper aims to let readers understand the development status of AI in the financial field, and also provide theoretical reference for scholars in this field.



    Benign airway stenosis refers to airway stenosis caused by airway wall damage by a variety of non-neoplastic diseases, which can lead to cough, sputum, varying degrees of dyspnea and other symptoms. Benign airway stenosis seriously affects the quality of life of patients, and even the occurrence of respiratory failure and death. The etiology includes: long-term tracheal intubation, tracheotomy, tracheal-bronchial tuberculosis, trauma and so on [1]. Previous treatment of secondary benign airway stenosis was limited, mainly based on surgical resection and reconstruction. However, surgical treatment not only requires good condition of patients, but also has many disadvantages, such as many perioperative complications and long recovery time after operation. In particular, those patients are often suffering from combined pulmonary infection, dysfunction of central nervous system and other complications, consequently leading to the loss of possibility for traditional surgical procedures. With the rapid development of interventional therapy under bronchoscopy, the endoscopic interventional therapy is becoming more and more [2], such as laser, balloon dilatation, freezing, stenting and so on. These measures provide safer and more effective treatment options for patients with benign airway stenosis after tracheotomy. Among them, Montgomery T-tube implantation under rigid bronchoscopy is considered as an effective, safe and well-tolerated method for tracheal stenosis.

    This study retrospectively reviewed 20 patients who had treatments of secondary benign airway stenosis after tracheotomy with Montgomery T-tube between September 2015 and February 2019 in Sir Run Run Shaw Hospital, affiliated with Zhejiang University. The clinical data including clinical features, efficacy, complications and prognosis were retrospectively analyzed to evaluate the value of Montgomery T-tube placement in secondary benign airway stenosis after tracheotomy.

    All of the 20 patients were hospitalized, including 14 males and 6 females aged 20–71 years old. The clinical manifestations were mainly cough, sputum, varying degrees of dyspnea, and failed plugging with tracheostomy cannula. The duration of tracheotomy was 28 days to 16 months (Table 1). Twenty patients were diagnosed with benign tracheal stenosis by medical history, physical examination, and chest CT scan and bronchoscopy. Complete trachea obstruction was in 8 cases and partial tracheal stenosis was in 12 cases. After discussion, the intervention team decided that these patients were not suitable for surgical tracheal resection and reconstruction. Through the multidisciplinary (anesthesiology, ENT and cardiothoracic surgery) discussion, a suitable endoscopic interventional treatment was developed.

    Table 1.  Basic information of patients.
    N G Age Underlying diseases Duration of tracheotomy Clinical symptoms The degree of stenosis Stenosis types Stenosis length
    1 M 71 Cerebral hemorrhage 1 month Failed tracheal plugging > 2/3 Granulation tissue combined with tracheal wall collapse 1–2 cm
    2 M 39 Craniocerebral trauma 9 months Failed tracheal plugging Complete Granulation tissue 1–2 cm
    3 F 55 Car accident trauma 6 months Cough, Dyspnea > 2/3 Granulation tissue combined with scar stenosis 2 cm
    4 M 41 Cerebral hemorrhage 16 months Cough, expectoration > 2/3 Granulation tissue 1–2 cm
    5 M 36 Cerebral hemorrhage 3 months Dyspnea Complete Scar stenosis 2 cm
    6 M 20 Electric injury 2 months Expectoration, failed tracheal plugging Complete Scar stenosis 3 cm
    7 M 46 Cerebral hemorrhage 20 days Cough, expectoration, dyspnea > 2/3 Tracheal distortions combined with scar stenosis 2–3 cm
    8 M 66 Cerebral infarction 3 months Failed tracheal plugging Complete Granulation tissue combined with scar stenosis 1–2 cm
    9 M 52 Craniocerebral trauma 2 months Cough, dyspnea Complete Granulation tissue combined with scar stenosis 1–2 cm
    10 F 51 Cerebral hemorrhage 6 months Failed tracheal plugging > 2/3 Tracheal distortions combined with scar stenosis 1–2 cm
    11 F 69 Cerebral hemorrhage 69 days Failed tracheal plugging > 2/3 Scar stenosis 1–2 cm
    12 M 71 Cerebral hemorrhage 28 days Failed tracheal plugging Complete Tracheal distortions combined with scar stenosis 1–2 cm
    13 F 24 Granulomatosis with polyangiitis 36 days Failed tracheal plugging > 2/3 Granulation tissue combined scar stenosis 3 cm
    14 M 66 Cerebral hemorrhage 3 months Failed tracheal plugging Complete Tracheal distortions combined with scar stenosis 1–2 cm
    15 F 55 Cerebral hemorrhage 50 days Failed tracheal plugging > 2/3 Scar stenosis 2 cm
    16 F 47 Craniocerebral trauma 3 months Failed tracheal plugging > 2/3 Tracheal distortions combined with scar stenosis 2 cm
    17 M 28 Craniocerebral trauma 2 months Failed tracheal plugging > 2/3 Granulation tissue combined with scar stenosis 3 cm
    18 M 70 Cerebral infarction 1 months Failed tracheal plugging > 2/3 Scar stenosis 1–2 cm
    19 M 48 Cerebral infarction 3 months Failed tracheal plugging Complete Scar stenosis > 3 cm
    20 M 59 Cerebral hemorrhage 70 days Failed tracheal plugging > 2/3 Tracheal distortions combined with scar stenosis 2 cm
    N: number; G: gender; M: male; F: female.

     | Show Table
    DownLoad: CSV

    The protocol of endoscopic intervention is as follows:

    a. Anesthesia: Patients were given tracheotomy and indwelling metal tracheostomy cannulas before operation. After intravenous anesthesia, the metal tracheostomy cannula was replaced by a plastic tracheostomy cannula and then connected to a ventilator.

    b. Airway assessment and intervention: Oral insertion of STORZ rigid bronchoscope was performed after position placed to observe the stenosis of glottic and airway. For patients with incomplete airway atresia, rigid bronchoscopic mechanical expansion, balloon dilatation, granulation tissue resection or other intervention methods can be used to dilatation the narrow airway to 10–15 mm, hence ensuring that the airway has adequate space for T-tube placement. For patients with complete airway obstruction (8/20, Figure 1), tracheostomy cannulas were replaced with size 5.5–6 tracheal tubes for ventilation. After the ENT physician's cooperation, the anatomical structure through retrograde exploration from the distal end of atresia trachea was undertaken, and electric knife or laser was used in the proximal end of trachea for airway atresia recanalization. Balloon dilatation of the stenotic trachea was then performed after successful recanalization.

    Figure 1.  The bronchoscopic result indicated the complete atresia of upper trachea (A). The CT result suggested the complete atresia of cervical trachea (B). Complete atresia of cervical trachea and indwelling metal tracheostomy cannula were found before the operation (C). Airway atresia recanalization was achieved and the indwelling T-tube was observed after the operation (D).

    c. T-tube placement: T-tubes with appropriate diameter were selected according to the chest CT measurement results, and then were pruned and polished when the length of T-tube proximal and distal branch was determined by bronchoscopic labeling and measurement (Table 2). The distal branch of T-tube was clamped by a vessel forceps and inserted into the airway, and the proximal branch was pulled into the proximal airway by foreign body forceps through the rigid bronchial duct, and then the position was adjusted.

    Table 2.  Information of Montgomery T-tube implantation.
    Cases Rate
    T-tube model (diameter mm) 13 mm: 3 14 mm: 5 15 mm: 3 8/20 9/20 3/20
    Combined with balloon dilatation 18 18/20
    Combined with rigid bronchoscopic mechanical expansion 13 13/20
    Combined with granulation tissue resection 13 13/20
    Retrograde tracheal blunt separation 8 8/20
    Rate of postoperative tracheal plugging 19 19/20

     | Show Table
    DownLoad: CSV

    d. Off-line recovery and care: The external branch of T-tube was closed, and the laryngeal mask was inserted for ventilation. The patients can be taken off the ventilator and returned back ward after spontaneous breathing was restored. 18 patients restored oral ventilation in the recovery room; 2 patient was unable restore oral ventilation and was failed in tracheal plugging; blood oxygen saturation decreased in 2 patients after returning to the ward, which was ameliorated by opening the external branches of T-tubes; tracheal plugging was successful after 24 hours, and the possible vocal cord edema was observed as a considerably postoperative complication. The routine doctor's advice includes: reducing mucous (ambroxol), atomization (saline + ipratropium bromide), the use of prophylactic antibiotics, cervical and chest CT review 3 days after operation; the patients were admitted to hospital for assessments respectively at 1, 3 and 6 months after the operation.

    Eighteen patients successfully restored oral respiration after closing external branches of T-tubes, and were able to phonate with significant improvement in quality of life. CPAP-assisted ventilation was performed after the surgery in 1 patient due to the combined OSAS (sleep apnea syndrome). One patient still failed to restore oral breathing after the operation, considering as bilateral vocal cord paralysis caused by cerebrovascular accident after ENT assessment. And another patient failed was due to pulmonary infection. Mild mediastinal emphysema in mediastinum and neck was observed in 1 patient in routine examination of chest CT after the operation, which was self-absorbed after oxygen inhalation (Figure 2); different levels of increased sputum were found in all 20 patients; obstruction in partial lumen due to phlegm scab formation was found in only 4 cases by bronchoscopy, which was extracted by repeatedly douching of normal saline. Granulation tissue formation on the edge of T-tubes was found in 13 patients at 3 and 6 months respectively after the operation (Figure 3), and granulation tissue resection was then performed in 5 cases among them. Increases in cough and expectoration were found in 1 patient with cerebral infarction at 1 month after the operation; no fever was observed; the chest CT result indicated the right lower lung infection, considering as aspiration pneumonia, which was improved after anti-infection treatment. Dyspnea appeared in 1 patient at 15 days after the operation, and then ventilation by opening external branches of T-tubes was performed; the neck and chest CT examination showed that the T-tube moves down about 1 cm due to the large incision stoma in the patient, consequently leading to stenosis in the upper edge of T-tube caused by the shorter length of superior T-tube branch. Thus, T-tube replacement was scheduled to perform by a bronchoscope under general anesthesia, and partial of the incision stoma was sutured to prevent T-tube displacement. Two patients accepted the T-tube re-implantation due to the re-stenosis after removing the T-tube (Table 3).

    Figure 2.  Postoperative neck and subcutaneous emphysema, which was self-absorbed after oxygen inhalation.
    Figure 3.  Granulation tissue formed on the upper limb of the tube and secondary airway stenosis (A); Airway stenosis was improved after endoscopic granulation tissue resection (B).
    Table 3.  Complications after T-tube implantation.
    Complications Cases Treatment measures and outcomes
    Short-term < 24 h Mediastinum / neck emphysema 1/20 Oxygen inhalation; self-absorbed after 3 d
    Dyspnea 2/20 Improved after oxygen inhalation
    Irritating cough 6/20 Not serious r; aerosol treatment
    Increased secretion of mucous 20/20 Aerosol treatment of saline
    Vocal cord edema 3/20 Untreated; improved after 24 h
    Long-term * > 24 h Obstruction due to mucous formation in T-tube 4/20 Suction under bronchoscope
    Combined with lower respiratory tract infection 1/20 Improved after antibiotics treatment
    Granulation tissue formed at proximal end of T-tube 13/20 Endoscopic granulation resection was performed in 5 cases
    Granulation tissue formed at distal end of T-tube 0/20
    T-tube re-implantation 3/20 Improved after T-tube re-implantation
    Subcutaneous soft tissue infection 1/20 local disinfection and antibiotics therapy
    Note: among the 20 cases, 18 patients had been completed 1-month follow-up, but 2 patients had not yet reached the 1-month follow-up date.

     | Show Table
    DownLoad: CSV

    Ten patients were successfully removed T-tubes about 6 months after the operation, and no dyspnea or other uncomfortable symptoms was observed after T-tube removal. However, 2 patients replaced the T-tube. The remaining 8 patients have still been indwelling of T-tubes and following up.

    The incidence of secondary benign airway stenosis caused by long-term tracheal intubation and tracheotomy was rare previously. As reported, the incidence of benign airway stenosis in the critically ill patients with ICU mechanical ventilation was reported to be about 1% [3]. However, with the improvement of surgical operation and critical medicine at present, the incidence of benign tracheal stenosis is underestimated. Previous treatments of secondary benign airway stenosis were mainly based on curative surgical resection and reconstruction [4]. However, whether the operation can be performed is highly related to the degree and range of airway stenosis, the presence of infection and other factors. Besides, surgical treatment also requires patients in good condition and can tolerate surgery. However, these patients tend to have more complications, for examples, most of the 20 patients in this study have traumatic brain injury, cerebrovascular accident and other severe central nervous system injury, which do not allow the patients to tolerate surgical treatment after assessments. Moreover, there are many problems such as large surgical trauma, many perioperative complications and difficult operation, and even occurrence of long-term anastomotic restenosis in a considerable ratio [5]. Although the surgical treatment, when not contraindicated by associated diseases or by the excessive length of the tracheal lesions, still remains the treatment of choice, with the development of interventional therapy, endoscopic interventional therapy has become an effective and feasible method for treatment of benign tracheobronchial stenosis because of its limited trauma, easy operation and rapid relief of symptoms.

    In 1965, William Montgomery pioneered the use of T-tube for the prevention of tracheal stenosis after tracheal surgery [6]. The original T-tube was made of acrylic material and was later changed to silicone material due to the hard texture. The internal branch of the T-tube is used to support and shape trachea, and the external branch is used for external fixation, preventing T-tube slippage and displacement. There are different diameter models in internal branch of T-tube, which can be chosen according to the tracheal thickness of patients. The operating doctor can determine the length of upper and lower branches according to the length of tracheal stenosis and the location of incision. This should be carefully measured and evaluated before T-tube placement. The advantages of the T-tube in treatment of benign airway stenosis are as follows:

    a. Patients can restore natural cavity breathing and phonate after T-tube placement.

    b. T-tube is made by silicone material which is soft and has considerably less irritation to airway, and not easy to produce granulation tissue compared with metal material [7,8]; patients are well tolerated with T-tube which is good for supporting and conducive to airway remodeling.

    c. The external branch of T-tube plays a fixed role and overcomes the disadvantage that the straight cylinder type silicone stent is easy to shift. It has been reported that stent displacement occurs in approximately 6–18% of patients with the most frequently used straight cylinder type silicone DUMON stent [9,10].

    d. If stenosis of the upper end of T-tube or blockage due to secretions in T-tube appears again, the doctor can open the external branch of T-tube to conduct ventilation and mucous suction through the external branch which can connect to a ventilator. DUMON stent is more likely to result in accumulation and blockage of mucous, and there is no effective way to avoid. If necessary, DUMON stent must be removed. T-tube has obviously better safety compared with DUMON stent and metal stent.

    e. T-tube is easy to place and remove, and the support time of T-tube usually takes at least 6 months. Compared with silicone stent, metal stent is not easy to remove [7,11]. Therefore, for subglottic benign airway stenosis, the Montgomery T-tube is a better choice compared with traditional self-expanding metal stent and straight cylinder silicone DUMON stent.

    In this study, 20 cases of T-tube placement were under general anesthesia, which is more conducive to implementation of the operation [12,13]. A tracheostomy cannula was placed before T-tube placement to ensure safe ventilation and operation. Among them, 8 patients had complete airway obstruction and required retrograde exploration of the distal end of atresia airway by surgical teamwork; besides, electrocoagulation was performed for airway recanalization. These patients need more sufficient assessments and teamwork before operation, and should be carefully operated to avoid tracheal perforation, fracture, tracheo-esophageal fistula and other complications. All patients were operated under rigid bronchoscopy, which is easier and safer for balloon dilatation, granulation excision or other operation of airway before T-tube implantation. After placing T-tube in incision stoma, it needs to be adjusted under rigid bronchoscopy [14].

    The most important point for T-tube implantation is preoperative evaluation. The achievement rate of T-tube placement is closely related to the location and length of stenosis. Therefore, the range and severity of airway stenosis, as well as the distance from stenosis area to glottis and carina should be evaluated by imaging examination before operation. The major points are as follows:

    a. The upper branch of T-tube cannot be longer than the glottis, or else it will result in glottis discomfort and dysfunction; the distance from the upper end of T-tube to glottis is at least 1 cm, so that patient with the distance from narrow segment to glottis shorter than 2 cm is not suitable for T-tube placement.

    b. The diameter of T-tube should be appropriate, otherwise, it will cause the risk of granulation tissue on the edge of T-tube. Besides, the compressed and ischemic airway mucosa is also easy to combine with infection and restenosis. The diameter of T-tube should not be too small, or it will cause mucous obstruction and is not easy for airway support.

    c. There is a function of the structure of tracheal cartilage. If the cartilage collapse and lose support function completely, the patient is not suitable for T-tube implantation.

    The success rate and safety of T-tube placement were higher, similar as those in previously reports [15,16,17]. All of the 20 patients were successfully placed T-tubes. Although 2 patients failed in T-tubes plugging in 24h after operation, they were successfully completely plugged several days. We attributed the delay of T-tube plugging to the adaptation and condition of the patients. We found that the short-term complications mainly included mucous secretion, irritating cough, and transient dyspnea, which were generally alleviated after symptomatic treatments alone; while long-term complication was mainly granulation tissue hyperplasia on the edge of T-tube, and only 5 patients needed for endoscopic resection of granulation tissue due to secondary airway stenosis. Since many patients suffer from sputum retention and require long-time T-tube implantation, attention and assessments of expectoration in patients should be considered after operation, and regular cleaning of the wall is necessary to prevent T-tubes from occlusion. For benign airway stenosis, support time of T-tube has not been determined yet [12,18]. The removal time should be determined based on the characteristics of each patient's condition, and performed at 6 months after the operation is generally appropriate. After T-tube removal, a temporary tracheostomy cannula should be placed, which can be removed if there is no airway collapse at 2 months after the operation. Otherwise, T-tube replacement or surgical treatment should be selected. There are 3 cases re-implanted the T-tube. One patient re-implanted due to the moving down of T-tube, another two patients re-implanted due to re-stenosis after T-tube removal (3 months and another 2 months later). For those two patients, treatment should in fact be based on a combination of surgical and endoscopic treatments, and also remind us that T-tubes may be effective and safe, however, surgical treatment still is an important choice. The target group of T-tube implantation should be careful and precise, exclude those patients who eligible for surgery.

    In summary, for patients with secondary benign airway stenosis after tracheal intubation or tracheostomy who are not suitable for surgery, Montgomery T-tube replacement under rigid bronchoscopy is an effective, safe and well-tolerated method for tracheal stenosis, and is helpful for improvement of quality of life.

    The study was supported by Zhejiang Medical and Health Science and Technology Project (no. 2016ZDA010).

    The authors declare no conflict of interest.



    [1] Abbadi IM, Alawneh M (2008) Preventing insider information leakage for enterprises. 2008 Second International Conference on Emerging Security Information, Systems and Technologies, 99–106.
    [2] Abellán J, Castellano JG (2017) A comparative study on base classifiers in ensemble methods for credit scoring. Expert Syst Appl 73: 1–10. doi: 10.1016/j.eswa.2016.12.020
    [3] Albashrawi M (2021) Detecting financial fraud using data mining techniques: A decade review from 2004 to 2015. J Data Sci 14: 553–570. doi: 10.6339/JDS.201607_14(3).0010
    [4] Anthony M, Bartlett P (1999) Neural Network Learning-Theoretical Foundations.
    [5] Khedr AE, Salama SE, Yaseen N (2017) Predicting stock market behavior using data mining technique and news sentiment analysis. Int J Intell Syst Appl 9: 22–30.
    [6] Bahnsen AC, Aouada D, Stojanovic A (2016) Feature engineering strategies for credit card fraud detection. Expert Syst Appl 51: 134–142. doi: 10.1016/j.eswa.2015.12.030
    [7] Bahnsen AC, Stojanovic A, Aouada D, et al. (2013) Cost sensitive credit card fraud detection using bayes minimum risk. 2013 12th International Conference on Machine Learning and Applications.
    [8] Bhingarde A, Bangar A, Gupta K, et al. (2015) Credit card fraud detection using hidden markov model. Int J Comput Sci Inform Technol 76: 169–170.
    [9] Brummer C (2010) How International Financial Law Works (and How it Doesn't).
    [10] Cerullo MJ, Cerullo V (1999) Using neural networks to predict financial reporting fraud: part 2. Comput Fraud Secur 1999: 14–17.
    [11] Chen WS, Du YK (2009) Using neural networks and data mining techniques for the financial distress prediction model. Expert Syst Appl 36: 4075–4086. doi: 10.1016/j.eswa.2008.03.020
    [12] Cheng DL (2016) Application status and security risk analysis of artificial intelligence in financial field. Financ Technol Era 2016: 47–49.
    [13] Cheng J, He J, Yuan H, et al. (2017) Financial technology risks and regulatory countermeasures. China Financ 2017.
    [14] Chu AB (2018) Mobile Technology and financial inclusion. In: Handbook of Blockchain, Digital Finance, and Inclusion, 1 Eds., Cambridge: Academic Press, 131–44.
    [15] Du Jardin P (2010) Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy. Neurocomputing 73: 2047–2060. doi: 10.1016/j.neucom.2009.11.034
    [16] Fu K, Cheng D, Tu Y, et al. (2016) Credit card fraud detection using convolutional neural networks. International Conference on Neural Information Processing, 483–490.
    [17] Gutierrez FH, Levin SC, Chambers MA, et al. (2015) FinCEN proposes AML requirements for registered investment advisers. Bank Financ Serv Policy Rep 34:15–18.
    [18] Ibrahim A (2004) Chapter 6-Neural networks.
    [19] IDC (2016) Worldwide Semiannual Cognitive/Artificial Intelligence Systems Spending Guide.
    [20] Jiang HY, Wu CF (2016) Development status and regulatory suggestions of intelligent investment consultant. Secur Mark Guide.
    [21] Kaminski KA, Wetzel TS, Guan L (2004) Can financial ratios detect fraudulent financial reporting? Managerial Auditing J 19: 15–28.
    [22] Khandani AE, Kim AJ, Lo AW (2010) Consumer credit-risk models via machine-learning algorithms. J Bank Financ 34: 2767–2787. doi: 10.1016/j.jbankfin.2010.06.001
    [23] Khashman A (2011) Credit risk evaluation using neural networks: Emotional versus conventional models. Appl Soft Comput 11: 5477–5484. doi: 10.1016/j.asoc.2011.05.011
    [24] Killeen A, Chan R (2018) Global financial institutions 2.0, In: Handbook of Blockchain, Digital Finance, and Inclusion, 2 Eds., Amsterdam: Elsevier Inc, 213–242.
    [25] Kim D, Kwahk K (2013) Investigating the global financial markets from a social network analysis perspective. J Korean Oper Res Manage Sci Soc 38: 11–33.
    [26] Kim J (2018) Tasks and current status of the uses of artificial intelligence (fintech ai) in the fintech industry in the USA. J Payment Settlement 10: 185–214.
    [27] Korinek A, Stiglitz JE (2017) Artificial intelligence and its implications for income distribution and unemployment. Natl Bur Econ Res.
    [28] Koskivaara E (2004) Artificial neural networks in analytical review procedures. Manage Auditing J 19: 191–223. doi: 10.1108/02686900410517821
    [29] Kotsiantis S, Koumanakos E, Tzelepis D, et al. (2006) Forecasting fraudulent financial statements using data mining. Int J Comput Int 3: 104–110.
    [30] Kumar V, Rajan B, Venkatesan R, et al. (2019) Understanding the role of artificial intelligence in personalized engagement marketing. Calif Manage Rev 61: 135–155. doi: 10.1177/0008125619859317
    [31] Küükkocaolu G, Benli Y, Küçüksözen C (1997) Detecting the manipulation of financial information by using artificial neural network models. Istanbul Stock Exc Rev 9.
    [32] Lessmann S, Baesens B, Seow HV, et al. (2015) Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. Eur J Oper Res 247: 124–136. doi: 10.1016/j.ejor.2015.05.030
    [33] Li JZ (2012) Improving the management structure of consumer protection in banking institutions-Also commenting on the notice of China Banking Regulatory Commission on improving the customer complaint handling mechanism of banking financial institutions and doing a good job in financial consumer protection. Banker, 116–119.
    [34] Lin C, Chiu A, Huang SY, et al. (2015) Detecting the financial statement fraud: The analysis of the differences between data mining techniques and experts' judgments. Knowl Based Syst 89: 459–470. doi: 10.1016/j.knosys.2015.08.011
    [35] Ma SL, Wei FY (2018) Application of artificial intelligence technology in financial field: main difficulties and countermeasures. South Financ, 78–84.
    [36] Marcus C, Huang Z (2019) Artificial intelligence attacks: Artificial intelligence security vulnerabilities and countermeasures. Inform Secur Commun Secrecy, 72–81.
    [37] Mashrur A, Luo W, Zaidi NA, et al. (2020) Machine learning for financial risk management: A survey. IEEE Access 8: 203203–203223. doi: 10.1109/ACCESS.2020.3036322
    [38] McCauley D (2016) Ghosts in the Machine: Artificial Intelligence, Risks and Regulation in Financial Markets. London Thought Leadership Consulting. Available from: https://www.euromoneythoughtleadership.com/ghostsinthemachine/.
    [39] Mustafa M, Rahman M (2015) Financial inclusion and per capita real GSP growth across fifty US states and the district of Columbia: Evidence from panel cointegration and GMM estimates. Glob Bus Financ Rev 20: 87–94. doi: 10.17549/gbfr.2015.20.1.87
    [40] Pacelli V (2011) An artificial neural network approach for credit risk management. J Intell Learn Syst Appl 3: 103–112.
    [41] Patel CI, Labana D, Pandya S, et al. (2020) Histogram of oriented gradient-based fusion of features for human action recognition in action video sequences. Sensors 20: 7299.
    [42] Patel J, Shah S, Thakkar P, et al. (2015) Predecting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Syst Appl 42: 2162–2172. doi: 10.1016/j.eswa.2014.10.031
    [43] Ponemon L, Julian T, Lalan C (2016) IBM & Ponemon Institute Study: Data Breach Costs Rising, Now $4 million per Incident.
    [44] Sahin Y, Bulkan S, Duman E (2013) A cost-sensitive decision tree approach for fraud detection. Expert Syst Appl 40: 5916–5923. doi: 10.1016/j.eswa.2013.05.021
    [45] Schwab K (2017) Science and technology policy institute forum, In: The Fourth Industrial Revolution, 26 Eds., Geneva: Crown Publishing Group, 12–15.
    [46] Sureshkumar K, Elango N (2012) Performance analysis of stock price prediction using artificial neural network. Glob J Comput Sci Technol 12.
    [47] Swicegood P, Clark JA (2001) Off-site monitoring systems for predicting bank underperformance: a comparison of neural networks, discriminant analysis, and professional human judgment, intelligent. Syst Account Financ Manage 10: 169–186.
    [48] Timoshenko A, Hauser JR (2019) Identifying customer needs from user-generated content. Mark Sci 38.
    [49] Tractica (2015) Artificial Intelligence for Enterprise Applications: Deep Learning, Predictive Computing, Image Recognition, Speech Recognition, and Other AI Technologies for Enterprise Markets-Global Market Analysis and Forecasts. Available from: https://tractica.omdia.com/wp-content/uploads/2015/04/AIE-15-Brochure.pdf.
    [50] Tsai CF, Wu JW (2008) Using neural network ensembles for bankruptcy prediction and credit scoring. Expert Syst Appl 34: 2639–2649. doi: 10.1016/j.eswa.2007.05.019
    [51] Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49: 1225–1231. doi: 10.1016/S0895-4356(96)00002-9
    [52] Wang D (2017) Traditional financial institutions are ready to move. Is it more advantageous to set foot in intelligent investment advisory. China's Strategic Emerg Ind, 70–72.
    [53] Wong BK, Lai VS, Lam J (2000) A bibliography of neural network business applications research: 1994–1998. Comput Oper Res 27: 1045–1076. doi: 10.1016/S0305-0548(99)00142-2
    [54] Wu HD (2017) Institutional arrangement and legal regulation in the age of artificial intelligence. Legal Sci, 128–136.
    [55] Wu J, Chen L, Gao Y (2016) The application of foreign artificial intelligence in the field of financial investment advisory and its enlightenment to my country. Financ Asp, 88–92.
    [56] Wu C, Wu F, Liu J, et al. (2019) Neural demographic prediction using search query. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining.
    [57] Alvarez Y, Leguizamón-Páez MA, Londoño TJ (2020) Risks and security solutions existing in the Internet of things (IoT) in relation to Big Data. Ing Compet 23: 9–10.
    [58] Yu M (2019) Research on the current situation and development trend of marketing industry under the background of artificial intelligence. Wealth Life, 82–83.
    [59] Yu XJ, Peng YY (2017) Application and challenge of artificial intelligence in financial risk management. South Financ.
    [60] Yu L, Yue W, Wang S, et al. (2010) Support vector machine based multiagent ensemble learning for credit risk evaluation. Expert Syst Appl 37: 1351–1360. doi: 10.1016/j.eswa.2009.06.083
  • This article has been cited by:

    1. Juan Margallo Iribarnegaray, Ricardo García Luján, Isabel Pina Maíquez, Fernando Revuelta Salgado, José Alfaro Abreu, Eduardo de Miguel Poch, Montgomery T-Tube in the treatment of tracheal stenosis: Experience of a respiratory endoscopy unit and review of the literature, 2021, 57, 15792129, 72, 10.1016/j.arbr.2020.11.006
    2. Juan Margallo Iribarnegaray, Ricardo García Luján, Isabel Pina Maíquez, Fernando Revuelta Salgado, José Alfaro Abreu, Eduardo de Miguel Poch, Prótesis en T de Montgomery para el tratamiento de la estenosis traqueal: experiencia de una Unidad de Endoscopia Respiratoria y revisión de la literatura, 2021, 57, 03002896, 70, 10.1016/j.arbres.2020.07.012
    3. Yuhua Fan, Xin Li, Xing Fang, Yalan Liu, Suping Zhao, Zicheng Yu, Yaoyun Tang, Ping Wu, Antifibrotic Role of Nintedanib in Tracheal Stenosis After a Tracheal Wound, 2021, 131, 0023-852X, 10.1002/lary.29618
    4. Weitao Sun, Dan Zhao, Hongkun Wang, Acquired supraglottic stenosis, 2023, 46, 10159584, 1380, 10.1016/j.asjsur.2022.08.127
    5. Chung-Kan Tsao, Hui-Yi Hsiao, Ming-Huei Cheng, Wen-Bin Zhong, Tracheal Reconstruction with the Scaffolded Cartilage Sheets in an Orthotopic Animal Model, 2022, 28, 1937-3341, 685, 10.1089/ten.tea.2021.0193
    6. Adrien Ferney, Thibault Ferney, Ludovic Giraud, Amandine Briault, Marie-Pierre Aboussouan, Paul F. Castellanos, Ihab Atallah, Endoscopic management of adult subglottic stenosis: an alternative to open surgery, 2023, 280, 0937-4477, 1865, 10.1007/s00405-022-07733-9
    7. Bengi Yilmaz, Bilge Yilmaz Kara, Mathematical surface function-based design and 3D printing of airway stents, 2022, 8, 2365-6271, 10.1186/s41205-022-00154-8
    8. Fengjie Wu, Yangwei Yao, Yangyang Gu, Meng Yang, Enguo Chen, Huihui Hu, Jisong Zhang, Liangliang Dong, Yeli Zhu, Tao Huang, Application of Montgomery T-Tube Placement in Treating Cotton-Myer IV Subglottic Airway Atresia after Bi-Level Airway Recanalization, 2021, 2021, 1748-6718, 1, 10.1155/2021/5517536
    9. Raviv Allon, Saurabh Bhardwaj, Josué Sznitman, Hagit Shoffel-Havakuk, Sapir Pinhas, Elchanan Zloczower, Yael Shapira-Galitz, Yonatan Lahav, A Novel Trans-Tracheostomal Retrograde Inhalation Technique Increases Subglottic Drug Deposition Compared to Traditional Trans-Oral Inhalation, 2023, 15, 1999-4923, 903, 10.3390/pharmaceutics15030903
    10. Zhenyu Yang, Xiaoli Zhou, Wenying Pan, Daxiong Zeng, Junhong Jiang, Youfeng Zhu, Clinical Analysis of 32 Cases of Subglottic Benign Airway Stenosis Treated With Montgomery T Silicone Stent, 2024, 2024, 1198-2241, 10.1155/2024/2145560
    11. Jinmei Wei, Shujuan Qin, Wentao Li, Yan Chen, Tingmei Feng, Yuhui Wei, Sen Tan, Guangnan Liu, Analysis of clinical characteristics of 617 patients with benign airway stenosis, 2023, 10, 2296-858X, 10.3389/fmed.2023.1202309
    12. Yi-Ying Xiong, Chao-Yang Chen, Xiang Li, Xin-Xin Yue, Ze-Yu Zhao, Efficacy of a self-made tracheostomy oxygen delivery device for oxygen therapy during postoperative anesthesia recovery, 2024, 09287329, 1, 10.3233/THC-241184
    13. Sen-Ei Shai, Yi-Ling Lai, Chi-Wei Hsieh, Shih-Chieh Hung, A modified procedure of T-tube maneuver to treat tracheal total obstruction involving ablative bronchoscopy sparing open surgical intervention, 2023, 22, 26662507, 317, 10.1016/j.xjtc.2023.09.004
    14. Carina Escudero, Fernanda Chiarion Sassi, Ana Paula Ritto, Paulo Francisco Guerreiro Cardoso, Claudia Regina Furquim de Andrade, Clinical and swallowing characteristics of tracheostomized patients with post-intubation acquired tracheal or laryngotracheal stenosis, 2025, 80, 18075932, 100552, 10.1016/j.clinsp.2024.100552
    15. Weifei Li, Yanjie Hu, Yan Hu, Meng Zhou, Yuehua Li, Jun Peng, Relative Factors Analysis of the Occurrence and Location of Intratracheal Granuloma Following Tracheotomy, 2024, Volume 17, 1178-7074, 6355, 10.2147/IJGM.S493335
    16. 静 林, Emergency Experience of Sudden Asphyxia Combined with Traditional Chinese Medicine Affective Care in a Patient with Benign Airway Stenosis after Balloon Dilatation and Tracheotomy, 2025, 14, 2168-5657, 209, 10.12677/ns.2025.142028
    17. XiaoFeng Liu, Lei Li, FuYao Nan, JiaPing Liu, Heng Zou, Nan Zhang, HongWu Wang, Study on risk factors of Montgomery T-tube extraction in patients with post-tracheotomy tracheal stenosis based on Cox regression analysis, 2025, 25, 1471-2466, 10.1186/s12890-025-03732-8
  • Reader Comments
  • © 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(25058) PDF downloads(1287) Cited by(20)

Figures and Tables

Figures(5)

Other Articles By Authors

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog