1
|
Spinelli A, Carrano FM, Laino ME, Andreozzi M, Koleth G, Hassan C, Repici A, Chand M, Savevski V, Pellino G. Artificial intelligence in colorectal surgery: an AI-powered systematic review. Tech Coloproctol 2023; 27:615-629. [PMID: 36805890 DOI: 10.1007/s10151-023-02772-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/14/2022] [Accepted: 02/07/2023] [Indexed: 02/23/2023]
Abstract
Artificial intelligence (AI) has the potential to revolutionize surgery in the coming years. Still, it is essential to clarify what the meaningful current applications are and what can be reasonably expected. This AI-powered review assessed the role of AI in colorectal surgery. A Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compliant systematic search of PubMed, Embase, Scopus, Cochrane Library databases, and gray literature was conducted on all available articles on AI in colorectal surgery (from January 1 1997 to March 1 2021), aiming to define the perioperative applications of AI. Potentially eligible studies were identified using novel software powered by natural language processing (NLP) and machine learning (ML) technologies dedicated to systematic reviews. Out of 1238 articles identified, 115 were included in the final analysis. Available articles addressed the role of AI in several areas of interest. In the preoperative phase, AI can be used to define tailored treatment algorithms, support clinical decision-making, assess the risk of complications, and predict surgical outcomes and survival. Intraoperatively, AI-enhanced surgery and integration of AI in robotic platforms have been suggested. After surgery, AI can be implemented in the Enhanced Recovery after Surgery (ERAS) pathway. Additional areas of applications included the assessment of patient-reported outcomes, automated pathology assessment, and research. Available data on these aspects are limited, and AI in colorectal surgery is still in its infancy. However, the rapid evolution of technologies makes it likely that it will increasingly be incorporated into everyday practice.
Collapse
Affiliation(s)
- A Spinelli
- IRCCS Humanitas Research Hospital, via Manzoni 56, 20089, Rozzano, MI, Italy.
- Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20090, Pieve Emanuele, MI, Italy.
| | - F M Carrano
- IRCCS Humanitas Research Hospital, via Manzoni 56, 20089, Rozzano, MI, Italy
| | - M E Laino
- Artificial Intelligence Center, Humanitas Clinical and Research Center-IRCCS, Via A. Manzoni 56, 20089, Rozzano, MI, Italy
| | - M Andreozzi
- Department of Clinical Medicine and Surgery, University "Federico II" of Naples, Naples, Italy
| | - G Koleth
- Department of Gastroenterology and Hepatology, Hospital Selayang, Selangor, Malaysia
| | - C Hassan
- IRCCS Humanitas Research Hospital, via Manzoni 56, 20089, Rozzano, MI, Italy
| | - A Repici
- IRCCS Humanitas Research Hospital, via Manzoni 56, 20089, Rozzano, MI, Italy
| | - M Chand
- Wellcome EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - V Savevski
- Artificial Intelligence Center, Humanitas Clinical and Research Center-IRCCS, Via A. Manzoni 56, 20089, Rozzano, MI, Italy
| | - G Pellino
- Department of Advanced Medical and Surgical Sciences, Università degli Studi della Campania "Luigi Vanvitelli", Naples, Italy
- Colorectal Surgery, Vall d'Hebron University Hospital, Universitat Autonoma de Barcelona UAB, Barcelona, Spain
| |
Collapse
|
2
|
Scardino M, Di Matteo B, De Angelis A, Anzillotti G, Martorelli F, Simili V, Monteleone G, Bovio M, Tasso F, Laino ME, Tommasini T, Savevski V, Grappiolo G, Kon E, D'Amato T. Clinical efficacy of implementing a Patient Blood Management (PBM) Protocol in joint replacement surgery: a retrospective cohort study in a national referral center. Eur Rev Med Pharmacol Sci 2022; 26:9221-9229. [PMID: 36591834 DOI: 10.26355/eurrev_202212_30675] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
OBJECTIVE The aging of population has dramatically broadened the total number of Total Hip Arthroplasty (THA) and Total Knee Arthroplasty (TKA) performed worldwide. To optimize the number of blood transfusions performed, a multimodal and multidisciplinary approach was introduced, called Patient Blood Management (PBM). The aim of the present retrospective study is to evaluate the feasibility and clinical outcomes of a PBM protocol applied in a national referral center for joint replacement surgery. PATIENTS AND METHODS Clinical reports of 9,635 patients undergoing primary THA or TKA, from 2014 to 2019, were screened. The trends of hemoglobin value at admission and at day 4 after surgery were analyzed. Furthermore, the trend of blood bags' requests and blood transfusions was longitudinally evaluated to assess the efficacy of our PBM protocol and its potential impact in reducing the length of stay in the hospital. RESULTS In 2014, mean hemoglobin (Hb) levels at postoperative day 4 were 10.3 g/dl and 10.2 g/dl for TKA (unilateral and bilateral, respectively), and in 2019 were 11.3 g/dl and 11.6 g/dl (unilateral and bilateral, respectively, p=0.001). Total requested red blood cell (RBC) transfusions by each surgery over time have decreased for THA (277 in 2014 vs. 120 in 2019, p=0.001). A correlation matrix analysis between Hb level, body mass index (BMI), age, days spent in orthopedic (OR) ward and number of requested transfusions showed that RBC bags transfusions were related to the length of the hospital stay. CONCLUSIONS A timely application of a PBM protocol in the perioperative period of TKA and THA was significantly associated to the reduction of blood transfusions and total length of hospital stay, with clear benefits for both the patients and the hospital.
Collapse
Affiliation(s)
- M Scardino
- IRCCS Humanitas Research Hospital, Rozzano, Italy.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
3
|
Biamonte E, Levi R, Carrone F, Vena W, Brunetti A, Battaglia M, Garoli F, Savini G, Riva M, Ortolina A, Tomei M, Angelotti G, Laino ME, Savevski V, Mollura M, Fornari M, Barbieri R, Lania AG, Grimaldi M, Politi LS, Mazziotti G. Artificial intelligence-based radiomics on computed tomography of lumbar spine in subjects with fragility vertebral fractures. J Endocrinol Invest 2022; 45:2007-2017. [PMID: 35751803 DOI: 10.1007/s40618-022-01837-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Accepted: 06/06/2022] [Indexed: 10/17/2022]
Abstract
PURPOSE There is emerging evidence that radiomics analyses can improve detection of skeletal fragility. In this cross-sectional study, we evaluated radiomics features (RFs) on computed tomography (CT) images of the lumbar spine in subjects with or without fragility vertebral fractures (VFs). METHODS Two-hundred-forty consecutive individuals (mean age 60.4 ± 15.4, 130 males) were evaluated by radiomics analyses on opportunistic lumbar spine CT. VFs were diagnosed in 58 subjects by morphometric approach on CT or XR-ray spine (D4-L4) images. DXA measurement of bone mineral density (BMD) was performed on 17 subjects with VFs. RESULTS Twenty RFs were used to develop the machine learning model reaching 0.839 and 0.789 of AUROC in the train and test datasets, respectively. After correction for age, VFs were significantly associated with RFs obtained from non-fractured vertebrae indicating altered trabecular microarchitecture, such as low-gray level zone emphasis (LGLZE) [odds ratio (OR) 1.675, 95% confidence interval (CI) 1.215-2.310], gray level non-uniformity (GLN) (OR 1.403, 95% CI 1.023-1.924) and neighboring gray-tone difference matrix (NGTDM) contrast (OR 0.692, 95% CI 0.493-0.971). Noteworthy, no significant differences in LGLZE (p = 0.94), GLN (p = 0.40) and NGDTM contrast (p = 0.54) were found between fractured subjects with BMD T score < - 2.5 SD and those in whom VFs developed in absence of densitometric diagnosis of osteoporosis. CONCLUSIONS Artificial intelligence-based analyses on spine CT images identified RFs associated with fragility VFs. Future studies are needed to test the predictive value of RFs on opportunistic CT scans in identifying subjects with primary and secondary osteoporosis at high risk of fracture.
Collapse
Affiliation(s)
- E Biamonte
- Endocrinology, Diabetology and Medical Andrology Unit, IRCCS, Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - R Levi
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy
- Neuroradiology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - F Carrone
- Endocrinology, Diabetology and Medical Andrology Unit, IRCCS, Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - W Vena
- Endocrinology, Diabetology and Medical Andrology Unit, IRCCS, Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - A Brunetti
- Endocrinology, Diabetology and Medical Andrology Unit, IRCCS, Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - M Battaglia
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy
- Neuroradiology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - F Garoli
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy
- Neuroradiology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - G Savini
- Neuroradiology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - M Riva
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy
- Neurosurgery Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - A Ortolina
- Neurosurgery Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - M Tomei
- Neurosurgery Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - G Angelotti
- Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - M E Laino
- Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - V Savevski
- Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - M Mollura
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy
| | - M Fornari
- Neurosurgery Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - R Barbieri
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy
| | - A G Lania
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy
- Endocrinology, Diabetology and Medical Andrology Unit, IRCCS, Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - M Grimaldi
- Neuroradiology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| | - L S Politi
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy.
- Neuroradiology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy.
| | - G Mazziotti
- Department of Biomedical Sciences, Humanitas University, Via R. Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy
- Endocrinology, Diabetology and Medical Andrology Unit, IRCCS, Humanitas Research Hospital, Via Manzoni 56, Rozzano, 20089, Milan, Italy
| |
Collapse
|
4
|
Gohel S, Laino ME, Rajeev-Kumar G, Jenabi M, Peck K, Hatzoglou V, Tabar V, Holodny AI, Vachha B. Resting-State Functional Connectivity of the Middle Frontal Gyrus Can Predict Language Lateralization in Patients with Brain Tumors. AJNR Am J Neuroradiol 2019; 40:319-325. [PMID: 30630835 DOI: 10.3174/ajnr.a5932] [Citation(s) in RCA: 23] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2018] [Accepted: 11/12/2018] [Indexed: 01/28/2023]
Abstract
BACKGROUND AND PURPOSE A recent study using task-based fMRI demonstrated that the middle frontal gyrus is comparable with Broca's area in its ability to determine language laterality using a measure of verbal fluency. This study investigated whether the middle frontal gyrus can be used as an indicator for language-hemispheric dominance in patients with brain tumors using task-free resting-state fMRI. We hypothesized that no significant difference in language lateralization would occur between the middle frontal gyrus and Broca area and that the middle frontal gyrus can serve as a simple and reliable means of measuring language laterality. MATERIALS AND METHODS Using resting-state fMRI, we compared the middle frontal gyrus with the Broca area in 51 patients with glial neoplasms for voxel activation, the language laterality index, and the effect of tumor grade on the laterality index. The laterality index derived by resting-state fMRI and task-based fMRI was compared in a subset of 40 patients. RESULTS Voxel activations in the left middle frontal gyrus and left Broca area were positively correlated (r = 0.47, P < .001). Positive correlations were seen between the laterality index of the Broca area and middle frontal gyrus regions (r = 0.56, P < .0005). Twenty-seven of 40 patients (67.5%) showed concordance of the laterality index based on the Broca area using resting-state fMRI and the laterality index based on a language task. Thirty of 40 patients (75%) showed concordance of the laterality index based on the middle frontal gyrus using resting-state fMRI and the laterality index based on a language task. CONCLUSIONS The middle frontal gyrus is comparable with the Broca area in its ability to determine hemispheric dominance for language using resting-state fMRI. Our results suggest the addition of resting-state fMRI of the middle frontal gyrus to the list of noninvasive modalities that could be used in patients with gliomas to evaluate hemispheric dominance of language before tumor resection. In patients who cannot participate in traditional task-based fMRI, resting-state fMRI offers a task-free alternate to presurgically map the eloquent cortex.
Collapse
Affiliation(s)
- S Gohel
- From the Department of Health Informatics (S.G.), Rutgers University School of Health Professions, Newark, New Jersey
| | - M E Laino
- Departments of Radiology (M.E.L., M.J., K.P., V.H., A.I.H., B.V.).,Department of Radiology (M.E.L.), Catholic University of the Sacred Heart, Rome, Italy
| | - G Rajeev-Kumar
- Icahn School of Medicine at Mount Sinai (G.R.-K.), New York, New York
| | - M Jenabi
- Departments of Radiology (M.E.L., M.J., K.P., V.H., A.I.H., B.V.)
| | - K Peck
- Departments of Radiology (M.E.L., M.J., K.P., V.H., A.I.H., B.V.).,Medical Physics (K.P.)
| | - V Hatzoglou
- Departments of Radiology (M.E.L., M.J., K.P., V.H., A.I.H., B.V.)
| | - V Tabar
- Neurosurgery (V.T.), Memorial Sloan Kettering Cancer Center, New York, New York
| | - A I Holodny
- Departments of Radiology (M.E.L., M.J., K.P., V.H., A.I.H., B.V.)
| | - B Vachha
- Departments of Radiology (M.E.L., M.J., K.P., V.H., A.I.H., B.V.)
| |
Collapse
|