Negli ultimi anni le informazioni digitali di tutto il mondo sono più che raddoppiate e questa tendenza è destinata ad aumentare in modo esponenziale generando enormi moli di dati elettronici: i big data. La medicina è uno dei principali protagonisti della crescita esponenziale dei big data, a motivo di quattro importanti fenomeni: la digitalizzazione della diagnostica per immagini, la reportistica digitale in sostituzione delle cartelle cartacee, lo sviluppo di biotecnologie impiegate nel campo delle cosiddette scienze “omiche”, l’esplosione del cosiddetto IoMT (internet of medical things). Necessaria a questo punto una sintesi e un glossario in tema di tecnologie di intelligenza artificiale e medicina, e una revisione sulle principali criticità che il loro utilizzo può generare. AMD ha provato a fare il punto con il documento Intelligenza artificiale e big data in ambito diabetologico. La prospettiva di AMD pubblicato nel 2018. Approfittando dell’esperienza acquisita in occasione della sua stesura, abbiamo intervistato sul tema Alberto De Micheli, Giacomo Guaita e Paola Ponzani, tra gli autori del documento.
a cura di Miryam Ciotola per il gruppo ComunicAzione
Alberto De Micheli, considerato gli argomenti trattati nel documento, quanto è stato complesso sistematizzare queste tematiche?
La difficoltà è nata dall’affrontare un tema nuovo e diverso rispetto alle abituali competenze dei medici, tradizionalmente cliniche o fisiopatologiche, più recentemente anche organizzative, ma molto lontane dalla logica delle macchine pensanti. In tale prospettiva è stato indispensabile e fondamentale la collaborazione di esperti della materia, a cui siamo molto grati per il rispettivo contributo.
Quali le fasi del processo?
L’iter è stato per fasi. Prima fase: creare prioritariamente un glossario indispensabile, che sintetizzasse con chiarezza non equivocabile e soprattutto in termini pratici, quello di cui stavamo parlando. Seconda fase: l’analisi e il tentativo di valutare le prospettive, i vantaggi e i possibili limiti dell’utilizzo delle diverse tecniche nell’ambito medico e anche più specificamente nell’ambito della gestione del diabete e delle patologie croniche. Terza fase: la riflessione critica specifica sugli aspetti conoscitivi, applicativi ed etici, fortunatamente supportata da una vasta letteratura, dato il grandissimo interesse suscitato nel mondo medico dalle prospettive aperte dall’intelligenza artificiale.
Paola Ponzani, uno dei temi cardine dell’argomento è la refertazione automatica. Quali sono i benefici?
Gli ambiti di applicazione dell’intelligenza artificiale in medicina sono molteplici, dalla ricerca al campo della gestione, dalla cura del paziente alla diagnostica. Ed è proprio in quest’ultima area che i software di intelligenza artificiale già oggi permettono di ottenere grandi benefici. Il deep learning ad esempio consente, unitamente a tecniche di visual and pattern recognition, di identificare le caratteristiche con il più alto valore predittivo direttamente dalle immagini, su un ampio set di dati di esempi, consentendo cosi una refertazione automatizzata ad alta sensibilità e specificità, ad esempio delle immagini della retina.
Vantaggi?
Consente un aumento dell’efficienza e della riproducibilità, una copertura dei programmi di screening, fornendo diagnosi e trattamento precoci, snellendo e facilitando il lavoro del medico.
E noi diabetologi possiamo considerarci pronti a questo cambiamento?
Il diabetologo più di altri professionisti ha già la mentalità adatta, pronta a raccogliere questa innovazione: la cultura del dato è nel suo DNA, la necessità di fenotipizzare il paziente e personalizzare la cura e l’approccio terapeutico sono da tempo sue priorità, le competenze per gestire una malattia complessa come il diabete sono state affinate nel tempo, spaziando tra quelle tecnologiche a quelle comunicative, da quelle educative e andragogiche a quelle gestionali e manageriali. Grazie a tutto questo percorso compiuto negli anni e fortemente voluto da AMD, siamo pronti per una nuova sfida nella gestione della Diabetologia.
Alberto De Micheli, il flusso di questa immensa mole di dati deve avere una regolamentazione precisa per quanto riguarda gli aspetti della privacy. A che punto siamo in proposito?
La normativa esiste ma è in evoluzione, sia perché ogni nuovo progresso tecnologico pone problematiche nuove e sia perché all’evolvere delle tecniche di deidentificazione segue una altrettanto rapida evoluzione delle tecniche di reidentificazione. Il prezzo dell’innovazione non può essere l’erosione del diritto fondamentale alla privacy quindi sono necessarie regole e leggi ad hoc, che mantengano i principi legali fondamentali in sincronia e sintonia con la continua evoluzione tecnologica.
E coniugare l’intelligenza artificiale con la medicina personalizzata, è possibile?
Certamente. I dati analizzati dall’intelligenza artificiale sui grandi numeri sono la base per la medicina personalizzata, che non è certamente medicina soggettiva.
Come?
Pensiamo per esempio alla prescrizione di analisi appropriate per tipologia e tempistiche sulla base delle caratteristiche dei pazienti, attraverso l’individuazione di fenotipi specifici nell’ambito della malattia; alla valutazione di rischi individuali o di fattori prognostici per prescrivere azioni ad hoc; alla ricerca sulla radice genetica delle malattie per ottimizzarne il trattamento e la prevenzione; alla prescrizione di farmaci personalizzata sulla base delle caratteristiche cliniche e genetiche del paziente… E potremmo fornire innumerevoli altri esempi.
Paola Ponzani, quali potranno essere i vantaggi della “salute digitale” per la diabetologia?
La diabetologia si trova ad affrontare diverse sfide: il numero sempre minore di diabetologi, il numero crescente dei pazienti, la riduzione del tempo di visita, la sempre maggiore complessità della patologia sia dal punto di vista clinico sia assistenziale, la difficoltà di raggiungimento degli obiettivi, l’accessibilità alle cure e la sostenibilità. Le nuove tecnologie digitali e l’utilizzo dell’intelligenza artificiale rappresentano sicuramente una grande opportunità per tutto questo.
Facciamo un esempio concreto?
Grazie al machine learning, è possibile effettuare analisi descrittive, predittive e prescrittive su grandi database provenienti da fonti diverse, non analizzabili con la statistica tradizionale. È possibile effettuare una migliore valutazione del rischio di patologia nella popolazione generale, è possibile identificare nuove variabili e nuovi fattori di rischio, identificare le strategie terapeutiche più efficaci a seconda della tipologia di paziente.
Giacomo Guaita, nel documento si parla di population health management. Al di là dell’inglesismo?
In realtà, come spesso accade, è un’espressione mutuata dal mondo anglo-sassone in quanto si tratta di un modello di governo clinico che è stato ideato e applicato per la prima volta in quei sistemi sanitari. Il modello ha l’ambizione di garantire la salute delle persone per tutto l’arco della vita, è rivolto alla prevenzione, riduzione, rallentamento e cura delle patologie croniche, con delle direzioni strategiche ben precise: coinvolgere e responsabilizzare gli assistiti, riorientare il modello di cura e il coordinamento dei servizi, adottare ed estendere la proattività e quindi l’equità delle cure, creare un ambiente professionale favorevole allo sviluppo di una cultura organizzativa improntata alla condivisione.
Il diabete è l’esempio paradigmatico di patologia cronica, ma è possibile applicare l’intelligenza artificiale al chronic care model?
Il chronic care model cerca di migliorare i risultati di salute anche attraverso strumenti di business intelligence per aggregare i dati e fornire un quadro clinico completo di ciascun paziente. Utilizzando i dati, si possono monitorare e migliorare i risultati clinici riducendo al contempo i costi. Riunendo dati clinici ed economico-finanziari si possono ottenere parametri analitici utili per migliorare l’efficienza e la cura del paziente sfruttando l’intelligenza artificiale si possono fornire informazioni in tempo reale sia ai medici che agli amministratori con evidenti vantaggi rispetto alla identificazione di problematiche assistenziali.
Quando parliamo di intelligenza artificiale non possiamo dimenticare costi e risorse…
La sostenibilità economica è un aspetto ineludibile, specialmente a fronte dell’innovazione tecnologica che procede a ritmi esponenziali e con costi conseguentemente elevatissimi. Ma proprio per questo ritengo che l’adozione dell’intelligenza artificiale in sanità, con particolare riguardo alle malattie croniche, dalle piattaforme tecnologiche per la sanità digitale, alla telemedicina possa rappresentare una grande opportunità, facilitante nella direzione della equità delle cure, della condivisione partecipativa dei professionisti e degli utenti, dell’empowerment e della promozione della salute.
Il commento di Nicoletta Musacchio, Presidente di Fondazione AMD
I sistemi sanitari richiedono scelte coerenti, appropriate e sostenibili. La complessità della medicina oggi va certamente oltre la capacità della mente umana, gli stessi pazienti sono sempre più complessi e sappiamo quanto le variabili che impattano sull’efficacia nel lungo periodo del trattamento dipenda da variabili non più solo “numeriche”, ma anche da altre informazioni difficilmente strutturabili. Avere la possibilità di raccogliere e utilizzare in modo coerente, in questo mare magnum, le informazioni chiave che diventano sempre più importanti, è l’elemento cruciale del sistema e quello che serve è trovare strumenti di analisi, efficaci e affidabili.
AMD ha già sviluppato cultura e strumenti sull’importanza dei dati, ma ora possiamo e dobbiamo andare oltre. È quello che Fondazione AMD ha voluto fare creando intanto un gruppo di lavoro ad hoc che ha iniziato a studiare e a produrre sull’argomento, come pionieri, affinché AMD possa svolgere sul campo un ruolo da protagonista.
Scarica i documenti (in PDF)
- Musacchio N, Guaita G, Ozzello A, Pellegrini MA, Ponzani P, Zilich R, De Micheli A. (Position statement) Intelligenza artificiale e big data in ambito diabetologico. La prospettiva di AMD. JAMD 2018;21(3):219-31
- Musacchio N, Guaita G, Ozzello A, Pellegrini MA, Ponzani P, Zilich R, De Micheli A. (Review) Intelligenza artificiale e big data in ambito medico: prospettive, opportunità, criticità. JAMD 2018;21(3):204-18
Video
Intelligenza artificiale e big data in ambito medico – Bibliografia e sitografia
- Bacchi S, Tan Y, Oakden-Rayner L, Jannes J, et al. Machine Learning in the Prediction of Medical Inpatient Length of Stay. Intern Med J. 2020 Oct 23. doi: 10.1111/imj.14962. Online ahead of print.
- Hasis Y, Seldin M, Lusis A. ‘Multi-omics approaches to disease’. Genome Biol. 2017;18:83.
- https://foreignpolicy.com/2012/10/08/big-data-a-short-history/
- https://forum.huawei.com/enterprise/en/data/attachment/forum/dm/ecommunity/uploads/2016/0322/17/56f1129356a58.png
- https://www.emc.com/leadership/digital-universe/2014iview/executive-summary.htm
- https://www.igi-global.com/chapter/electronic-health-record-ehr-diffusion-and-an-examination-of-physician-resistance/184077
- https://www.techemergence.com/machine-learning-in-pharma-medicine/
- http://clinicalml.org/research
- https://en.wikipedia.org/wiki/Logic_learning_machine
- https://en.wikipedia.org/wiki/Right_to_explanation
- https://www.youtube.com/watch?v=O8OfhvUJ66A
- https://www.corriere.it/salute/18_maggio_04/anche-intelligenza-artificiale-puo-sbagliare-ma-colpa-uomo-a5e3d0f2-4f79-11e8-8934-320f-886fd76.shtml
- Norgeot B, Quer G, Beaulieu-Jones BK, et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat Med. 2020 Sep;26(9):1320-4.
- Ridi A. La gestione dei Big Data: strumenti di governance e appropriatezza.
- Alanazi HO, Abdullah AH, Qureshi KN, et al. Accurate and dynamic predictive model for better prediction in medicine and healthcare. Ir J Med Sci. 2018;187:501-13.
- Alimadadi A, Aryal S, Manandhar et al. Artificial intelligence and machine learning to fight COVID-19. Physiol Genomics. 2020 Apr 1;52(4):200-2.
- Allen S. Artificial intelligence and the future of psychiatry. IEEE Pulse. 2020 May-Jun;11(3):2-6.
- Berger JS, Haskell L, Ting W, et al. Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon? EPMA J. 2020 Jan 3;11(1):53-64.
- N. Biller-Andorno N, Biller A. Algorithm-Aided Prediction of Patient Preferences — An Ethics Sneak Peek. N Engl J Med. 2019 Oct 10;381(15):1480-5.
- Boyd D, Crawford K. Critical questions for big data. Inf Commun Soc. 2012;15:662-79.
- Bragazzi NL, Dai H, Damiani G, et al. J. How Big Data and Artificial Intelligence Can Help Better Manage the COVID-19 Pandemic. Int J Environ Res Public Health. 2020 May 2;17(9):E3176.
- Char DS, Shah NH, Magnus D. Implementing machine learning in health care – Addressing ethical challenges. N Engl J Med. 2018 Mar 15;378(11):981-3.
- Cruz Rivera S, Liu X, Chan A-W, et al.; and The SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. The Lancet Digital Health. Published online: September 9, 2020.
- Cui W, Robins D, Finkelstein J. Unsupervised Machine Learning for the Discovery of Latent Clusters in COVID-19 Patients Using Electronic Health Records. Stud Health Technol Inform. 2020 Jun 26;272:1-4.
- Desai RJ, Wang SV, Vaduganathan M, et al. Comparison of machine learning methods with traditional models for use of administrative claims with electronic medical records to predict heart failure outcomes. JAMA Netw Open. 2020 Jan 3;3(1):e1918962.
- Editorial. Guiding better design and reporting of AI-intervention trials. The Lancet Digital Health. Published online: September 9, 2020.
- Fdez-Olivares J, Onaindia E, Castillo L, et al. Personalized conciliation of clinical guidelines for comorbid patients through multi-agent planning. Artif Intell Med. 2018 Nov 22. pii: S0933-3657(17)30521-3. doi: 10.1016/j.artmed.2018.11.003. [Epub ahead of print].
- Guney S, Daniels C, MS, Childers Z. Using AI to understand the patient voice during the covid-19 pandemic. NEJM Catalyst, April 2020.
Hansen MM, Miron-Shatz T, Lau AY, et al. Big data in science and healthcare: A review of recent literature and perspectives. Contribution of the IMIA Social Media Working Group. Yearb Med Inform. 2014 Aug 15;9:21-6. - Herriman M, Meer E, Rosin R, et al. Asked and answered: building a chatbot to address COVID-19–Related concerns. NEJM Catalyst 2020;June 18.
- HMA-EMA Joint Big Data Taskforce – Summary report. Summary report EMA/105321/2019.
- Hood L. Systems biology and p4 medicine: past, present, and future. Rambam Maimonides Med J. 2013;4:e0012.
- Keesara S, Jonas A, Schulman K. Covid-19 and health care’s digital revolution. N Engl J Med. 2020 Apr 2. doi: 10.1056/NEJMp2005835. Online ahead of print.
- Li Y, Sperrin M, Ashcroft DM, van Staa TP. Consistency of variety of machine learning and statistical models in predicting clinical risks of individual patients: longitudinal cohort study using cardiovascular disease as exemplar. BMJ. 2020 Nov 4;371:m3919.
- Lin B, Wu S. COVID-19 (coronavirus disease 2019): opportunities and challenges for digital health and the internet of medical things in China. OMICS. 2020 May;24(5):231-232.
- Liu X, Cruz Rivera S, Moher D, et al.; and the SPIRIT-AI and CONSORT-AI Working Group. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. The Lancet Digital Health. Published online: September 9, 2020.
- Lo-Ciganic WH, Donohue JM, Thorpe JM, et al. Using machine learning to examine medication adherence thresholds and risk of hospitalization. Med Care. 2015 Aug;53(8):720-8.
- Mackey T, Purushothaman V, Li J, et al. Machine learning to detect self-reporting of symptoms, testing access, and recovery associated with COVID-19 on Twitter: retrospective big data Infoveillancestudy. JMIR Public Health Surveill. 2020 Jun 8;6(2):e19509.
- Mahmood S, Hasan K, Colder Carras M, et al. Global preparedness against COVID-19: we must leverage the power of digital health. JMIR Public Health Surveill. 2020 Apr 16;6(2):e18980.
- Mehta MC, Katz IT, Jha AK. Transforming Global Health with AI. N Engl J Med. 2020 Feb 27;382(9):791-3.
- Metsker O, Magoev K, Yanishevskiy S, Yakovlev A, Kopanitsa G, Zvartau N. Identification of Diabetes Risk Factors in Chronic Cardiovascular Patients. Stud Health Technol Inform. 2020 Sep 4;273:136-41.
- Michelson M, Chow T, Martin NA, et al. Artificial intelligence for rapid meta-analysis: case study on ocular toxicity of hydroxychloroquine. J Med Internet Res. 2020 Aug 17;22(8):e20007.
- Milea D, Najjar RP, Zhubo J, et al.; BONSAI Group. Artificial intelligence to detect papilledema from ocular fundus photographs. N Engl J Med. 2020 Apr 30;382(18):1687-1695.
- Na L, Yang C, Lo C-C, et al. Feasibility of reidentifying individuals in large national physical activity data sets from which protected health information has been removed with use of machine learning. JAMA Netw Open. 2018 Dec 7;1(8):e186040.
- Nagaraj SB, Sidorenkov G, van Boven JFM, et alP. Predicting short- and long-term glycated haemoglobin response after insulin initiation in patients with type 2 diabetes mellitus using machine-learning algorithms. Diabetes Obes Metab. 2019 Dec;21(12):2704-11.
- Ohura N, Mitsuno R, Sakisaka M, et al. Convolutional neural networks for wound detection: the role of artificial intelligence in wound care. J Wound Care. 2019 Oct 1;28(Sup10):S13-S24.
- Ong E, Wong MU, Huffman A, He Y. COVID-19 Coronavirus Vaccine Design Using Reverse Vaccinology and Machine Learning. Front Immunol. 2020 Jul 3;11:1581.
- Role of big data for evaluation and supervision of medicines in the EU. EMA News 15/02/2019.
- Russo G, Reche P, Pennisi M, Pappalardo F. The combination of artificial intelligence and systems biology for intelligent vaccine design. Expert Opin Drug Discov. 2020 Nov;15(11):1267-1281.
- Schwartz FL, Marling CR, Bunescu RC.The promise and perils of wearable physiological sensors for diabetes management. J Diabetes Sci Technol. 2018 May;12(3):587-91.
- Sim I. Mobile Devices and Health. N Engl J Med. 2019;381(10): 956-68.
- Simsek M, Kantarci B. Artificial intelligence-empowered mobilization of assessments in COVID-19-like pandemics: a case study for early flattening of the curve. Int J Environ Res Public Health. 2020 May 14;17(10).
- Scott IA. Machine learning and evidence-based medicine. Ann Intern Med. 2018 Jul 3;169(1):44-6.
- Toğaçar M, Ergen B, Cömert Z. COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches. Comput Biol Med. 2020 Jun;121:103805.
- Vu GT, Tran BX, McIntyre RS, et al. Modeling the Research Landscapes of Artificial Intelligence Applications in Diabetes (GAP RESEARCH). Int J Environ Res Public Health. 2020 Mar 17;17(6):1982.
- Zhou Y, Wang F, Tang J, et al. Artificial intelligence in COVID-19 drug repurposing. The Lancet Digital Health. Published online: September 18, 2020.
- Abbott CA, Chatwin KE, Foden P, et al. Innovative intelligent insole system reduces diabetic foot ulcer recurrence at plantar sites: a prospective, randomised, proof-of-concept study. Lancet Digital Health 2019;1 Oct:e308-18.
- Alloghani M, Aljaaf A, Hussain A, et al.Implementation of machine learning algorithms to create diabetic patient re-admission profiles. BMC Med Inform Decis Mak. 2019 Dec 12;19(Suppl 9):253.
- Aminian A, Zajichek A, Arterburn DE, et al. Predicting 10-year risk of end-organ complications of type 2 diabetes with and without metabolic surgery: a machine learning approach. Diabetes Care. 2020 Feb 6.doi: 10.2337/dc19-2057. [Epub ahead of print].
- Arcadu F, Benmansour F, Maunz A, et al. Deep learning predicts oct measures of diabetic macular thickening from color fundus photographs. Invest Ophthalmol Vis Sci. 2019 Mar 1;60(4):852-7.
- Basu S, Raghavan S, Wexler DJ, et al. Characteristics associated with decreased or increased mortality risk from glycemic therapy among patients with type 2 diabetes and high cardiovascular risk: Machine learning analysis of the ACCORD trial. Diabetes Care. 2018 Mar;41(3):604-12.
- Bellemo V, Lim Z W, Lim G, et al. Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study. Lancet Digital Health 2019;1:e35-44.
- Broome DT, Hilton CB, Mehta N. Policy Implications of Artificial Intelligence and Machine Learning in Diabetes Management. Curr Diab Rep. 2020 Feb 1;20(2):5.
- Buch V, Varughese G, Maruthappu M. Artificial intelligence in diabetes care. Diabet Med. 2018 Apr;35(4):495-7.
- Bus SA. Preventing foot ulcers in diabetes using plantar pressure feedback. Lancet Digital Health 2019;1 Oct:e250-1.
- Cao W, Czarnek N, Shan J, Li L. Microaneurysm Detection Using Principal Component Analysis and Machine Learning Methods. IEEE Trans Nanobioscience. 2018 Jul;17(3):191-8.
- Cappon G, Vettoretti M, Marturano F, et al. A neural-network-based approach to personalize insulin bolus calculation using continuous glucose monitoring. J Diabetes Sci Technol. 2018 Mar;12(2):265-72.
- Cahn A, Shoshan A, Sagiv T, et al. Prediction of progression from pre-diabetes to diabetes: Development and validation of a machine learning model. Diabetes Metab Res Rev. 2020 Feb;36(2):e3252.
- Choi BG, Rha SW, Kim SW, et al. Machine learning for the prediction of new-onset diabetes mellitus during 5-year follow-up in non-diabetic patients with cardiovascular risks. Yonsei Med J. 2019;60:191-9.
- Contreras I, Vehi J. Artificial intelligence for diabetes management and decision support: literature review. J Med Internet Res. 2018 May 30;20(5):e10775.
- Cruz-Vega I, Hernandez-Contreras D, Peregrina-Barreto H, et al. Deep Learning Classification for Diabetic Foot Thermograms. Sensors (Basel). 2020 Mar 22;20(6):1762.
- Dagliati A, Marini S, Sacchi L, et al. Machine learning methods to predict diabetes complications. J Diabetes Sci Technol. 2018 Mar;12(2):295-302.
- Das SK. Integrating transcriptome and epigenomic: putting together the pieces of the type 2 diabetes pathogenesis puzzle. Diabetes. 2014 Sep;63(9):2901-3.
- (Editorial) Wearable technology and lifestyle management: the fight against obesity and diabetes. Lancet Digital Health 2019;1 Oct:e243.
- Eghbali-Zarch M, Tavakkoli-Moghaddam R, Esfahanian F, et al. Pharmacological therapy selection of type 2 diabetes based on the SWARA and modified MULTIMOORA methods under a fuzzy environment. Artif Intell Med. 2018 May;87:20-33.
- El-Sappagh S, Kwak D, Ali F, et al. DMTO: a realistic ontology for standard diabetes mellitus treatment. J Biomed Semantics. 2018 Feb 6;9(1):8.
- Ellahham S. Artificial Intelligence: The future for diabetes care. Am J Med. 2020 Aug;133(8):895-900.
- Ellahham S. Artificial intelligence in diabetes care. Am J Med. Pub. online 20 April 2020.
- Esmaeily H, Tayefi M, Ghayour-Mobarhan M, et al. Comparing three data mining algorithms for identifying the associated risk factors of type 2 diabetes Iran. Biomed J. 2018;22:303-11.
- Fagherazzi G, Ravaud P. Digital diabetes: perspectives for diabetes prevention, management and research. Diabetes Metab. 2019 Sep;45(4):322-9.
- Fiorini S, Hajati F, Barla A, et al. Predicting diabetes second-line therapy initiation in the Australian population via time span-guided neural attention network. PLoS One. 2019 Oct 18;14(10):e0211844.
- Forlenza GP. Use of Artificial intelligence to improve diabetes outcomes in patients using multiple daily injections therapy. Diabetes Technol Ther. 2019 Jun;21(S2):S24-8.
- Franks PW, Pearson E, Florez JC. Gene-environment and gene-treatment interactions in type 2 diabetes. Progress, pitfalls and prospect. Diabetes Care. 2013 May;36(5):1413-21.
- Garcia-Carretero R, Vigil-Medina L, Barquero-Perez O, et al. Pulse wave velocity and machine learning to predict cardiovascular outcomes in prediabetic and diabetic populations. J Med Syst. 2019 Dec 9;44(1):16.
- Giorda CB, Pisani F, De Micheli A, et al.; Associazione Medici Diabetologi (AMD) Annals Study Group. Determinants of good metabolic control without weight gain in type 2 diabetes management: a machine learning analysis. BMJ Open Diabetes Res Care. 2020 Sep;8(1):e001362.
- Gong F, Chen Y, Wang H, Lu H. On building a diabetes centric knowledge base via mining the web. BMC Med Inform Decis Mak. 2019 Apr 9;19(Suppl 2):49.
- Gou W, Ling C, He Y, et al. Interpretable Machine Learning Framework Reveals Robust Gut Microbiome Features Associated With Type 2 Diabetes. Diabetes Care. 2020 Dec 7;dc201536. doi: 10.2337/dc20-1536. Online ahead of print.
- Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016 Dec 13;316(22):2402-10.
- Gunasekeran DV, Ting DSW, Tan GSW, Wong TY. Artificial intelligence for diabetic retinopathy screening, prediction and management. Curr Opin Ophthalmol. 2020 Sep;31(5):357-365.
- Hatanaka Y. Retinopathy Analysis Based on Deep Convolution Neural Network. Adv Exp Med Biol. 2020;1213:107-20.
- Hathaway QA, Roth SM, Pinti MV, et al. Machine-learning to stratify diabetic patients using novel cardiac biomarkers and integrative genomics. Cardiovasc Diabetol. 2019 Jun 11;18(1):78.
- He J, Cao T, Xu F, et al. Artificial intelligence-based screening for diabetic retinopathy at community hospital. Eye (Lond). 2019 Aug 27. doi: 10.1038/s41433-019-0562-4. [Epub ahead of print].
- http://www.emif.eu/
- Iyengar V, Wolf A, Brown A et al. Challenges in diabetes care: can digital health address them? Clin Diabetes. 2016Jul;34(3):133-41.
- Jin K, Pan X, You K, et al. Automatic detection of non-perfusion areas in diabetic macular edema from fundus fluorescein angiography for decision making using deep learning. Sci Rep. 2020 Sep 15;10(1):15138.
- Karsaz A. Chattering–free hybrid adaptive neuro-fuzzy inference system-particle swarm optimisation data fusion-based BG-level control. IET Syst Biol. 2020 Feb;14(1):31-38.
- Kerr D and Klonoff DC. Digital diabetes data and artificial intelligence: A time for humility not hubris. J Diabetes Sci Technol. 2019 Jan;13(1):123-7.
- Khojasteh P, Aliahmad B, Arjunan SP, et al. Introducing a novel layer in convolutional neural network for automatic identification of diabetic retinopathy. Conf Proc IEEE Eng Med Biol Soc. 2018 Jul;2018:5938-41.
- Kim E, Caraballo PJ, Castro MR, et al. Towards more accessible precision medicine: building a more transferable machine learning model to support prognostic decisions for micro- and macrovascular complications of type 2 diabetes mellitus. J Med Syst. 2019;43(7):185.
- Klompas M, Eggleston E, Mcvetta J, et al. Automated detection and classification of type 1 versus type 2 diabetes using electronic health record data. Diabetes Care. 2013 Apr;36(4):914-21.
- Kopitar L, Kocbek P, Cilar L, et al. Early detection of type 2 diabetes mellitus using machine learning-based prediction models. Sci Rep. 2020 Jul 20;10(1):11981.
- Lekha S, M S. Real-time non-invasive detection and classification of diabetes using modified convolution neural network. IEEE J Biomed Health Inform. 2018 Sep;22(5):1630-6.
- Liaw ST, Taggart J, Yu H, et al. Integrating electronic health record information to support integrated care: Practical application of ontologies to improve the accuracy of diabetes disease registers. J Biomed Inform. 2014 Dec;52:364-72.
- Maguire J, Dhar V. Comparative effectiveness for oral anti-diabetic treatments among newly diagnosed type 2 diabetics: data-driven predictive analytics in healthcare. Health Syst 2013 Jul;2:73-92.
- Makam AN, Nguyen OK, Moore B, et al. Identifying patients with diabetes and the earliest date of diagnosis in real time: an electronic health record case-finding algorithm. BMC Med Inform Decis Mak 2013 Augu 1;1:13:81.
- Maniruzzaman M, Rahman J, Al-Mehedi H, et al.Accurate diabetes risk stratification using machine learning: role of missing value and outliers. J Med Syst 2018;42:92.
- Maniruzzaman M, Kumar N, Abedin M, et al. Comparative approaches for classification of diabetes mellitus data: Machine learning paradigm. Comput Methods Programs Biomed. 2017 Dec;152:23-34.
- Mayo M, Chepulis L, Paul RG. Glycemic-aware metrics and oversampling techniques for predicting blood glucose levels using machine learning. PLoS One. 2019 Dec 2;14(12):e0225613.
- Musacchio N, Giancaterini A, Guaita G, et al. artificial intelligence and big data in diabetes care: a position statement of the Italian Association of Medical Diabetologists. J Med Internet Res. 2020 Jun 22;22(6):e16922.
- Nadimi ES, Majtner T, Yderstraede KB, et al. Facial erythema detects diabetic neuropathy using the fusion of machine learning, random matrix theory and self organized criticality. Sci Rep. 2020 Oct 8;10(1):16785.
- Nagasawa T, Tabuchi H, Masumoto H, et al. Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy. Int Ophthalmol. 2019 Oct;39(10):2153-2159.
- Natarajan S, Jain A, Krishnan R, et al. Diagnostic accuracy of community-based diabetic retinopathy screening with an offline artificial intelligence system on a smartphone. JAMA Ophthalmol. 2019 Aug 8. doi: 10.1001/jamaophthalmol.2019.2923. [Epub ahead of print].
- Ngufor C, Van Houten H, Caffo BS, et al. Mixed effect machine learning: A framework for predicting longitudinal change in hemoglobin A1c. J Biomed Inform. 2019 Jan;89:56-67.
- Nielsen KB, Lautrup ML, Andersen JKH, et al. Deep Learning-Based Algorithms in Screening of Diabetic Retinopathy: A Systematic Review of Diagnostic Performance. Ophthalmol Retina. 2019 Apr;3(4):294-304.
- Olivera AR, Roesler V, Iochpe C, et al. Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes – ELSA-Brasil: accuracy study Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre (RS), Brazil. Sao Paulo Med J. 2017 May-Jun;135(3):234-46.
- Oviedo S, Contreras I, Bertachi A, et. al. Minimizing postprandial hypoglycemia in Type 1 diabetes patients using multiple insulin injections and capillary blood glucose self-monitoring with machine learning techniques. Comput Methods Programs Biomed. 2019 Sep;178:175-80.
Raman R, Srinivasan S, Virmani S, et al. Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy. Eye (Lond). 2019 Jan;33(1):97-109. - Razavian N, Bleker S, Schmidt AM, et al. Population-level prediction of type 2 diabetes from claims data and analysis of risk factors. Big Data. 2015 Dec;3(4):277-87.
- Ren F, Cao P, Zhao D, et al. Diabetic macular edema grading in retinal images using vector quantization and semi-supervised learning. Technol Health Care. 2018;26(S1):389-97.
- Renard LM, Bocquet V, Vidal-Trecan G, et al. An algorithm to identify patients with treated type 2 diabetes using medico-administrative data. BMC Med Inform Decis Mak. 2011 Apr 14;11:23.
- Rigla M, García-Sáez G, Pons B, et al. Artificial intelligence methodologies and their application to diabetes. J Diabetes Sci Technol. 2018 Mar;12(2):303-10.
- Roberto G, Leal I, Sattar N, et al. Identifying cases of type 2 diabetes in heterogeneous data sources: Strategy from the EMIF project. PLoS One. 2016 Aug 31;11(8):e0160648.
- Rodríguez-Rodríguez I, Chatzigiannakis I, Rodríguez JV, et al. Utility big data in predicting short-term blood glucose levels in type 1 diabetes mellitus through machine learning techniques. Sensors (Basel). 2019 Oct 16;19(20).
- Ruan Y, Bellot A, Moysova Z, et al. Predicting the Risk of Inpatient Hypoglycemia With Machine Learning Using Electronic Health Records. Diabetes Care. 2020 Apr 29;dc191743. doi: 10.2337/dc19-1743. Online ahead of print.
- Ruan Y, Bellot A, Moysova Z, et al. Predicting the risk of inpatient hypoglycemia with machine learning using electronic health records. Diabetes Care. 2020 Apr 29;dc191743. doi: 10.2337/dc19-1743. Online ahead of print.
- Sabanayagam C, Xu D, Ting DSW, et al. A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations. Lancet Digital Health 2020;2:e295-302.
- Schulman KA, Richman BD. Toward an effective innovation agenda. N Engl J Med. 2019 Mar 7;380(10):900-1.
- Schwartz FL, Marling CR, Bunescu RC.The promise and perils of wearable physiological sensors for diabetes management. J Diabetes Sci Technol. 2018 May;12(3):587-91.
- Segar MV, Vaduganathan M, Patel KV, et al. Machine Learning to Predict the Risk of Incident Heart Failure Hospitalization Among Patients With Diabetes: The WATCH-DM Risk Score. Diabetes Care. 2019 Sep 13. pii: dc190587. doi: 10.2337/dc19-0587. [Epub ahead of print].
- Shan R, Sarkar S, Martin SS. Digital health technology and mobile devices for the management of diabetes mellitus: state of the art. Diabetologia. 2019 Jun;62(6):877-87.
- Shankaracharya, Odedra D, Samanta S, et al. Computational intelligence-based diagnosis tool for the detection of prediabetes and type 2 diabetes in India. Rev Diabet Stud 2012;9(1):55-62.
- Talaei-Khoei A, Wilson JM. Identifying people at risk of developing type 2 diabetes: A comparison of predictive analytics techniques and predictor variables. Int J Med Inform. 2018 Nov;119:22-38.
- Tsao HY, Chan PY, Su ECY. Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms. BMC Bioinformatics. 2018 Aug 13;19(Suppl 9):283.
- Verbraak FD, Abramoff MD, Bausch GCF, et al. diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting. Diabetes Care. 2019 Apr;42(4):651-6.
- Vettoretti M, Cappon G, Facchinetti A, et al. Advanced Diabetes Management Using Artificial Intelligence and Continuous Glucose Monitoring Sensors. Sensors (Basel). 2020 Jul 10;20(14).
- Williams BM, Borroni D, Liu R, et al. An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study. Diabetologia. 2019 Nov 12. doi: 10.1007/s00125-019-05023-4. [Epub ahead of print].
- Wu XW, Yang HB, Yuan R, et al. Predictive models of medication non-adherence risks of patients with T2D based on multiple machine learning algorithms. BMJ Open Diabetes Res Care. 2020 Mar;8(1).
- Xiong XL, Zhang RX, Bi Y, et al. Machine learning models in type 2 diabetes risk prediction: results from a cross-sectional retrospective study in Chinese adults. Curr Med Sci. 2019;39(4):582-8.
- Yamada T, Iwasaki K, Maedera S, et al. Myocardial infarction in type 2 diabetes using sodium-glucose co-transporter-2 inhibitors, dipeptidyl peptidase-4 inhibitors or glucagon-like peptide-1 receptor agonists: proportional hazards analysis by deep neural network based machine learning. Curr Med Res Opin. 2020 Mar;36(3):403-9.
- You Y, Doubova SV, Pinto-Masis D, et al. Application of machine learning methodology to assess the performance of DIABETIMSS program for patients with type 2 diabetes in family medicine clinics in Mexico. BMC Med Inform Decis Mak. 2019 Nov 12;19(1):221.
- Zarkogianni K, Athanasiou M, Thanopoulou AC. Comparison of machine learning approaches toward assessing the risk of developing cardiovascular disease as a long-term diabetes complication. IEEE J Biomed Health Inform. 2018:1637-47.
- Zhixi L, Liu SKC, He Y, et al. An automated grading system for detection of vision-threatening referable diabetic retinopathy on the basis of color fundus photographs. Diabetes Care. 2018 Dec;41(12):2509-16.
- Zhou K, Gu Z, Liu W, et al. Multi-cell multi-task convolutional neural networks for diabetic retinopathy grading. Conf Proc IEEE Eng Med Biol Soc. 2018 Jul;2018:2724-7.
- Armstrong S. Data, data everywhere: the challenges of personalised medicine. BMJ. 2017;359:j4546.
- Asghari S, Mahdavian M. Secondary analysis of electronic databases: potentials and limitations. Diabetologia. 2013 Sep;56(9):2096-7.
- Bachtiger P, Peters NS, Walsh SLF. Machine learning for COVID-19—asking the right questions. The Lancet Digital Health. Published online: July 10, 2020.
- Beam AL, Kohane IS. Translating artificial intelligence into clinical care. JAMA. 2016 Dec 13;316(22):2368-2369.
- Beam AL, Kohane IS. Big data and machine learning in health care. JAMA. 2018 Apr 3;319(13):1317-8.
- Bitterman DS, Aerts JWLH, Mak RH. Approaching autonomy in medical artificial intelligence. Lancet Digit Health. 2020 Sep;2(9):e447-e449.
- Cabitza F, Rasoini R, Gensini GF. Unintended consequences of machine learning in medicine. JAMA. 2017 Aug 8;318(6):517-8.
- Caruana R, Lou Y, Gehrke J et al. Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Cham, Switzerland: Springer International Publishing AG 2015;1721-30.
- Celi LA, Fine C, Stone DJ. An awakening in medicine: the partnership of humanity and intelligent machines. Lancet Digital Health 2019;1 Oct:e255-7.
Centre for Evidence-Based Medicine. Study Designs. - Chen JH, Asch SM. Machine learning and prediction in medicine – Beyond the peak of inflated expectations. N Engl J Med. 2017 Jun 29;376(26):2507-9.
- Cohen IG, Mello MM. Big data, big tech, and protecting patient privacy. JAMA. 2019 Aug 9. doi: 10.1001/jama.2019.11365. [Epub ahead of print].
- Cohen IG, Mello MM. HIPAA and protecting health information in the 21st century. JAMA. 2018 Jul 17;320(3):231-2.
- Cross M. Show us the data: why clinical outcomes matter. BMJ. 2012;344:e66.
- Desai AN. Artificial intelligence: promise, pitfalls, and perspective. JAMA. 2020 Jun 3.
- Duncan MJ, Kolt GS. Learning from community-led and co-designed m-health interventions. Lancet Digital Health 2019;1 Oct:e248-9.
- Eaneff S, Obermeyer Z, Butte AJ. Algorithmic Stewardship for Artificial Intelligence and Machine Learning Technologies. JAMA. 2020 Sep 14. doi: 10.1001/jama.2020.9371. Online ahead of print.
- Editorial, Lancet. Is digital medicine different? Lancet 2018 Jul14;374:1105-12.
- Feeley TW, Landman Z, Porter ME. The agenda for the next generation of health care information technology. NEJM Catalyst, June 2020.
- Fridsm DB. Health informatics: a required skill for 21st century clinicians. BMJ. 2018;362:k3043.
- Futoma J, Simons M, Panch T, et al. The myth of generalisability in clinical research and machine learning in health care. Digit Health. 2020 Sep;2(9):e489-e492.
- Gianfrancesco MA, Tamang S, YazdanyJ, et al. Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med. 2018 Nov 1;178(11):1544-7.
- Gill J, Prasad V. Improving observational studies in the era of big data 716-7. Lancet. 2018 Sep 1;392(10149):716-7.
- Goldhahn J, Rampton V, Weiss B, et al. Could artificial intelligence make doctors obsolete? BMJ. 2018;363 k4563.
- Gruber K. Is the future of medical diagnosis in computer algorithms? www.thelancet.com/digital-health Vol 1 May 2019.
- Haendel MA, Chute CG, Robinson PN. Classification, ontology, and precision medicine. N Engl J Med. 2018 Oct 11;379(15):1452-62.
- Hinton G. Deep learning—A technology with the potential to transform health care. JAMA. 2018 Sep 18;320(11):1101-2.
- Hoff T. Deskilling and adaptation among primary care physicians using two work innovations. Health Care Manage Rev. 2011 Oct-Dec;36(4):338-48.
- Hwang TJ, Kesselheim AS, Vokinger KN. Lifecycle regulation of artificial intelligence– and machine learning–based software devices in medicine. JAMA. 2019 Nov 22. doi: 10.1001/jama.2019.16842. [Epub ahead of print]
- Ienca M, Vayena E. On the responsible use of digital data to tackle the COVID-19 pandemic. Nat Med. 2020 Apr;26(4):463-4.
- Israni ST, Verghese A. Humanizing artificial intelligence. JAMA. 2019 Jan 1;321(1):29-30.
- Keesara S, Jonas A, Schulman K. COVID-19 and health care’s digital revolution. N Engl J Med. 2020 Jun 4;382(23):e82.
- Lenzer J. Big data’s big bias: bringing noise and conflicts to US drug regulation. BMJ. 2017;358:j3275.
- Longhurst CA, Harrington RA, Shah NH. A ‘green button’ for using aggregate patient data at the point of care. Health Aff (Millwood). 2014 Jul;33(7):1229-35.
- McCoy TH Jr, Hughes MC. Preserving patient confidentiality as data grow implications of the ability to reidentify physical activity data. JAMA Netw Open. 2018 Dec 7;1(8):e186029.
- McGreevey III JD, Hanson III CW, Koppel R. Clinical, Legal, and Ethical Aspects of Artificial Intelligence–Assisted Conversational Agents in Health Care. JAMA 2020 Jul 24. Online ahead of print.
- Mittelman M, Markham S, Taylor M. Patient commentary: Stop hyping artificial intelligence—patients will always need human doctors. BMJ. 2018;363:k4669.
- Moskowitz A, McSparron J, Stone DJ, Celi LA. Preparing a new generation of clinicians for the era of big data. Harv Med Stud Rev. 2015 Jan; 2(1): 24-7.
- Nagendran M, Chen Y, Lovejoy CA, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ 2020;368:m689.
- Naylor CD. On the prospects for a (deep) learning health care system. JAMA. 2018 Sep 18;320(11):1101-2.https://jamanetwork.com/journals/jama/article-abstract/2701666
- Obermeyer Z, Lee T H. Lost in thought – The limits of the human mind and the future of medicine. N Engl J Med. 2017 Sep 28;377(13):1209-11.
- Oren O, Gersh BJ, Bhatt DL. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. Digit Health. 2020 Sep;2(9):e486-e488.
- Parikh RB, Teeple S, Navathe AS. Addressing bias in artificial intelligence in health care. JAMA. 2019 Nov 22. doi: 10.1001/jama.2019.18058. [Epub ahead of print]
- Park Y, Casey D, Joshi I, et al. Emergence of New Disease: How Can Artificial Intelligence Help? Trends Mol Med. 2020 Jul;26(7):627-629.
- Perakslis ED, PGinsburg GS. Digital Health—The Need to Assess Benefits, Risks, and Value. JAMA. Published online December 28, 2020. doi:10.1001/jama.2020.22919.
- Peterson ED. Machine learning, predictive analytics, and clinical practice – can the past inform the present? JAMA. 2019 Nov 22. doi: 10.1001/jama.2019.17831. [Epub ahead of print]
- Rajkomar A, DeanJ, Kohane I. Machine learning in medicine. N Engl J Med. 2019 Apr 4;380(14):1347-58.
- Schulman KA, Richman BD. Toward an effective innovation agenda. N Engl J Med. 2019 Mar 7;380(10):900-1.
- Roca J, Tenyi A, Cano I. Paradigm changes for diagnosis: Using big data for prediction. Clin Chem Lab Med. 2019; 57:317-27.
- Shah ND, Steyerberg EW, Kent DM. Big data and predictive analytics: Recalibrating expectations. JAMA. 2018 Jul 3;320(1):27-8.
- Sim I. Two ways of knowing: Big data and evidence-based medicine. Ann Intern Med. 2016 Apr 19;164(8):562-3.
- Snyder M, Zhou W. Big data and health. Lancet Digital Health 2019;1 Oct:e252-4.
- Stead WW. Clinical implications and challenges of artificial intelligence and deep learning. JAMA. 2018 Sep 18;320(11):1107-8.
- Stey A, Kanzaria H, Brook R. How disruptive innovation by business and technology firms could improve population health. JAMA. 2018 Sep 11;320 (10):973-4.
- Svensson CM, Hübler R, Figge MT. Automated classification of circulating tumor cells and the impact of interobsever variability on classifier training and performance. J Immunol Res. 2015;2015:573165.
- Ting DSW, Carin L, Dzau V, Wong TY. Digital technology and COVID-19. Nat Med. 2020 Apr;26(4):459-61.
- Verghese A, Shah NH, Harrington RA. What this computer needs is a physician: Humanism and artificial intelligence. JAMA. 2018 Jan 2;319(1):19-20.
- Vigilante K, Escaravage S, McConnell M. Big Data and the Intelligence Community – Lessons for Health Care. N Engl J Med. 2019 May 16;380(20):1888-90.
- Wang F, Casalino LP, Khullar D. Deep learning in medicine—Promise, progress, and challenges. JAMA Intern Med. 2018 Dec 17. doi: 10.1001/jamainternmed.2018.7117. [Epub ahead of print].
- Wilkinson J, Arnold KF, Murray EJ, et al. Time to reality check the promises of machine learning-powered precision medicine. The Lancet Digital Health. Published online: September 16, 2020.
- Zilich R, Musacchio N, Medea G, et al. Big data: la medicina delle 4P (preventiva, predittiva, personalizzata e partecipata). MEDIA 2017;17:58.63.