Classification of skin blemishes with cell phone images using deep learning techniques.

Skin blemishes can be caused by multiple events or diseases and, in some cases, it is difficult to distinguish where they come from. Therefore, there may be cases with a dangerous origin that go unnoticed or the opposite case (which can lead to overcrowding of health services). To avoid this, the use of artificial intelligence-based classifiers using images taken with mobile devices is proposed; this would help in the initial screening process and provide some information to the patient prior to their final diagnosis. To this end, this work proposes an optimization mechanism based on two phases in which a global search for the best classifiers (from among more than 150 combinations) is carried out, and, in the second phase, the best candidates are subjected to a phase of evaluation of the robustness of the system by applying the cross-validation technique. The results obtained reach 99.95% accuracy for the best case and 99.75% AUC. Comparing the developed classifier with previous works, an improvement in terms of classification rate is appreciated, as well as in the reduction of the classifier complexity, which allows our classifier to be integrated in a specific purpose system with few computational resources.

A lightweight xAI approach to cervical cancer classification.

Cervical cancer is caused in the vast majority of cases by the human papilloma virus (HPV) through sexual contact and requires a specific molecular-based analysis to be detected. As an HPV vaccine is available, the incidence of cervical cancer is up to ten times higher in areas without adequate healthcare resources. In recent years, liquid cytology has been used to overcome these shortcomings and perform mass screening. In addition, classifiers based on convolutional neural networks can be developed to help pathologists diagnose the disease. However, these systems always require the final verification of a pathologist to make a final diagnosis. For this reason, explainable AI techniques are required to highlight the most significant data to the healthcare professional, as it can be used to determine the confidence in the results and the areas of the image used for classification (allowing the professional to point out the areas he/she thinks are most important and cross-check them against those detected by the system in order to create incremental learning systems). In this work, a 4-phase optimization process is used to obtain a custom deep-learning classifier for distinguishing between 4 severity classes of cervical cancer with liquid-cytology images. The final classifier obtains an accuracy over 97% for 4 classes and 100% for 2 classes with execution times under 1 s (including the final report generation). Compared to previous works, the proposed classifier obtains better accuracy results with a lower computational cost.

A Robust Ensemble of Convolutional Neural Networks for the Detection of Monkeypox Disease from Skin Images.

Monkeypox is a smallpox-like disease that was declared a global health emergency in July 2022. Because of this resemblance, it is not easy to distinguish a monkeypox rash from other similar diseases; however, due to the novelty of this disease, there are no widely used databases for this purpose with which to develop image-based classification algorithms. Therefore, three significant contributions are proposed in this work: first, the development of a publicly available dataset of monkeypox images; second, the development of a classification system based on convolutional neural networks in order to automatically distinguish monkeypox marks from those produced by other diseases; and, finally, the use of explainable AI tools for ensemble networks. For point 1, free images of monkeypox cases and other diseases have been searched in government databases and processed until we are left with only a section of the skin of the patients in each case. For point 2, various pre-trained models were used as classifiers and, in the second instance, combinations of these were used to form ensembles. And, for point 3, this is the first documented time that an explainable AI technique (like GradCAM) is applied to the results of ensemble networks. Among all the tests, the accuracy reaches 93% in the case of single pre-trained networks, and up to 98% using an ensemble of three networks (ResNet50, EfficientNetB0, and MobileNetV2). Comparing these results with previous work, a substantial improvement in classification accuracy is observed.

AnkFall-Falls, Falling Risks and Daily-Life Activities Dataset with an Ankle-Placed Accelerometer and Training Using Recurrent Neural Networks.

Falls are one of the leading causes of permanent injury and/or disability among the elderly. When these people live alone, it is convenient that a caregiver or family member visits them periodically. However, these visits do not prevent falls when the elderly person is alone. Furthermore, in exceptional circumstances, such as a pandemic, we must avoid unnecessary mobility. This is why remote monitoring systems are currently on the rise, and several commercial solutions can be found. However, current solutions use devices attached to the waist or wrist, causing discomfort in the people who wear them. The users also tend to forget to wear the devices carried in these positions. Therefore, in order to prevent these problems, the main objective of this work is designing and recollecting a new dataset about falls, falling risks and activities of daily living using an ankle-placed device obtaining a good balance between the different activity types. This dataset will be a useful tool for researchers who want to integrate the fall detector in the footwear. Thus, in this work we design the fall-detection device, study the suitable activities to be collected, collect the dataset from 21 users performing the studied activities and evaluate the quality of the collected dataset. As an additional and secondary study, we implement a simple Deep Learning classifier based on this data to prove the system's feasibility.

Evaluation of user satisfaction and usability of a mobile app for smoking cessation.

BACKGROUND: Mobile apps have a great potential to support patients in healthcare, and to encourage healthy behavioral changes such as smoking cessation. Nevertheless, the user rejection levels are still high. A set of factors that has impact on the app effectiveness is related to the quality of those features that lead to positive user experiences when using the app. This work aims to evaluate the user experience, and more specifically the usability and the user satisfaction with a mobile application for smoking cessation. This will also provide a basis for future improvements. METHODS: We provided a smoking cessation mobile Android app to two different user cohorts, the smokers as valid users and the experts, for three weeks. The app featured usual functionalities to help quit smoking, including an achieved benefits section, mini-games to distract during cravings, and supportive motivational messages. We collected information about user experience, through game playability and message satisfaction questionnaires, and the experts' opinions. We also considered usage of app sections, the duration of the mini-game sessions, and the user ratings for motivational messages. RESULTS: We included 45 valid users and 25 experts in this study. The questionnaire indicated 80% satisfaction rate for the motivational messages. According to game questionnaires, over 69% of the participants agreed that the games have good usability features, however, for questions related to mobility and gameplay heuristics, agreements were below 67%. The most accessed app sections were achieved benefits and the one with motivational messages. The experts described issues that could help to improve the application. CONCLUSIONS: The combination of questionnaires with expert reports allowed to identify several problems and possible corrections. Our study showed that motivational messages have a good satisfaction rate, although it is necessary to consider technical features of some mobile devices that may hinder message reception. Games have good usability and it's expected that the addition of difficulty levels and a better accessibility to the game menu could make them more attractive and increase its usage. Future development of mHealth apps based on gamification and motivational messages need to consider these factors for better user satisfaction and usability.

Using the Social-Local-Mobile App for Smoking Cessation in the SmokeFreeBrain Project: Protocol for a Randomized Controlled Trial.

BACKGROUND: Smoking is considered the main cause of preventable illness and early deaths worldwide. The treatment usually prescribed to people who wish to quit smoking is a multidisciplinary intervention, combining both psychological advice and pharmacological therapy, since the application of both strategies significantly increases the chance of success in a quit attempt. OBJECTIVE: We present a study protocol of a 12-month randomized open-label parallel-group trial whose primary objective is to analyze the efficacy and efficiency of usual psychopharmacological therapy plus the Social-Local-Mobile app (intervention group) applied to the smoking cessation process compared with usual psychopharmacological therapy alone (control group). METHODS: The target population consists of adult smokers (both male and female) attending the Smoking Cessation Unit at Virgen del Rocío University Hospital, Seville, Spain. Social-Local-Mobile is an innovative intervention based on mobile technologies and their capacity to trigger behavioral changes. The app is a complement to pharmacological therapies to quit smoking by providing personalized motivational messages, physical activity monitoring, lifestyle advice, and distractions (minigames) to help overcome cravings. Usual pharmacological therapy consists of bupropion (Zyntabac 150 mg) or varenicline (Champix 0.5 mg or 1 mg). The main outcomes will be (1) the smoking abstinence rate at 1 year measured by means of exhaled carbon monoxide and urinary cotinine tests, and (2) the result of the cost-effectiveness analysis, which will be expressed in terms of an incremental cost-effectiveness ratio. Secondary outcome measures will be (1) analysis of the safety of pharmacological therapy, (2) analysis of the health-related quality of life of patients, and (3) monitoring of healthy lifestyle and physical exercise habits. RESULTS: Of 548 patients identified using the hospital's electronic records system, we excluded 308 patients: 188 declined to participate and 120 did not meet the inclusion criteria. A total of 240 patients were enrolled: the control group (n=120) will receive usual psychopharmacological therapy, while the intervention group (n=120) will receive usual psychopharmacological therapy plus the So-Lo-Mo app. The project was approved for funding in June 2015. Enrollment started in October 2016 and was completed in October 2017. Data gathering was completed in November 2018, and data analysis is under way. The first results are expected to be submitted for publication in early 2019. CONCLUSIONS: Social networks and mobile technologies influence our daily lives and, therefore, may influence our smoking habits as well. As part of the SmokeFreeBrain H2020 European Commission project, this study aims at elucidating the potential role of these technologies when used as an extra aid to quit smoking. TRIAL REGISTRATION: ClinicalTrials.gov NCT03553173; https://clinicaltrials.gov/ct2/show/record/NCT03553173 (Archived by WebCite at http://www.webcitation.org/74DuHypOW). INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/12464.

Tailoring motivational health messages for smoking cessation using an mHealth recommender system integrated with an electronic health record: a study protocol.

BACKGROUND: Smoking is one of the most avoidable health risk factors, and yet the quitting success rates are low. The usage of tailored health messages to support quitting has been proved to increase quitting success rates. Technology can provide convenient means to deliver tailored health messages. Health recommender systems are information-filtering algorithms that can choose the most relevant health-related items-for instance, motivational messages aimed at smoking cessation-for each user based on his or her profile. The goals of this study are to analyze the perceived quality of an mHealth recommender system aimed at smoking cessation, and to assess the level of engagement with the messages delivered to users via this medium. METHODS: Patients participating in a smoking cessation program will be provided with a mobile app to receive tailored motivational health messages selected by a health recommender system, based on their profile retrieved from an electronic health record as the initial knowledge source. Patients' feedback on the messages and their interactions with the app will be analyzed and evaluated following an observational prospective methodology to a) assess the perceived quality of the mobile-based health recommender system and the messages, using the precision and time-to-read metrics and an 18-item questionnaire delivered to all patients who complete the program, and b) measure patient engagement with the mobile-based health recommender system using aggregated data analytic metrics like session frequency and, to determine the individual-level engagement, the rate of read messages for each user. This paper details the implementation and evaluation protocol that will be followed. DISCUSSION: This study will explore whether a health recommender system algorithm integrated with an electronic health record can predict which tailored motivational health messages patients would prefer and consider to be of a good quality, encouraging them to engage with the system. The outcomes of this study will help future researchers design better tailored motivational message-sending recommender systems for smoking cessation to increase patient engagement, reduce attrition, and, as a result, increase the rates of smoking cessation. TRIAL REGISTRATION: The trial was registered at clinicaltrials.org under the ClinicalTrials.gov identifier NCT03206619 on July 2nd 2017. Retrospectively registered.

HealthRecSys: A semantic content-based recommender system to complement health videos.

BACKGROUND: The Internet, and its popularity, continues to grow at an unprecedented pace. Watching videos online is very popular; it is estimated that 500 h of video are uploaded onto YouTube, a video-sharing service, every minute and that, by 2019, video formats will comprise more than 80% of Internet traffic. Health-related videos are very popular on YouTube, but their quality is always a matter of concern. One approach to enhancing the quality of online videos is to provide additional educational health content, such as websites, to support health consumers. This study investigates the feasibility of building a content-based recommender system that links health consumers to reputable health educational websites from MedlinePlus for a given health video from YouTube. METHODS: The dataset for this study includes a collection of health-related videos and their available metadata. Semantic technologies (such as SNOMED-CT and Bio-ontology) were used to recommend health websites from MedlinePlus. A total of 26 healths professionals participated in evaluating 253 recommended links for a total of 53 videos about general health, hypertension, or diabetes. The relevance of the recommended health websites from MedlinePlus to the videos was measured using information retrieval metrics such as the normalized discounted cumulative gain and precision at K. RESULTS: The majority of websites recommended by our system for health videos were relevant, based on ratings by health professionals. The normalized discounted cumulative gain was between 46% and 90% for the different topics. CONCLUSIONS: Our study demonstrates the feasibility of using a semantic content-based recommender system to enrich YouTube health videos. Evaluation with end-users, in addition to healthcare professionals, will be required to identify the acceptance of these recommendations in a nonsimulated information-seeking context.

Exergames versus self-regulated exercises with instruction leaflets to improve adherence during geriatric rehabilitation: a randomized controlled trial.

BACKGROUND: Improving mobility in elderly persons is a primary goal in geriatric rehabilitation. Self-regulated exercises with instruction leaflets are used to increase training volume but adherence is often low. Exergames may improve adherence. This study therefore compared exergames with self-regulated exercise using instruction leaflets. The primary outcome was adherence. Secondary outcomes were enjoyment, motivation and balance during walking. METHODS: Design: single center parallel group non-blinded randomized controlled trial with central stratified randomization. SETTING: center for geriatric inpatient rehabilitation. Included were patients over 65 with mobility restrictions who were able to perform self-regulated exercise. Patients were assigned to self-regulated exercise using a) exergames on Windows Kinect® (exergame group EG) or b) instruction leaflets (conventional group CG). During two 30 min sessions physical therapists instructed self-regulated exercise to be conducted twice daily during thirty minutes during ten working days. Patients reported adherence (primary outcome), enjoyment and motivation daily. Balance during walking was measured blind before and after the treatment phase with an accelerometer. Analysis was by intention to treat. Repeated measures mixed models and Cohen's d effect sizes (ES, moderate if >0.5, large if > 0.8) with 95% CIs were used to evaluate between-group effects over time. Alpha was set at 0.05. RESULTS: From June 2014 to December 2015 217 patients were evaluated and 54 included, 26 in the EG and 28 in the CG. Adverse effects were observed in two patients in the EG who stopped because of pain during exercising. Adherence was comparable at day one (38 min. in the EG and 42 min. in the CG) and significantly higher in the CG at day 10 (54 min. in the CG while decreasing to 28 min. in the EG, p = 0.007, ES 0.94, 0.39-0.151). Benefits favoring the CG were also observed for enjoyment (p = 0.001, ES 0.88, 0.32 - 1.44) and motivation (p = 0.046, ES 0.59, 0.05-1.14)). There was no between-group effect in balance during walking. CONCLUSIONS: Self-regulated exercise using instruction leaflets is superior to exergames regarding adherence, enjoyment and motivation in a geriatric inpatient rehabilitation setting. Effects were moderate to large. There was no between group difference in balance during walking. TRIAL REGISTRATION: ClinicalTrials.gov, NCT02077049 , 6 February 2014.

Modelling side to side intestinal anastomosis.

Side-to-side intestinal anastomosis is a surgical procedure where an incision is performed between two parallel segments of gut and then they are sutured together. The purpose of this paper is to investigate if the standard surgical practice diameter used in anastomosis leads to undesirable closed circulatory flows which may be harmful to the gut tissue. A finite element model for the chyme flow in a side by side anastomosis with realistic user configurable parameters is developed and solved in a wide range of situations. We analyze the flow crossing the anastomosis, the normalized pressure difference in the gut section and the streamlines that show the presence or absence of closed flow regions for a set of surgically feasible anastomosis diameter values. In contrast with the findings of simpler analytical models, closed flows do not appear in any of these cases. The study shows that the current standard surgical practice where the anastomosis diameter is similar to the gut diameter does not lead to undesirable effects predicted by some simple analytical models.

The usefulness of activity trackers in elderly with reduced mobility: a case study.

UNLABELLED: This study was conducted to determine the accuracy and usefulness of two current commercially available activity trackers in rollator dependent elderly with reduced mobility (RME), compared with elderly with normal mobility (NME) and healthy adults (HA). METHODS: Accuracy of pedometers placed at hip (Fitbit Ultra and Samsung GT-I9300 mobile phone) and wrist (Fitbit Ultra) were evaluated against actual steps (video) in RME (n=5), NME (n=7) and HA (n=6). Walk speed, Tinetti gait score and device percent error was calculated and analyzed in SPSS using Kruskal-Wallis, Mann-Whitney U and correlation tests. RESULTS: NME and HA walked significantly faster (p = 0.001) than RME, had significantly higher gait score (p < 0.05). Gait scores were correlated with walking speed and negatively with pedometer percent error (p < 0.01). Estimation error in RME were >60% at all device locations CONCLUSIONS: Slow walking speed and gait disorders hamper the utility of pedometers for physical activity measurement in rollator dependent elderly, with estimation errors >60%. The tested devices are better suited for use by ostensibly healthy elderly or adult populations.