Shaping the future of men's sexual health: How artificial intelligence can assist in the management and treatment of erectile dysfunction

Abstract

Artificial intelligence (AI) is a complex combination of multidisciplinary machines and systems that can replicate human‐like cognitive tasks to execute capabilities such as pattern recognition, decision‐making, and problem‐solving. Dating back to the 2000s, AI has been utilized in the medical field, however the interest in this subject has sharply increased over the past several years. Erectile dysfunction (ED) is an increasingly pervasive issue as men age, affecting up to 150 million men worldwide. In the field of men's health, AI has been employed to assist physicians in the evaluation and management of ED. This article aims to summarize the ways in which AI has been utilized in the management of ED, as well as the considerations that must be made when implementing this technology. AI can be utilized for virtual health assistance to protect patient privacy and increase access to care. Augmented reality can aid surgeons in real‐time during operations, as well as be utilized to prepare physicians for situations that they may encounter in the operating room. Pharmaceutical companies can benefit from AI in the interpretation of data, analysis of chemical compounds and in drug development. Additionally, AI can be used to assist patients in post‐procedure recovery in the form of rehabilitation and post‐treatment monitoring. While the utilization of AI in men's health is an exciting venture, there are tremendous ethical and practical considerations that have limited its use in the management of ED.

Graphical abstract

Keywords

artificial intelligence / erectile dysfunction / male sexual dysfunction

1 INTRODUCTION

Artificial intelligence (AI) is a multidisciplinary field of computer science that focuses on creating machines and systems capable of performing tasks that typically require human intelligence. First presented in 1956, it was loosely defined as systems imitating intelligent human behaviors[1]. AI aims to simulate and replicate human‐like cognitive functions in computers and other machines. The tasks AI can perform include problem‐solving, learning from experience, recognizing patterns, understanding natural language, and making decisions.

Over the years, AI has been seen considerable advances in the medical field[2]. Numerous applications of AI have been developed to support physicians in various clinical settings, including inpatient, outpatient, emergency department, outreach, and surgery[3]. AI has been shown to assist in processing high‐volume data sets using data analytics[4,5], improving workflow efficiency through the self‐analysis of medical imaging[6], and analyzing information directly from health records[7]. Thousands of articles have been published on AI in medicine since the 2000s, with a considerable uptick occurring in 2017–2018 and an ever‐increasing amount every subsequent year[8]. AI generally benefits patients with lower costs, enhanced sensitivity of tests, and higher accuracy in diagnosis, all of which can be applied to the management of erectile dysfunction (ED).

ED is defined as the inability to attain and/or maintain penile erection sufficient for satisfactory sexual performance[9]. ED is a widespread health concern affecting men globally. It has been reported that up to 30 million men in the United States and 150 million men worldwide are estimated to be affected by ED[10,11]. It is estimated that by 2025 we will see up to 322 million men affected, with prevalence rates reaching up to 70% in men 70 years and above[12]. Independent risk factors for ED and cardiovascular disease (CVD) are well‐recognized and include age, smoking, diabetes mellitus, hypertension, dyslipidemia, depression, obesity, and a sedentary lifestyle[13–16]. With ever‐increasing rates of CVD among men around the world, it is no wonder we have seen a parallel increase in the prevalence of ED as well[17–19].

Traditionally, ED diagnosis and treatment relied on clinical assessments and pharmaceutical interventions. However, with the advent of AI and machine learning (ML), significant transformations are evident in the way we approach and manage this sensitive health issue[20]. This article delves into the latest advances in AI and ML in ED management.

2 AI TERMINOLOGY TO KNOW

The healthcare sector is witnessing rapid advancements with the integration of AI and ML in diagnostics, patient care, and treatment protocols. In essence, AI employs algorithms and software to perform tasks that usually require human intelligence, while ML, a subset of AI, uses statistical methods to allow machines to improve tasks with experience. While complex, AI systems function in many different capacities and can be catered to fulfill specific needs in both clinical and research settings. Provided below is a brief overview of some of the important nomenclature and predictive models used when describing AI (Figure 1).

2.1 ML

ML is a subfield of AI that focuses on the development of algorithms and statistical models that enable computers and machines to learn and make predictions or decisions without being explicitly programmed[21]. In ML, computers use data to identify patterns, make inferences, and improve their performance on a specific task over time. The goal is to enable machines to generalize from past data and make accurate predictions or decisions on new, unseen data[22]. Its unique quality is the ability of the system to improve on itself over time, without needing explicit input or updating from the user.

2.2 Deep learning

Deep learning is a subfield of ML and AI that focuses on training artificial neural networks to perform tasks by simulating the way the human brain processes information. Using large data sets, it can recognize patterns in imaging and records that would be otherwise missed with conventional methods. It is characterized by the use of deep neural networks, which are composed of multiple layers of interconnected artificial neuron networks that can automatically learn and extract features from data. The term “deep” refers to the presence of many layers (hence, “deep” learning) in these networks, which allows them to represent complex hierarchical patterns and relationships within data[23]. It has demonstrated state‐of‐the‐art performance in tasks such as image classification, object detection, language translation, and more, making it a crucial technology in modern AI research and applications[24].

2.3 Expert systems

An expert system is a computer‐based information system that emulates the decision‐making ability of a human expert in a specific domain or field of knowledge. It is a type of AI system designed to provide solutions, recommendations, or answers to complex problems by applying a set of rules, heuristics, and knowledge derived from experts in the domain[25]. Key components of an expert system typically include: a knowledge base with an archive of structured information and expertise to the specific domain; an inference engine which is the software component responsible for applying the knowledge from the knowledge base to the specific problem at hand; a user interface that allows users to interact with the system, input data, and receive recommendations or solutions; and an explanation module which can provide users with explanations of the system's reasoning process and the basis for its recommendations or decisions[26].

2.4 Natural language processing

Natural language processing (NLP) is a field of AI that focuses on the interaction between computers and human language. It involves the development of algorithms and models that enable computers to understand, interpret, and generate language in a way that is both meaningful and useful. NLP encompasses a wide range of tasks and applications, including: text understanding such as text classification (e.g., spam detection) and named entity recognition (e.g., identifying names of people, places, organizations, etc.), language generation (e.g., chatbots and virtual assistants), converting spoken language into written text (e.g., Dragon software), machine translation (e.g., google translate), question answering, and analyzing the sentiment or emotion expressed in text[27].

3 AI APPLICATIONS IN THE FIELD OF SEXUAL MEDICINE AND MEN'S HEALTH

In the field of sexual medicine, the most widespread use of AI has been seen in andrology[8]. With exceptionally high costs associated with the field, these automated AI predictive models can offer a more cost‐effective and efficient approach to the clinical management of infertility. AI has been developed and used for the interpretation of semen analysis[28], determination of sperm hyperactivation and DNA fragmentation[29,30], objective sperm selection for assisted reproductive techniques[31], imaging of reproductive structures[32,33], and more. Less commonly used in sexual medicine so far has been the applications of AI in ED, presumably due to the lower costs associated with treatment, simpler diagnosis, and lower overall research funding than infertility.

The initial steps in managing ED naturally involve a precise diagnosis, which requires comprehensive patient information, imaging, questionnaires, equipment, and history. The bulk of AI discourse to date has surrounded the ability of AI systems to compress vast amounts of information to develop novel approaches to an accurate ED diagnosis that is seemingly more sensitive and specific than a clinician's medical decision‐making, thus minimizing errors in diagnosis. AI in diagnostics has been used to (Figure 2):

‐Develop novel questionnaires that showed greater accuracy than the established International Index of Erectile Function (IIEF‐5)[34];

‐Develop equipment such as corpus cavernosum electromyogram and digital inflection rigidometer analyzed to yield an ED diagnosis[35,36];

‐Develop expert systems used as a clinical decision support system in men to diagnose ED without a physician following initial evaluation by questionnaires and equipment[7,37];

‐Analyze medical images such as penile Doppler ultrasonography and positron emission tomography/computed tomography imaging of penile arteries in patients with prostate cancer to determine etiology of ED[38,39];

‐Predict the onset or worsening of ED as a preoperative risk stratification for prostate cancer treatment, or predictive of postradiotherapy ED in men with prostate cancer[40–42].

While AI in diagnostics has been reviewed previously[20], less so has been the uses of AI in the treatment of ED postdiagnosis. We summarize the various ways AI has been studied in the management of ED, as well as explore ways in which AI used in other specialties can be applied to future ED treatment (Figure 3).

4 AI IN MANAGEMENT AND TREATMENT OF ED

4.1 Virtual health assistants for ED

Discussing ED can be challenging due to the associated stigma. It was reported that 50% of ED patients would not seek medical attention or take ED medication with professional advice, which leads to low diagnosis rates and drug misuse[43]. Virtual health assistants powered by AI provide an environment where patients can comfortably discuss their symptoms, get information, or be directed to specialists. Patients can describe their symptoms to these AI‐powered platforms (expert systems), which can then offer preliminary diagnoses or suggest further tests.

One such study is currently being formally conducted in a randomized control trial[44]. The chatbot uses an AI model integrated with the line developer platform to predict risks for men's health conditions such as urinary symptoms and ED. It provides self‐management advice on issues such as prostate enlargement, urinary symptoms, and ED. It also provides patient‐centered decision‐making aids that support and encourage patients, especially in improving urination and ED. When this study is completed, it should provide good evidence of the impact of AI chatbot aid intervention on enhancing self‐management and decision‐making among men with ED without the need for a physician on hand. Whether this aid will be comparable to or worse than being treated by a urologist remains to be seen.

In addition, we know that AI‐driven chatbots can provide psychological counseling, helping patients address the emotional and psychological aspects of ED, which are often left out of urology outpatient consults[45]. Although not an AI experiment, Andersson et al. showed, in a randomized controlled trial of guided internet‐delivered cognitive behavioral therapy for ED, that using an online discussion group had significantly greater improvements with regard to erectile performance compared with the control group[46]. Developing a similar AI system to function as an online support system is not beyond the realm of possibilities, and would likely yield similar results.

4.2 Augmented reality

Augmented reality‐assisted surgery was developed as an aid during surgical procedures. Typically, an overlay of medical images is shown on the surgical field developed using image recognition AI. The AI can then guide surgeons in real time, highlighting anatomical landmarks, predicting potential challenges based on the individual's unique anatomy, and suggesting optimal insertion sites[47]. One can see this technology being used, for instance, in the installation of penile prosthesis to suggest optimal positioning and sizing, or guiding placement of the reservoir. Eun et al. showed, during surgery for ureteral/urethral strictures, that augmented reality could be used to guide the surgeon to the stenotic area[48]. Similar technique could be used to guide surgeons to the scarred plaque in Peyronie's disease for appropriate surgical or medical management.

Augmented reality can also be used in the creation of surgical simulators, and thus can play a strong role in education and training[49]: AI‐powered surgical simulators can help novice surgeons or surgeons with a low volume of a particular procedure to practice in a virtual environment, providing instant feedback and guidance, ensuring that they are well‐prepared before they operate on real patients.

4.3 Surgery

In regards to preoperative planning, AI can assist in analyzing patient data, previous surgical outcomes, and anatomical factors to help surgeons make optimal preoperative decisions[50]. For instance, it could recommend the type or size of the prosthesis based on specific patient parameters. By analyzing large data sets, AI can study the outcomes of thousands of penile prosthesis surgeries to identify patterns, complications, and factors contributing to both successful and unsuccessful surgeries. This can help in refining surgical techniques and patient care protocols.

4.4 Personalized treatment plans

One of the challenges in ED management is the broad spectrum of underlying causes, making a one‐size‐fits‐all approach suboptimal. AI can sift through vast amounts of patient data, considering everything from hormonal levels to psychological profiles, to craft personalized treatment plans. This could range from lifestyle changes and medications to more advanced treatments like vascular surgeries. In addition, ML can adapt recommendations based on patient feedback. For instance, if a patient reports side effects from medication, the system can suggest alternative therapies or dosages.

4.5 Enhanced drug discovery and therapy

Pharmaceutical research benefits immensely from AI. AI can analyze the vast landscape of chemical compounds to identify potential candidates for new ED medications, as well as potential drugs/substances that may be causing ED. Jang et al. in Korea developed an artificial neural network classification‐driven method using the LC‐MS/MS software for screening unknown ED drugs and analogs[51]. She reported with 100% classification accuracy the ability to classify unknown drugs and compounds into sildenafil, vardenafil, and tadalafil families and non‐ED compounds. This provided a powerful tool in research to develop and classify new unknown compounds that were not established in any known databases. Clinically it can provide support in diagnosing unconventional substances that could be contributing to a patient's ED.

Yang et al. documented a case of using AI‐powered drug discovery in treating diabetic ED[52]. Yang described a technique known as “network pharmacology” where information from complex biological databases of gene/proteins or molecular interactions was used to decide what network nodes or edges were potential targets for therapeutic intervention[53]. Hirudin, the main active ingredient in the leech, could ameliorate the ED symptoms of a diabetic ED mouse model. Using the network pharmacology with a pool of known genes and protein interactions, Yang was able to discover hirudin's potential target on myeloperoxidase (MPO). Hirudin directly interacts with MPO and inhibits its activity, thus further decreasing the content of oxidized low‐density lipoprotein in the serum and improving diabetic ED. Thus, Yang successfully documented a case in ED where we can see AI's powerful potential in the research field to discover drug and protein mechanisms for further investigation.

4.6 Rehabilitation and post‐treatment monitoring

Recovery and monitoring post‐treatment are crucial in ED management. AI‐powered wearable devices are one modality in which one can monitor physiological parameters, offering real‐time feedback on the body's response to treatment. ML algorithms can adjust rehabilitation exercises and routines based on the patient's progress. One such device was detailed in a 2017 news article. The Fitdix smartwatch app was an AI‐driven application reported to log 100 different techniques to boost arousal, sensation, pleasure and stamina[54]. Users could search for techniques or anonymously share their favorites on the app. Fitdix saved data on motion, pace, intensity, time, and calories burned; users could then use this data to set new personal goals. According to consumer trials conducted over a 6‐month period, users reported that 57% experienced a decrease in premature ejaculation, 76% reported an increase in natural erection strength, and 61% reported lasting longer during sex. Although the study was not available online to be reviewed and substantiated, this article shows the potential draw of wearable devices to continuously monitor physiological parameters and provide improvement in one's sexual function to the point of no longer needing pharmacological management.

5 CHALLENGES AND ETHICAL CONSIDERATIONS OF AI APPLICATIONS IN ED

Despite the considerable work that has been done in the development of AI technology to be used in the diagnosis and management of ED detailed in this article, very little has seen practical use today. For instance, a review of the 2018 American Urological Association guidelines for the management of ED makes zero mention of AI or ML technology[55]. A review of the clinicaltrails.gov site revealed only one trial worldwide currently being conducted on AI and ED[56]. The reason AI has seen such limited use has to do with the substantial challenges and ethical considerations revolving AI's application today that are detailed subsequently (Figure 4).

5.1 No external validation

Very few if any of the current AI models developed within sexual medicine or throughout the healthcare field have been externally validated to be accurate. In fact, because of AI's novelty new external validation systems must also be developed in tandem with AI for them to see use. Additionally, without prospective and blind experimental studies being conducted using these AI systems, they cannot see applications in practice. Clinicians rely on randomized controlled trials to practice evidence‐based medicine. Thus, these AI systems remain as interesting hypotheses in most cases that have yet to be formally tested in a real‐world setting.

5.2 Lack of comprehensive national databases

The strength of AI algorithms relies entirely on the vast amount of data available to analyze. Without national databases that characterize and amass this information, the data provided to develop AI systems would be limited. There has been extensive work in crafting and managing cancer and genomic databases such as the Cancer Genome Atlas and Kyoto Encyclopedia of Genes[57–59]. Unfortunately, we have no such national databases for the recording of ED in patients. Additionally, an AI developed using only the population data set of a single institution would be beneficial for that specific institution, but be less applicable to a wider population with a different demography.

5.3 Data privacy

Along with the need to develop larger comprehensive databases comes concern with data privacy. Patients often must be signed and consented to be included in these databases, adding workload to the clinical setting. Handling sensitive patient data also requires robust security measures to prevent breaches.

5.4 Overreliance

There is growing concern that sole dependence on AI can lead to overlooked nuances in patient care, potentially decreasing medical decision‐making ability[60]. Although this has never been proven, it still remains a hot topic in the field. There is additional concern that AI will be used to replace rather than augment current practitioners, seemingly decreasing the rate at which this technology would normally be researched and adopted for fear of decreased reliance on physicians in the future.

5.5 Ethical dilemmas

Lastly, the potential misuse of AI in creating unrealistic expectations or the dissemination of misleading information is a concern that needs addressing. Any chatbot or expert system created must be extensively validated to be providing accurate and appropriate information to the patient. After all, where does the burden of fault lie when the AI makes a wrong decision, with the practitioner, the developer of the AI, or the institution?

6 CONCLUSION

The integration of AI and ML in ED management heralds a new era in personalized medicine. By offering more accurate diagnostics, augmenting surgeries in real time and in education, enhancing research output, tailoring treatments to individual needs, and providing supportive virtual environments, AI is poised to transform the way we understand and address ED. However, as with all advancements, a balanced approach that melds technology with the human touch will yield the best outcomes. The future holds promise, but it also calls for a conscious effort to use technology responsibly and ethically.

References

[1] Moor J. The Dartmouth college artificial intelligence conference: the next fifty years. AI Mag. 2006;27:87–91.

[2] Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69S:S36–S40.

[3] Kulkarni S, Seneviratne N, Baig MS, Khan AHA. Artificial intelligence in medicine: where are we now? Acad Radiol. 2020;27:62–70.

[4] Oh JH, Kerns S, Ostrer H, Powell SN, Rosenstein B, Deasy JO. Computational methods using genome‐wide association studies to predict radiotherapy complications and to identify correlative molecular processes. Sci Rep. 2017;7:43381.

[5] Kunjachen LM, Kavitha R. Artifical intelligence based predictive and prescriptive analytics on clinical data using data analytics. NeuroQuantology. 2022;20.11:5235.

[6] Yi J, Kang HK, Kwon JH, Kim KS, Park MH, Seong YK, et al. Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency. Ultrasonography. 2021;40.1:7–22.

[7] Chen YF, Lin CS, Hong CF, Lee DJ, Sun C, Lin HH. Design of a clinical decision support system for predicting erectile dysfunction in men using NHIRD dataset. IEEE J Biomed Health Inform. 2019;23:2127–2137.

[8] Ghayda RA, Cannarella R, Calogero AE, Shah R, Rambhatla A, Zohdy W, et al. Artificial intelligence in andrology: from semen analysis to image diagnostics. World J Men's Health. 2023;41:e57.

[9] Droller MJ, Anderson JR, Beck JC, Bremner WJ, Evans K, Mikel Gray M, et al. Impotence. NIH Consensus Development Panel on Impotence. JAMA. 1993;270:83–90.

[10] McKinlay J. The worldwide prevalence and epidemiology of erectile dysfunction. Int J Impot Res. 2000;12(Suppl 4):S6–S11.

[11] Aytaç IA, McKinlay JB, Krane RJ. The likely worldwide increase in erectile dysfunction between 1995 and 2025 and some possible policy consequences. BJU Int. 1999;84:50–56.

[12] Selvin E, Burnett AL, Platz EA. Prevalence and risk factors for erectile dysfunction in the US. Am J Med. 2007;120:151–157.

[13] Jackson G, Boon N, Eardley I, Kirby M, Dean J, Hackett G, et al. Erectile dysfunction and coronary artery disease prediction: evidence‐based guidance and consensus. Int J Clin Pract. 2010;64:848–857.

[14] Martin‐Morales A, Sanchez‐Cruz JJ, Saenz de Tejada I, Rodriguez‐Vela L, Fernando Jimenez‐Cruz J, Burgos‐Rodriguez R. Prevalence and independent risk factors for erectile dysfunction in Spain: results of the epidemiologia de la disfuncion erectil masculina study. J Urol. 2001;166:569–575.

[15] Corona G, Lee DM, Forti G, O'Connor DB, Maggi M, O'Neill TW, et al. Age‐related changes in general and sexual health in middle‐aged and older men: results from the European Male Ageing Study (EMAS). J Sex Med. 2010;7:1362–1380.

[16] Feldman HA, Goldstein I, Hatzichristou DG, Krane RJ, McKinlay JB. Impotence and its medical and psychosocial correlates: results of the Massachusetts Male Aging Study. J Urol. 1994;151:54–61.

[17] Fung MM, Bettencourt R, Barrett‐Connor E. Heart disease risk factors predict erectile dysfunction 25 years later. J Am Coll Cardiol. 2004;43:1405–1411.

[18] Esposito K, Giugliano F, Martedì E, Feola G, Marfella R, D'Armiento M, et al. High proportions of erectile dysfunction in men with the metabolic syndrome. Diabetes Care. 2005;28:1201–1203.

[19] Ansong KS, Lewis C, Jenkins P, Bell J. Epidemiology of erectile dysfunction. Ann Epidemiol. 2000;10:293–296.

[20] Xiong Y, Zhang Y, Zhang F, Wu C, Qin F, Yuan J. Applications of artificial intelligence in the diagnosis and prediction of erectile dysfunction: a narrative review. Int J Impot Res. 2023;35:95–102.

[21] Sidey‐Gibbons JAM, Sidey‐Gibbons CJ. Machine learning in medicine: a practical introduction. BMC Med Res Methodol. 2019;19:64.

[22] Choi RY, Coyner AS, Kalpathy‐Cramer J, Chiang MF, Campbell JP. Introduction to machine learning, neural networks, and deep learning. Transl Vis Sci Technol. 2020;9:14.

[23] Nguyen D, Nguyen H, Ong H, Le H, Ha H, Duc NT, et al. Ensemble learning using traditional machine learning and deep neural network for diagnosis of Alzheimer's disease. IBRO Neurosci Rep. 2022;13:255–263.

[24] Gupta P, Sharma A, Jindal R. Scalable machine‐learning algorithms for big data analytics: a comprehensive review. WIRES Data Min Knowl Discov. 2016;6:194–214.

[25] Metaxiotis KS, Samouilidis JE. Expert systems in medicine: academic exercise or practical tool? J Med Eng Technol. 2000;24.2:68–72.

[26] Heathfield H. The Rise and ‘Fall’ of expert systems in medicine. Expert Syst. 1999;16:183–188.

[27] Locke S, Bashall A, Al‐Adely S, Moore J. Natural language processing in medicine: a review. Trends Anaesth Crit Care. 2021;38:4–9.

[28] Tomlinson MJ, Naeem A. CASA in the medical laboratory: CASA in diagnostic andrology and assisted conception. Reprod Fertil Dev. 2018;30:850–859.

[29] Turner HC, Sharma P, Perrier JR, Bertucci A, Smilenov L, Johnson G, et al. The RABiT: high‐throughput technology for assessing global DSB repair. Radiat Environ Biophys. 2014;53:265–272.

[30] Goodson SG, White S, Stevans AM, Bhat S, Kao CY, Jaworski S, et al. CASAnova: a multiclass support vector machine model for the classification of human sperm motility patterns. Biol Reprod. 2017;97:698–708.

[31] El‐shafeiy E, El‐Desouky A, El‐Ghamrawy S. An optimized artificial neural network approach based on sperm whale optimization algorithm for predicting fertility quality. Stud Inform Control. 2018;27:349–355.

[32] Favaron T, Huang DY, Christensen‐Jeffries K, Eckersley RE, Sidhu PS, Grisan E. Building a reduced dictionary of relevant perfusion patterns from Ceus data for the classification of testis lesions. In: Paper presented at 2019 IEEE  16th International Symposium on Biomedical Imaging (ISBI 2019); 2019 Apr 8–11; Venice, Italy. IEEE; 2019; p. 850–854.

[33] Cui Y, Wang G, Ren J, Hou L, Li D, Wen Q, et al. Radiomics features at multiparametric MRI predict disease‐free survival in patients with locally advanced rectal cancer. Acad Radiol. 2022;29:e128–e138.

[34] Glavaš S, ValenćIć L, Trbojević N, Tomašić AM, Turćić N, Tibauth S, et al. Erectile function in cardiovascular patients: its significance and a quick assessment using a visual‐scale questionnaire. Acta Cardiol. 2015;70:712–719.

[35] Kellner B, Stief CG, Hinrichs H, Hartung C. Computerized classification of corpus cavernosum electromyogram signals by the use of discriminant analysis and artificial neural networks to support diagnosis of erectile dysfunction. Urol Res. 2000;28:6–13.

[36] El‐Sakka A. Association between International Index of Erectile Function and axial penile rigidity in patients with erectile dysfunction. Int J Impot Res. 2003;15:426–429.

[37] Zhang Y, Tian X, Xia K, Zhuang J, Feng X, Zhou M, et al. Construction of intelligent expert system and its preliminary clinical application in the real world of diagnosis of sexual dysfunction. J Clin Urol. 2018;33:603–606.

[38] Elhanbly S, Elkholy A. Nocturnal penile erections: the role of RigiScan in the diagnosis of vascular erectile dysfunction. J Sex Med. 2012;9:3219–3226.

[39] Nakahara T, Narula J, Tijssen JGP, Agarwal S, Chowdhury MM, Coughlin PA, et al. (18) F‐fluoride positron emission tomographic imaging of penile arteries and erectile dysfunction. J Am Coll Cardiol. 2019;73:1386–1394.

[40] Briganti A, Gallina A, Suardi N, Capitanio U, Tutolo M, Bianchi M, et al. Predicting erectile function recovery after bilateral nerve sparing radical prostatectomy: a proposal of a novel preoperative risk stratification. J Sex Med. 2010;7:2521–2531.

[41] Cozzi G, Musi G, Monturano M, Bagnardi V, Frassoni S, Jereczek‐Fossa BA, et al. Sexual function recovery after robot‐assisted radical prostatectomy: outcomes from an Italian referral centre and predicting nomogram. Andrologia. 2019;51:e13385.

[42] Mulhall JP, Kattan MW, Bennett NE, Stasi J, Nascimento B, Eastham J, et al. Development of nomograms to predict the recovery of erectile function following radical prostatectomy. J Sex Med. 2019;16:1796–1802.

[43] Lin H, Zhao L, Wu H, Cao M, Jiang H. Sexual life and medication taking behaviors in young men: an online survey of 92620 respondents in China. Int J Clin Pract. 2020;74:e13417.

[44] Chen KK. The impact of Chatbot‐aid on promoting self‐management of men's health in the post COVID‐19 era. ClinicalTrials.gov identifier NCT05765331. [updated 2023 Mar 13].

[45] Segraves RT. Considerations for diagnostic criteria for erectile dysfunction in DSM V. J Sex Med. 2010;7.2(Pt 1):654–660.

[46] Andersson E, Walén C, Hallberg J, Paxling B, Dahlin M, Almlöv J, et al. A Randomized controlled trial of guided internet‐delivered cognitive behavioral therapy for erectile dysfunction. J Sex Med. 2011;8:2800–2809.

[47] He C, Liu Y, Wang Y. Sensor‐fusion based augmented‐reality surgical navigation system. The institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings, 2016 May 23–26 Taipei, Taiwan, China. IEEE; 2016.

[48] Eun SJ, Park JM, Kim KH. Development of an artificial intelligence‐based support technology for urethral and ureteral stricture surgery. Int Neurourol J. 2022;26:78–84.

[49] Yoon JW, Chen RE, Kim EJ, Akinduro OO, Kerezoudis P, Han PK, et al. Augmented reality for the surgeon: systematic review. Int J Med Robot Comput Assist Surg. 2018;14:e191.

[50] Zhou XY, Guo Y, Shen M, Yang GZ. Application of Artificial Intelligence in Surgery. Front Med. 2020;14:417–430.

[51] Jang I, Lee J, Lee J, Kim BH, Moon B, Hong J, et al. LC–MS/MS software for screening unknown erectile dysfunction drugs and analogues: artificial neural network classification, peak‐count scoring, simple similarity search, and hybrid similarity search algorithms. Anal Chem. 2019;91:9119–9128.

[52] Yang R, Liu C, Li Q, Wang W, Wu B, Chen A, et al. Artificial intelligence based identification of the functional role of hirudin in diabetic erectile dysfunction treatment. Pharmacol Res. 2021;163:105244.

[53] Muqbil I, Asfar SA, Ramzi MM. Chapter 18—systems and network pharmacology strategies for pancreatic ductal adenocarcinoma therapy: a resource review. In: Azmi AS, editor. Molecular diagnostics and treatment of pancreatic cancer. Academic Press; 2014. p. 405–425.

[54] PR Newswire Association LLC. Fitdix launches first iWatch app that boosts men's sexual performance: using artificial intelligence, Fitdix will disrupt Big Pharma's grip on erectile dysfunction medication. New York: PR Newswire Association LLC; 2017.

[55] Burnett AL, Nehra A, Breau RH, Culkin DJ, Faraday MM, Hakim LS, et al. Erectile dysfunction: AUA guideline. J Urol. 2018;200:633–641.

[56] Clinicaltrails.gov search [Internet]. Artificial intelligence, erectile dysfunction. 2023.

[57] Cancer Genome Atlas Research Network. Comprehensive molecular characterization of urothelial bladder carcinoma. Nature. 2014;507:315–322.

[58] Schymura MJ, Sun L, Percy‐Laurry A. Prostate cancer collaborative stage data items—their definitions, quality, usage, and clinical implications: a review of SEER data for 2004–2010. Cancer. 2014;120:3758–3770.

[59] Kanehisa M. KEGG: Kyoto Encyclopedia of Genes and Genomes. Nucleic Acids Res. 2000;28:27–30.

[60] Yang GZ, Cambias J, Cleary K, Daimler E, Drake J, Dupont PE, et al. Medical robotics regulatory, ethical, and legal considerations for increasing levels of autonomy. Sci Robot. 2017;2(4):8638.

RIGHTS & PERMISSIONS

2024 The Authors. UroPrecision published by John Wiley & Sons Australia, Ltd on behalf of Higher Education Press.