Abstract
Artificial intelligence is transforming healthcare. Artificial intelligence can improve patient care by analyzing large amounts of data to help make more informed decisions regarding treatments and enhance medical research through analyzing and interpreting data from clinical trials and research projects to identify subtle but meaningful trends beyond ordinary perception. Artificial intelligence refers to the simulation of human intelligence in computers, where systems of artificial intelligence can perform tasks that require human-like intelligence like speech recognition, visual perception, pattern-recognition, decision-making, and language processing. Artificial intelligence has several subdivisions, including machine learning, natural language processing, computer vision, and robotics. By automating specific routine tasks, artificial intelligence can improve healthcare efficiency. By leveraging machine learning algorithms, the systems of artificial intelligence can offer new opportunities for enhancing both the efficiency and effectiveness of surgical procedures, particularly regarding training of minimally invasive surgery. As artificial intelligence continues to advance, it is likely to play an increasingly significant role in the field of surgical learning. Physicians have assisted to a spreading role of artificial intelligence in the last decade. This involved different medical specialties such as ophthalmology, cardiology, urology, but also abdominal surgery. In addition to improvements in diagnosis, ascertainment of efficacy of treatment and autonomous actions, artificial intelligence has the potential to improve surgeons’ ability to better decide if acute surgery is indicated or not. The role of artificial intelligence in the emergency departments has also been investigated. We considered one of the most common condition the emergency surgeons have to face, acute appendicitis, to assess the state of the art of artificial intelligence in this frequent acute disease. The role of artificial intelligence in diagnosis and treatment of acute appendicitis will be discussed in this narrative review.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
Introduction
Artificial intelligence (AI) was born in the 1950s [1], spreading in various fields in the last years including statistics, psychology, linguistics, and also medicine and surgery [2,3,4,5,6]. Surgeons must take decision for a correct diagnosis and treatment during their daily activity. This is not always easy and AI could have a role in this scenario. In fact, the aim of AI in medicine is to solve real-life clinical problems, achieving a result that has to be similar or even better than human mind’s [7, 8]. Specific applications of AI in surgery are preoperative risk prediction, intraoperative video analysis and electronic health records. Physicians have assisted to a spreading role of AI in the last decade and this involved different medical specialties such as ophthalmology [9], cardiology [10], urology [11, 12], but also colorectal [13,14,15], gastric [16, 17], hepatobiliary and pancreatic surgery [18,19,20,21]. Its role in the emergency departments has also been investigated [22,23,24,25,26]. De Simone et al.[27, 28] conceived the Artificial Intelligence in Emergency and Trauma Surgery project aiming at increasing AI availability for emergency surgeons. They carried out a survey to assess the relationship between AI and the emergency surgeons. It came out that most of them has an interest in this field and believes that could be helpful in improving clinical outcomes and surgical education. We considered one of the most common condition the emergency surgeons have to face, acute appendicitis, to assess the state of the art of AI in this frequent acute disease. For this reason, the role of AI in diagnosis and treatment of acute appendicitis will be discussed in the next sections.
Terminology of AI
AI has various subfields (Table 1). Machine learning (ML) [29] is certainly the most developed branch. It is based on algorithms which provide answers from a statistical analysis on large datasets. ML can be supervised, in which input objects and a desired output value train a model, or unsupervised [6]. Among the supervised ML techniques, one of the most widely used is logistic regression (LR). It is a statistical model used in machine learning classification algorithms to obtain the probability of belonging to a certain class. LR belongs to generalized linear models (GLM), a flexible generalization of ordinary linear regression.
Another widely used supervised model is random forest (RF) [30]. It is an ensemble learning method for classification, regression and other tasks that operates by constructing a multitude of decision trees at the time of training. RF aim is to achieve good predictive results through randomization of predictive factors. Support vector machine (SVM) [31], k-nearest neighbors (K-NN) [32], naïve bayes (NB) [33] are other frequently used supervised ML models. Decision tree (DT) [34] is a ML model that represents a series of logical decisions made on the basis of attribute values. DT consists of a tree structure that is used to make decisions or predictions from input data. This large family is represented, amongst many, by gradient boosted tree (GBT), classification and regression tree (CART), and even RF, which combine the simplicity of decision trees with the flexibility and power of an ensemble model. Unlike supervised learning, unsupervised learning does not utilize a prespecified annotation; rather, it draws inferences from unlabeled data to identify patterns and/or structure within a data set. This type of learning can be useful in identifying relationships between groups (e.g., clustering) for further hypothesis generation [35].
Deep learning (DL) is a more complex form of ML, able to learn features and to use them for diagnostic purposes [36, 37]. The adjective “deep” refers to the use of multiple layers in the network. This branch is based on artificial neural networks (ANN), models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. Hence, they simulate the human brain and its neural connections. It is still underused in medicine because of its complexity [38].
AI in diagnosis of acute appendicitis
Diagnosis of appendicitis can sometimes be challenging even for the most experienced surgeons. The latest guidelines of the World Society of Emergency Surgery on diagnosis and treatment of appendicitis [39] indicate that an integration of clinical, biochemical markers and imaging is necessary for the diagnosis of this condition, considering factors as the patient’s age, gender and comorbidities. Diagnostic tools such as the Alvarado score, the appendicitis inflammatory response and the adult appendicitis score are sensitive enough to suspect acute appendicitis. Laboratory markers as leukocytosis or elevated C-reactive protein are helpful for arising suspect of this pathology, especially for the complicated forms [39]. The gold standard for appendicitis radiologic diagnosis remains abdominal ultrasound, if performed by an experienced operator, both for adults and children. Second level investigations, preferably low-dose CT-scan, are to be considered in doubtful cases.
The use of AI in the diagnosis of acute appendicitis is still emerging [40,41,42,43]. A small number of studies have been published so far. The achievements of various research proposed in recent years in the field of ML and sophisticated human anatomy designed DL have been remarkable [43,44,45]. The aim of several studies was primarily the diagnosis of acute appendicitis, but also the differentiation between complicated and uncomplicated forms [40,41,42, 46,47,48]. AI training was based on data as demographics (gender and age), clinical (abdominal pain or other associated symptoms), biomarkers (especially leucocyte counts and C-reactive protein), and imaging techniques (abdominal ultrasound or CT-scan). In most cases, the input data were represented by a different combination of these factors.
Among ML models used, RF has proven to be the most accurate for acute appendicitis diagnosis. According to a prospective study by Aydin et al. [49], after adequate pre-training with demographic, clinical and laboratory data, RF showed the best results in terms of accuracy, sensitivity and specificity against the other ML methods analyzed (area under the cure—AUC 0.99). This result was not only for the diagnosis of acute appendicitis, but also for detecting the complicated forms. RF optimal results in diagnosing appendicitis were also observed by Hsieh et al. [50], with percentages of accuracy, sensitivity and specificity above 90%; input data were represented by a combination of demographics, clinical and biomarkers. Anyhow, these results have a limited significance because of the retrospective nature of the study and the number of case series. On the other hand, reduced sensitivity and specificity of RF technique was found by Mijwil et al. [51]; in this study AI training was performed exclusively with laboratory data. Nevertheless, DT models were preferred because of their greater ease of interpretation and simplicity of use in medical practice. Additionally, in a recent Brunei study [52] DT predictive model proved very useful in diagnosing acute appendicitis, with accuracy rates of 97%.
Other ML models have been investigated, too. Among them, the GBT, followed by RF, has been shown to be particularly effective in diagnosing appendicitis according to Akmese et al. [47]. Catboost, a supervised GBT on DT algorithm able to work with categorical data, found 92% accuracy in distinguishing perforated from non-perforated acute appendicitis [53]. The primary focus of some recent studies has been the identification of complicated appendicitis, through ML techniques that have proven to be particularly accurate such as RF, SVM [54] and GBT [55]. Reisman et al. [56], using bootstrapping resampling machine learning techniques, discriminated between phlegmonous and gangrenous forms of acute appendicitis on the basis of an extensive genetic analysis of 56,666 genes, revealing how gene expression may underlie the pathophysiology of these disease patterns. K-NN, DT, SVM, CART, NB, linear and LR [57] are other ML models that have been tested, with less promising results [45].
In the last few years, DL, a subset of AI based on ANN, has been increasingly used, with excellent results. ANN have proven to be particularly effective for the diagnosis of acute appendicitis [43, 52]. Prabhudesai et al. [58] showed that the use of ANN was better to exclude false appendicitis compared to the clinic and Alvarado score, significantly. It showed a sensitivity of 100% and specificity of about 97%. Yoldaş et al. [59] showed comparable results in identifying acute appendicitis. In 2015, Park et al. [60] worked on a case series of 801 patients after pre-training with Alvarado score. ANN demonstrated to have a high sensitivity and specificity in diagnosing acute appendicitis (close to 100%) compared to Alvarado score (P < 0.001). Recently, a subset of ANN, the convolutional neural networks (CNN) have been used in the processing of AppendiXnet [61]. This 18-layer 3D CNN is a form of AI able to diagnose acute appendicitis using a training dataset of 438 CT-scan exams after pretraining on a large collection of YouTube human videos called Kinetics. This pretraining was able to significantly improve the performance of the model in detecting appendicitis from an AUC of 0.72 to 0.81. The role of AI as an aid for the diagnosis of acute appendicitis (Table 2) seems to be promising, with DL techniques as ANN that seem to prove superior to more classical ML techniques [44, 46, 57, 61]. Further studies, with more conspicuous and multicenter data, would certainly help in the validation of this important diagnostic tool.
AI in the prediction of acute appendicitis management
It is essential to state that the histopathological type of appendicitis directs the type of management [62]. In other words, predicting the kind of appendicitis can guide the choice of treatment. The appendicitis diagnosis could be, more simply, divided into only two subgroups: complicated appendicitis and uncomplicated appendicitis. This is because uncomplicated appendicitis can benefit from non-operative treatment. Diagnostic methods, including CT scans, are not very accurate in this distinction and they cannot be relied upon for defining when non-operative management can be used. In the study by Liang et al. [63] was developed a combined model with CatBoost based on selected clinical characteristics, CT visual features, deep learning features and radiomics features. They externally validated this combined model and compared it both with the DL radiomics model and the radiologist’s visual diagnosis through receiver operating characteristic curve analysis. In this context, a combined use of DL and radiomics model was effective in distinguishing complicated from uncomplicated forms, and therefore, in predicting patients who can benefit from non-operative management, with good accuracy.
There are three histopathological categories of acute appendicitis: simple appendicitis (SA), purulent appendicitis (PA) and gangrenous or perforated appendicitis (GPA). According to Kang et al. [64] peripheral blood biomarkers can recognize the pathological type of SA from PA and GPA. They collected the basic information and preoperative clinical and laboratory data of 146 patients diagnosed with acute appendicitis from the electronic medical records system, retrospectively. These included: age, gender, clinical sign and symptom scores, laboratory records: blood routine, coagulation, blood biochemistry, white blood cells, neutrophils, lymphocytes CD3+ T, CD4+ T, CD8+ T, CD19+ T, CD16+ 56+, natural killer, total T cell counts, helper T cell counts, inhibitors T, B cell counts, natural killer cell counts, CD4+/CD8+ ratio, C-reactive protein, procalcitonin and neutrophil to lymphocyte ratio. Two datasets involving SA and PA, or PA and GPA data, were organized, retrospectively. The two groups were named SA/PA and PA/GPA. Afterwards, ML logistic regression models were built. It showed that nausea and vomiting, abdominal pain time, neutrophils, CD4+ T cell, helper T cell, B lymphocyte, natural killer cell counts and CD4+/CD8+ ratio were predictive features for the SA/PA group. On the other hand, nausea and vomiting, abdominal pain time, the highest temperature, CD8+ T cell, procalcitonin and C-reactive protein were prevalent in the PA/GPA group. This information obtained thanks to AI can guide the therapeutic choice both regarding the surgical approach and the possible use of antibiotics.
Marcinkevics et al. [65] developed a user-friendly online appendicitis prediction tool for children with suspected appendicitis. In detail, they used ML techniques based on retrospective data from 430 children, to establish diagnosis, severity and management of appendicitis. The model could differentiate patients requiring primary surgery from those suitable for conservative management with or without antibiotics, identifying the characteristics determining a spontaneous regression of acute appendicitis. Although there is still few evidence in the literature, the aid of AI in identifying type and severity of appendicitis seems to guide the choice of treatment, avoiding surgery when not indicated (Table 3).
AI in the prediction of postoperative complications of appendectomy
There are few data on the use of AI in investigating the outcome of patients undergoing appendectomy for acute appendicitis. The onset of intra-abdominal abscesses is the most frequent postoperative complication of such operations, especially in cases of complicated acute appendicitis [66]. The use of AI in relation to the occurrence of this complication has been poorly investigated. The most widespread studies in the literature focus on ML methods analyzing the surgical outcome of these patients. With the aid of RF techniques, after training with demographic, clinical and biomarker data, Eickhoff et al. [67] showed how the surgical outcome of patients with perforated appendicitis can be influenced by these factors. Outcomes such as the need for intensive postoperative treatment longer than 24 h and prolonged hospitalization longer than 7–15 days were predicted with high accuracy rates (88 and 76%, respectively).
Sepsis, a rare complication after appendectomy, was also investigated [68]. Various ML algorithms were used on a dataset of 223,214 appendectomy patients. LR, RF and GBT were the most accurate in predicting the occurrence of sepsis in these patients. After AI training with demographic, clinical and laboratory data, factors such as cardiac heart failure, exacerbation or diagnosis, acute renal failure and preoperative transfusion were significantly associated with the onset of postoperative sepsis. On the other hand, singular was the study by Ghomrawi et al. [69], in which a consumer-grade wearable device named Fitbit was used in the postoperative monitoring of appendectomy pediatric patients. This device was able to monitor parameters such as heart rate, physical activity and sleep pattern after discharge and associate them with the onset of postoperative symptoms or complications. These inputs, together with clinical and demographic data, allowed the development of ML models, specifically a balanced RF classifier capable of detecting with 83% of accuracy complicated appendicitis and with 70% of accuracy simple appendicitis, underlying such abnormal postoperative courses.
Only one study investigated ANN techniques in relation to postoperative complications. Indeed, according to a recent US study of 1574 patients, two ANNs with different architecture were able to predict post-appendicectomy abscess formation with high rates of accuracy, sensitivity and specificity, based on variables such as postoperative white blood cell count, intraoperative diagnosis, duration of surgery, antibiotic therapy completed, body temperature on the date of imaging and weight [70].
Hence, an increasing number of studies are focusing not only on the diagnosis of appendicitis but even on postoperative complications, to predict an abnormal course at an early stage and reduce the risks for the patient (Table 4).
Conclusion
AI in surgery is not limited to ML, DL, natural language processing, and computer vision. The dream of autonomous actions in surgery is already here, albeit, in limited ways. Surgeons must understand the basics of AI and learn to better understand its potential benefits instead of insisting on resisting innovation. The use of AI really seems to be a valuable tool in helping patients suffering from acute appendicitis, not only in diagnosing the condition but also in guiding treatment, whether surgical or not, and in preventing postoperative complications. Unfortunately, its use is still not so frequent and its application in clinical practice limited. This is due to the fact that some changes should be made in medical regulation and insurance for allowing its diffusion. Moreover, clinicians should be trained to use it and liaise with digital experts. Its application will spread in the next years, probably. In our opinion, considering its cost and the needed training, it will involve the academic hospitals at first, mainly. Further studies are needed to understand which method is more effective than others regarding acute appendicitis, but the results seem promising so far.
Data availability
Not applicable.
References
Turing AM (1950) Computing machinery and intelligence. Mind 59(236):433–460
Stajic J, Stone R, Chin G, Wible B (2015) Artificial intelligence. Rise of the machines. Science 349(6245):248–249
Bohannon J (2015) Artificial intelligence. The synthetic therapist. Science 349(6245):250–251
Buch VH, Ahmed I, Maruthappu M (2018) Artificial intelligence in medicine: current trends and future possibilities. Br J Gen Pract 68(668):143–144
Allen MR, Webb S, Mandvi A, Frieden M, Tai-Seale M, Kallenberg G (2024) Navigating the doctor-patient-AI relationship—a mixed-methods study of physician attitudes toward artificial intelligence in primary care. BMC Prim Care 25(1):42
Hashimoto DA, Rosman G, Rus D, Meireles OR (2018) Artificial intelligence in surgery: promises and perils. Ann Surg 268(1):70–76
Kaul V, Enslin S, Gross SA (2020) History of artificial intelligence in medicine. Gastrointest Endosc 92(4):807–812
Loftus TJ, Altieri MS, Balch JA, Abbott KL, Choi J, Marwaha JS, Hashimoto DA, Brat GA, Raftopoulos Y, Evans HL et al (2023) Artificial intelligence-enabled decision support in surgery: state-of-the-art and future directions. Ann Surg 278(1):51–58
Keskinbora K, Guven F (2020) Artificial intelligence and ophthalmology. Turk J Ophthalmol 50(1):37–43
Itchhaporia D (2022) Artificial intelligence in cardiology. Trends Cardiovasc Med 32(1):34–41
Dasgupta P (2019) Artificial intelligence, three-dimensional printing and global health. BJU Int 124(6):897
Park T, Gu P, Kim CH, Kim KT, Chung KJ, Kim TB, Jung H, Yoon SJ, Oh JK (2023) Artificial intelligence in urologic oncology: the actual clinical practice results of IBM Watson for Oncology in South Korea. Prostate Int 11(4):218–221
Martinez-Romero M, Vazquez-Naya JM, Rabunal JR, Pita-Fernandez S, Macenlle R, Castro-Alvarino J, Lopez-Roses L, Ulla JL, Martinez-Calvo AV, Vazquez S et al (2010) Artificial intelligence techniques for colorectal cancer drug metabolism: ontology and complex network. Curr Drug Metab 11(4):347–368
Rao HB, Sastry NB, Venu RP, Pattanayak P (2022) The role of artificial intelligence based systems for cost optimization in colorectal cancer prevention programs. Front Artif Intell 5:955399
Das K, Paltani M, Tripathi PK, Kumar R, Verma S, Kumar S, Jain CK (2023) Current implications and challenges of artificial intelligence technologies in therapeutic intervention of colorectal cancer. Explor Target Antitumor Ther 4(6):1286–1300
Jin P, Ji X, Kang W, Li Y, Liu H, Ma F, Ma S, Hu H, Li W, Tian Y (2020) Artificial intelligence in gastric cancer: a systematic review. J Cancer Res Clin Oncol 146(9):2339–2350
Kuwayama N, Hoshino I, Mori Y, Yokota H, Iwatate Y, Uno T (2023) Applying artificial intelligence using routine clinical data for preoperative diagnosis and prognosis evaluation of gastric cancer. Oncol Lett 26(5):499
Veerankutty FH, Jayan G, Yadav MK, Manoj KS, Yadav A, Nair SRS, Shabeerali TU, Yeldho V, Sasidharan M, Rather SA (2021) Artificial Intelligence in hepatology, liver surgery and transplantation: emerging applications and frontiers of research. World J Hepatol 13(12):1977–1990
Han IW, Cho K, Ryu Y, Shin SH, Heo JS, Choi DW, Chung MJ, Kwon OC, Cho BH (2020) Risk prediction platform for pancreatic fistula after pancreatoduodenectomy using artificial intelligence. World J Gastroenterol 26(30):4453–4464
Machry M, Ferreira LF, Lucchese AM, Kalil AN, Feier FH (2023) Liver volumetric and anatomic assessment in living donor liver transplantation: the role of modern imaging and artificial intelligence. World J Transplant 13(6):290–298
Yu YD, Lee KS, Man Kim J, Ryu JH, Lee JG, Lee KW, Kim BW, Kim DS (2022) Korean Organ Transplantation Registry Study G: Artificial intelligence for predicting survival following deceased donor liver transplantation: retrospective multi-center study. Int J Surg 105:106838
Clarke JR, Cebula DP, Webber BL (1988) Artificial intelligence: a computerized decision aid for trauma. J Trauma 28(8):1250–1254
Kim D, You S, So S, Lee J, Yook S, Jang DP, Kim IY, Park E, Cho K, Cha WC et al (2018) A data-driven artificial intelligence model for remote triage in the prehospital environment. PLoS ONE 13(10):e0206006
Stonko DP, Guillamondegui OD, Fischer PE, Dennis BM (2021) Artificial intelligence in trauma systems. Surgery 169(6):1295–1299
Litvin A, Korenev S, Rumovskaya S, Sartelli M, Baiocchi G, Biffl WL, Coccolini F, Di Saverio S, Kelly MD, Kluger Y et al (2021) WSES project on decision support systems based on artificial neural networks in emergency surgery. World J Emerg Surg 16(1):50
Cobianchi L, Piccolo D, Dal Mas F, Agnoletti V, Ansaloni L, Balch J, Biffl W, Butturini G, Catena F, Coccolini F et al (2023) Surgeons’ perspectives on artificial intelligence to support clinical decision-making in trauma and emergency contexts: results from an international survey. World J Emerg Surg 18(1):1
De Simone B, Abu-Zidan FM, Gumbs AA, Chouillard E, Di Saverio S, Sartelli M, Coccolini F, Ansaloni L, Collins T, Kluger Y et al (2022) Knowledge, attitude, and practice of artificial intelligence in emergency and trauma surgery, the ARIES project: an international web-based survey. World J Emerg Surg 17(1):10
De Simone B, Chouillard E, Gumbs AA, Loftus TJ, Kaafarani H, Catena F (2022) Artificial intelligence in surgery: the emergency surgeon’s perspective (the ARIES project). Discov Health Syst 1(1):9
Rowe M (2019) An introduction to machine learning for clinicians. Acad Med 94(10):1433–1436
Rigatti SJ (2017) Random forest. J Insur Med 47(1):31–39
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Mohanty S, Harun Ai Rashid M, Mridul M, Mohanty C, Swayamsiddha S (2020) Application of artificial intelligence in COVID-19 drug repurposing. Diabetes Metab Syndr 14(5):1027–1031
Langarizadeh M, Moghbeli F (2016) Applying Naive Bayesian networks to disease prediction: a systematic review. Acta Inform Med 24(5):364–369
Podgorelec V, Kokol P, Stiglic B, Rozman I (2002) Decision trees: an overview and their use in medicine. J Med Syst 26(5):445–463
Hashimoto DA, Ward TM, Meireles OR (2020) The role of artificial intelligence in surgery. Adv Surg 54:89–101
Wang F, Zhang Z, Wu K, Jian D, Chen Q, Zhang C, Dong Y, He X, Dong L (2023) Artificial intelligence techniques for ground fault line selection in power systems: state-of-the-art and research challenges. Math Biosci Eng 20(8):14518–14549
Howell MD, Corrado GS, DeSalvo KB (2024) Three epochs of artificial intelligence in health care. JAMA 331(3):242–244
Zou J, Han Y, So SS (2008) Overview of artificial neural networks. Methods Mol Biol 458:15–23
Di Saverio S, Podda M, De Simone B, Ceresoli M, Augustin G, Gori A, Boermeester M, Sartelli M, Coccolini F, Tarasconi A et al (2020) Diagnosis and treatment of acute appendicitis: 2020 update of the WSES Jerusalem guidelines. World J Emerg Surg 15(1):27
Nie D, Zhan Y, Xu K, Zou H, Li K, Chen L, Chen Q, Zheng W, Peng X, Yu M et al (2023) Artificial intelligence differentiates abdominal Henoch–Schonlein purpura from acute appendicitis in children. Int J Rheum Dis 26(12):2534–2542
Gracias D, Siu A, Seth I, Dooreemeah D, Lee A (2023) Exploring the role of an artificial intelligence chatbot on appendicitis management: an experimental study on ChatGPT. ANZ J Surg. https://doi.org/10.1111/ans.18736
Rey R, Gualtieri R, La Scala G, Posfay Barbe KM (2024) Artificial intelligence in the diagnosis and management of appendicitis in pediatric departments: a systematic review. Eur J Pediatr Surg. https://doi.org/10.1055/a-2257-5122
Issaiy M, Zarei D, Saghazadeh A (2023) Artificial intelligence and acute appendicitis: a systematic review of diagnostic and prognostic models. World J Emerg Surg 18(1):59
Sakai S, Kobayashi K, Toyabe S, Mandai N, Kanda T, Akazawa K (2007) Comparison of the levels of accuracy of an artificial neural network model and a logistic regression model for the diagnosis of acute appendicitis. J Med Syst 31(5):357–364
Ghareeb WM, Emile SH, Elshobaky A (2022) Artificial intelligence compared to Alvarado scoring system alone or combined with ultrasound criteria in the diagnosis of acute appendicitis. J Gastrointest Surg 26(3):655–658
Lam A, Squires E, Tan S, Swen NJ, Barilla A, Kovoor J, Gupta A, Bacchi S, Khurana S (2023) Artificial intelligence for predicting acute appendicitis: a systematic review. ANZ J Surg 93(9):2070–2078
Akmese OF, Dogan G, Kor H, Erbay H, Demir E (2020) The use of machine learning approaches for the diagnosis of acute appendicitis. Emerg Med Int 2020:7306435
Akgul F, Er A, Ulusoy E, Caglar A, Citlenbik H, Keskinoglu P, Sisman AR, Karakus OZ, Ozer E, Duman M et al (2021) Integration of physical examination, old and new biomarkers, and ultrasonography by using neural networks for pediatric appendicitis. Pediatr Emerg Care 37(12):e1075–e1081
Aydin E, Turkmen IU, Namli G, Ozturk C, Esen AB, Eray YN, Eroglu E, Akova F (2020) A novel and simple machine learning algorithm for preoperative diagnosis of acute appendicitis in children. Pediatr Surg Int 36(6):735–742
Hsieh CH, Lu RH, Lee NH, Chiu WT, Hsu MH, Li YC (2011) Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery 149(1):87–93
Mijwil MM, Aggarwal K (2022) A diagnostic testing for people with appendicitis using machine learning techniques. Multimed Tools Appl 81(5):7011–7023
Shikha A, Kasem A (2023) The development and validation of artificial intelligence pediatric appendicitis decision-tree for children 0 to 12 years old. Eur J Pediatr Surg 33(5):395–402
Akbulut S, Yagin FH, Cicek IB, Koc C, Colak C, Yilmaz S (2023) Prediction of perforated and nonperforated acute appendicitis using machine learning-based explainable artificial intelligence. Diagnostics (Basel) 13(6):1173
Xia J, Wang Z, Yang D, Li R, Liang G, Chen H, Heidari AA, Turabieh H, Mafarja M, Pan Z (2022) Performance optimization of support vector machine with oppositional grasshopper optimization for acute appendicitis diagnosis. Comput Biol Med 143:105206
Phan-Mai TA, Thai TT, Mai TQ, Vu KA, Mai CC, Nguyen DA (2023) Validity of machine learning in detecting complicated appendicitis in a resource-limited setting: findings from Vietnam. Biomed Res Int 2023:5013812
Reismann J, Romualdi A, Kiss N, Minderjahn MI, Kallarackal J, Schad M, Reismann M (2019) Diagnosis and classification of pediatric acute appendicitis by artificial intelligence methods: an investigator-independent approach. PLoS ONE 14(9):e0222030
Reismann J, Kiss N, Reismann M (2021) The application of artificial intelligence methods to gene expression data for differentiation of uncomplicated and complicated appendicitis in children and adolescents—a proof of concept study. BMC Pediatr 21(1):268
Prabhudesai SG, Gould S, Rekhraj S, Tekkis PP, Glazer G, Ziprin P (2008) Artificial neural networks: useful aid in diagnosing acute appendicitis. World J Surg 32(2):305–309; discussion 310–301
Yoldas O, Tez M, Karaca T (2012) Artificial neural networks in the diagnosis of acute appendicitis. Am J Emerg Med 30(7):1245–1247
Park SY, Kim SM (2015) Acute appendicitis diagnosis using artificial neural networks. Technol Health Care 23(Suppl 2):S559-565
Rajpurkar P, Park A, Irvin J, Chute C, Bereket M, Mastrodicasa D, Langlotz CP, Lungren MP, Ng AY, Patel BN (2020) AppendiXNet: deep learning for diagnosis of appendicitis from a small dataset of CT exams using video pretraining. Sci Rep 10(1):3958
Bhangu A, Soreide K, Di Saverio S, Assarsson JH, Drake FT (2015) Acute appendicitis: modern understanding of pathogenesis, diagnosis, and management. Lancet 386(10000):1278–1287
Liang D, Fan Y, Zeng Y, Zhou H, Zhou H, Li G, Liang Y, Zhong Z, Chen D, Chen A et al. (2023) Development and validation of a deep learning and radiomics combined model for differentiating complicated from uncomplicated acute appendicitis. Acad Radiol. https://doi.org/10.1016/j.acra.2023.08.018
Kang CB, Li XW, Hou SY, Chi XQ, Shan HF, Zhang QJ, Li XB, Zhang J, Liu TJ (2021) Preoperatively predicting the pathological types of acute appendicitis using machine learning based on peripheral blood biomarkers and clinical features: a retrospective study. Ann Transl Med 9(10):835
Marcinkevics R, Reis Wolfertstetter P, Wellmann S, Knorr C, Vogt JE (2021) Using machine learning to predict the diagnosis, management and severity of pediatric appendicitis. Front Pediatr 9:662183
Gupta R, Sample C, Bamehriz F, Birch DW (2006) Infectious complications following laparoscopic appendectomy. Can J Surg 49(6):397–400
Eickhoff RM, Bulla A, Eickhoff SB, Heise D, Helmedag M, Kroh A, Schmitz SM, Klink CD, Neumann UP, Lambertz A (2022) Machine learning prediction model for postoperative outcome after perforated appendicitis. Langenbecks Arch Surg 407(2):789–795
Bunn C, Kulshrestha S, Boyda J, Balasubramanian N, Birch S, Karabayir I, Baker M, Luchette F, Modave F, Akbilgic O (2021) Application of machine learning to the prediction of postoperative sepsis after appendectomy. Surgery 169(3):671–677
Ghomrawi HMK, O’Brien MK, Carter M, Macaluso R, Khazanchi R, Fanton M, DeBoer C, Linton SC, Zeineddin S, Pitt JB et al (2023) Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy. NPJ Digit Med 6(1):148
Alramadhan MM, Al Khatib HS, Murphy JR, Tsao K, Chang ML (2022) Using artificial neural networks to predict intra-abdominal abscess risk post-appendectomy. Ann Surg Open 3(2):e168
Funding
Open access funding provided by Università Cattolica del Sacro Cuore within the CRUI-CARE Agreement.
Author information
Authors and Affiliations
Contributions
Bianchi V.: conceptualization, methodology, writing—original draft, writing—reviewing and editing. Giambusso M.: conceptualization, methodology, data curation, formal analysis, writing—original draft. De Jacob A.: investigation, formal analysis, data curation. Chiarello MM: writing—reviewing and editing. Brisinda G.: conceptualization, methodology, data curation, formal analysis, writing -reviewing and editing. All the authors read and approved the final manuscript. Bianchi V. and Giambusso M. equally contributed to the drafting of the manuscript and must both be considered first author.
Corresponding author
Ethics declarations
Conflict of interest
All authors meet the criteria for authorship and have participated in writing this manuscript. There was no conflict of interest for any of the author. Moreover, none of the authors of the study have received subsidies from Public Bodies or from any other sources for the execution of this study.
Ethical standards
All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1964 and later versions.
Research involving human participants and/or animals
This article does not contain any experimental studies with human participants or animal performed by any of the authors. The research protocol has been notified to the local IRB. Ethical review and approval were waived for this study due to the study is a narrative review of the literature.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Bianchi, V., Giambusso, M., De Iacob, A. et al. Artificial intelligence in the diagnosis and treatment of acute appendicitis: a narrative review. Updates Surg 76, 783–792 (2024). https://doi.org/10.1007/s13304-024-01801-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13304-024-01801-x