The prefrontal cortex (PFC) has extensive reciprocal connections with nearly all cortical and subcortical structures, placing it in a unique position to orchestrate a wide range of cognitive and affective neural functions. Damage of PFC in humans is associated with profound changes in social and affective behavior. The development of new technologies in the field of cognitive rehabilitation is giving us the opportunity to use computer-based cognitive tools to improve the recovery of patients affected by acquired brain injury.

Objective: The objective of the study is to investigate the regional capacity and implementation of radiotherapy for nasopharyngeal carcinoma (NPC) in Chongqing city. Materials and Methods: The questionnaires, self-designed electronic forms in a uniform format, were distributed to 37 radiotherapy institutions, which covered all the medical units equipped with radiotherapy equipment in this city. Results: Of the 37 radiotherapy units in Chongqing, 27 could deliver radiotherapy for NPC, but the remaining 10 institutions could not due to equipment limitations. From January to December 2017, a total of 2904 patients with NPC were treated with radiotherapy. Patients from the five teaching hospitals in the main districts of the city accounted for 86% of the participants. There were four representative types of radiotherapy plan based on radiation technology among these units. Of the 37 units, 18 used intensity-modulated radiotherapy, 6 adopted three-dimensional conformal radiotherapy, 2 chose volumetric modulated arc therapy, and 1 delivered two-dimensional traditional radiotherapy; only 10 units applied magnetic resonance imaging (MRI)-computed tomography registration and fusion for gross tumor volume delineation in NPC treatment, and only 3 units routinely acquired nasopharyngeal and neck MRI scans to evaluate tumor shrinkage during treatment. Conclusion: Obvious distinctions exist between various units in Chongqing city in radiotherapeutic strategy, radiotherapy plan, frequency of image-guided radiation therapy, and mid-treatment evaluation for NPC radiotherapy. We need to learn and apply NPC guideline and consensus to improve NPC radiotherapy in Chongqing and to construct a rule with regional characteristics.

Background and Objectives: In neurorehabilitation, exoskeleton plays a key role among the numerous innovative and advanced frontiers in technology. The exoskeleton is intended for rehabilitation and mobility in patients with neurological motor diseases. The aim of this study is to evaluate the impact of robotic training in body perception and mood. Methods: Two patients, one affected by stroke and another affected by spinal cord injury admitted to our rehabilitation unit, have been studied. We used two exoskeletons (Ekso and Indego). Training occurred 3 days a week for a total of forty sessions, with a duration of 50–60 min each session. Psychological tests focused on depression (Beck Depression Inventory), self-perception (body uneasiness test A), and the workload (NASA-Task Load Index) were used. Results: After the treatment, we found a great improvement in mood disorders and body perception in the patients. Conclusions: Patients with neurological motor diseases can increase motor and psychological skills using an active powered exoskeleton.

Many elderly people prefer to live at home independently. They and their relatives face challenges with respect to physical and mental health care in this environment. In addition, the traditional model of hospital-based centralized healthcare is now under stress due to the ageing population worldwide, especially in countries, such as Japan, China and Europe. Robots are now being used extensively for many different applications in business (e.g., materials handling) and homes (e.g., floor cleaning). On the other hand, researchers all over the world have been investigating the use of robots (e.g., PARO the therapeutic baby seal robot) to provide emotional support and well-being for the elderly. The EU project VictoryaHome was designed to trial telepresence robots for the care, safety and emotional well-being of the elderly across four countries in Europe and Australia. This paper examines the potential of integrated care of the elderly in their own homes and is based on the findings of the VictoryaHome project.

This work presents our vision and work-in-progress on a new platform for immersive virtual and augmented reality (AR) training. ImmersiMed is aimed at medical educational and professional institutions for educating nurses, doctors, and other medical personnel. ImmersiMed is created with multi-platform support and extensibility in mind. By creating consistent experiences across different platforms and applications, ImmersiMed intends to increase simulation availability. Furthermore, it is expected to improve the quality of training and prepare students better for more advanced tasks and boost confidence in their abilities. Tools for educators are being provided so new scenarios can be added without the intervention of costly content creators or programmers. This article addresses how Immersive's mixed platform approach can ease the transition from basic school training to real-world applications by starting from a virtual reality simulation and gradually let the student move on to guided AR in the real world. By explaining the idea of a single development platform for multiple applications using different technologies and by providing tools for educators to create their own scenarios, ImmersiMed will improve training quality and availability at a low training and simulation costs.

Automatic processing large amount of microscopic images is important for medical and biological studies. Deep learning has demonstrated better performance than traditional machine learning methods for processing massive quantities of images; therefore, it has attracted increasing attention from the research and industry fields. This paper summarizes the latest progress of deep learning methods in biological microscopic image processing, including image classification, object detection, and image segmentation. Compared to the traditional machine learning methods, deep neural networks achieved better accuracy without tedious feature selection procedure. Obstacles of the biological image analysis with deep learning methods include limited training set and imperfect image quality. Viable solutions to these obstacles are discussed at the end of the paper. With this survey, we hope to provide a reference for the researchers conducting biological microscopic image processing.

Game-based rehabilitation proved its efficacy in recent years, and the areas of intervention are increasing. In this article, we report the definition of a protocol for the treatment of people suffering from acute cervical spinal cord injury and its preliminary application with five patients. A suite of serious games using Kinect as device for game sessions is adopted for upper-limb rehabilitation. The possibility to customize the training plans by selecting different games for each patient gives the chance to include game created for other training targets (e.g., balance) that train further body parts (e.g., the trunk) and that can thus adapt the training to specific patient's needs.

Background and Objectives: The utility of postdischarge remote monitoring with patient self-measurement of physiological parameters has not been utilized in the elective colorectal surgical setting till date. Before full application of this utility, patient-acquired measurements' accuracy, and ability to detect deviation from normal physiological must be assessed. This study aims to ascertain the congruency of patient-measured and nurse-measured readings in the postoperative in-hospital setting, before future application in the home setting. Methods: This is a prospective single-institution study comparing patient and nurse measured readings of blood pressure, heart rate, oxygen saturation, and temperature, in ambulatory patients in the postoperative setting. Patients were provided with and trained on the usage of a handheld computing device with bluetooth-enabled measuring adjuncts preoperatively. Patients were instructed to acquire two sets of readings per day for 2 days. These were compared with nurse-acquired measurements and extrapolated to the modified “National Early Warning Score” system. Inter-rater concordance was analyzed using the Bland–Altman method for raw physiological measurements and for modified-National Early Warning Score (NEWS) risk and response categories. Results: A total of 40 elective colorectal patients were prospectively approached. Twenty-seven completed the study with 25 patients (15 males, age range 18–79, undergoing a variety of colorectal procedures) accruing a total of 98 datasets of physiological parameter readings. There were no significant differences/bias between blood pressure (P = 0.572), heart rate (0.122), and oxygen saturation (P = 0.308) readings. Patient and linked nurse measurements for all patients elicited the same modified NEWS clinical risk and required response in all instances. Conclusion: Patient self-measurement of physiological parameters and subsequent derived modified NEWS categories using a remote monitoring system are comparable to nurse-acquired measurements. Remote monitoring is technically feasible, and the next steps would be to trial this technology in the home setting.

Background and Objectives: Diet plays a huge role in health, both by increasing metabolic disease risks and acutely through adverse interactions with diseases and medications. Multimorbid and polypharmaceutical patients are at a particularly high risk of such interactions due to the number of drugs they take. This leads to avoidable hospitalizations and poor compliance. This study built and demonstrated a tool that provides personalized dietary advice that accounts for a patient's combination of disease and drugs in real-time on their mobile device. Methods: A comprehensive list of validated drug-disease-food interactions from several reputable sources was constructed. This was compiled into a knowledge graph using the RACE array logic platform. This interactions knowledge graph was used to power a personalized dietary advisor application on a mobile device. Results: Data from over 500,000 drug-disease-food interactions including 1,699 food ingredients and 9,526 disease interactions were compiled into a highly compressed knowledge model. This was used to inform recommendations for individual complex patients. It was also tested on virtual population of 10,000 multimorbid and polypharmaceutical patients. Conclusions: This study showed that digital health tools can provide highly contextual and adaptive responses from a single knowledge graph. The study showed it is possible to provide highly personalized health advice to complex patients in real-time on their own mobile device without having to hold such private information on a server. This enables highly secure, private and personalized digital health tools to be built.

Background and Objectives: The Singapore population is aging rapidly, with increased prevalence of chronic diseases and healthcare demand. Telemonitoring of vital signs will enable better care of the patient. However, daily monitoring requires a change in lifestyle and compliance may be an issue. Materials and Methods: A total of 18 patients in 4 demographics were identified. Telemonitoring equipment was deployed to them for 3 months. Results: After 3 months, the well individual did not use the monitoring devices. 50% of the patients with chronic medical disease <65 years old continued the use of the devices. 2 out of 7 activities of daily living (ADL) independent individuals >65 years old continued the daily monitoring and almost all (5 out of 6) ADL dependent patients continued daily routine monitoring. The dropout may be due to technical issues, user fatigue, change in caregiver or resistance to technology. Conclusions: Remote monitoring will be more successful if the individual already is doing routine self-monitoring or has a life-threatening health-related event. Technical support is also important to help retrain the person in using the devices and for troubleshooting.

The emerging rapidly developing new technologies bring digital applications into our society. Digital technology had been widely applied to various health-care fields including the area of preventative health care. Digital preventative health care is the provision of health-care services for the prevention of diseases, controlling of disease processes, and other health-care services related to preventative health care by the use of digital technology. It is an essential element in the future development of the health-care environment. This review article highlights the current situation of digital technology used in providing health-care services for disease prevention in Myanmar health-care environment. It also covers the future direction of implementing digital technology in other specific areas of preventative health care in Myanmar designed to provide health-care delivery and services more effectively.

Background and Objectives: In this study, the spatial courses of the connecting tubule (CNT) of nephron from different depth of cortex and the collecting duct (CD) in mouse kidney was established with the aid of three-dimensional visualization technology. Subjects and Methods: Kidneys from three C57/BL/6J mice were removed after perfusion fixation. The tissue blocks were cut perpendicular to the longitudinal axis of the kidney and embedded in Epon-812. A total of 2000, 2.5-μm-thick consecutive sections were obtained from the renal capsule to papilla. After acquiring the digitalized images and alignment, the CNT from 137 nephrons were traced with the custom-made programs. The spatial arrangement of the CNT was visualized, and the length was measured. Results: Each CD received CNT from 5 to 7 nephrons. The CNT from different level of cortex all drained into the CD at superficial cortex but took different path. The CNT from superficial cortical nephron joined CD directly, while the CNT from middle and juxtamedullary cortical nephron joined each other to form an arcade, and the latter drained into CD at superficial cortex. The length of the arcade ranged 400–800 μm. Conclusions: The CNT joined CD at superficial cortex, which means the fluid along the CD from the cortex would not be added from outside, contributing to stabilization of the hormone regulation in the transportation of solutes and water along the CD from cortex to medulla.

Background and Objectives: Current developments in electroencephalography (EEG) foster medical and nonmedical applications outside the hospitals. For example, continuous monitoring of mental and cognitive states can contribute to avoid critical and potentially dangerous situations in daily life. An important prerequisite for successful EEG at home is a real-time classification of mental states. In this article, we compare different machine learning algorithms for the classification of eye states based on EEG recordings. Materials and Methods: We tested 23 machine learning algorithms from the Waikato Environment for Knowledge Analysis toolkit. Each classifier was analyzed on four different datasets, since two separate approaches – called sample-wise and segment-wise – in combination with raw and filtered data were applied. These datasets were recorded for 27 volunteers. The different approaches are compared in terms of accuracy, complexity, training time, and classification time. Results: Ten out of 23 classifiers fulfilled the determined requirements of high classification accuracy and short time of classification and can be denoted as applicable for real-time EEG eye state classification. Conclusions: We found that it is possible to predict eye states using EEG recordings with an accuracy from about 96% to over 99% in a real-time system. On the other hand, we found no best, universal method of classifying EEG eye states in all volunteers. Therefore, we conclude that the best algorithm should be chosen individually, using the optimal classification accuracy in combination with time of classification as the criterion.

For decision support, a globally connected digital information system is desirable, which uses diagnostic findings and makes language independently statistical (anonymized) information from similar cases of all countries available. It can be realized efficiently in the following way: The definitions of all used diagnostics and measurement procedures are placed online. The defined data are called “Domain Vectors.” Doctors who use the online definitions get measurement results as Domain Vectors in comparable and searchable form. Anonymized selective statistics over patient groups with similar data can help to find the best treatment. Precondition for such distributed and simultaneously connected Domain Vectors are their global online definitions. Every Domain Vector only consists of a link to its definition (e.g., via URL or an abbreviated equivalent) plus numbers. This article explains details and concludes that introduction of the Domain Vectors with their online definitions would be an important step toward internationally connected medicine.

Rapid developments in sensing and imaging technologies are transforming our ability to detect, diagnose, and manage disease. Given financial pressures on managed health care, there is increasing emphasis on disease prevention and wellness programs have become a feature of many plans. Recent market developments include the merger of pharmacy and health-care organizations, which promises to open new avenues in health maintenance and diagnosis. Herein, we review recent developments in the field and present a vision for how point-of-care providers can play a pivotal role in prodromal diagnostics and wellness programs. Emphasis is placed on recent advances in digital detection technologies which have the potential to accelerate evolution of such models. An additional potential benefit of large-scale community-based screening centers lies in the identification of patients for recruitment into clinical trials, and mechanisms are proposed.

Background: In this research, the pulse wave data of 274 subjects from both the patient and control groups are evaluated and analyzed. Based on the pulse wave analysis of those subjects, a study of diagnosing cardiovascular diseases is conducted. Methods and Results: By investigating the correlation between the cardiac indices Reverse Shoulder Index (RSI) and Ratio of Distance for patients with cardiovascular diseases from different age and gender groups, several common and important observations are reported. By carrying out case studies, we have verified some of our findings with several patient cases. Conclusion: In this research, pulse wave analysis is applied for the study of cardiovascular diseases with some important observations. We expect that our discoveries in this research can eventually help the end-users in cardiovascular diseases diagnosis.

Background and Objectives: Cervical total disc replacement (TDR) is a novel dynamically stabilizing technique for the symptomatic cervical intervertebral segment. While the long-term effect of mainstream cervical nonconstrained artificial disc group (CNAD) does not match the theoretical effects of mobility preserving and neural decompression. The cervical semiconstrained elastic integrated artificial disc (CSID) may be a more reasonable design. However, beneficial or adverse effects of this design have not been measured and data for biomechanical effect are unavailable. The aim of this study is to assess the biomechanical effect of CSID on the segmental motion at implanted and adjacent levels. Methods: This study was supported by medical science developmental funding of Nanjing (20,000 dollars). Eight cadaveric C3–T1 specimens were loaded in flexion/extension (F/E), axial rotation (AR), and lateral bending (LB) with CSID, CNAD, and anterior fusion (AF) implanted at C5–C6 level alternatively. The range of motion (ROM), neutral zone (NZ), and elastic zone (EZ) at implanted and adjacent levels were measured. The mean values of parameters in the intact specimen group (INT), CSID group, CNAD group, and AF group were compared statistically (n = 8). Results: There was no significant difference of ROM, NZ, and EZ at implanted and adjacent levels between CSID and INT in F/E, AR, and LB (P > 0.05). CNAD caused a significant change of EZ in F/E and LB and ROM in LB at implanted level. Meantime, CNAD caused ROM increasing at adjacent levels (P < 0.05). AF caused the most significant changes of ROM, NZ, and EZ in F/E, AR and LB, compared to CSID and CNAD (P < 0.05). Conclusions: The semiconstrained elastic integrated design of cervical artificial disc may mimic of physiological disc's biomechanical effects on segmental kinematics at implanted and adjacent levels more closely, compared to nonconstrained discs and AF. CSID disc may reduce the acceleration of postTDR degeneration at the implanted and adjacent levels due to this promoted biomechanical performance. CSID disc could be a potential candidate for future cervical artificial intervertebral prosthesis studies.

Objectives: This article describes novel magnetic resonance imaging (MRI)-compatible focused ultrasound robotic systems and agar-based MRI-compatible ultrasonic phantoms mimicking bone. Materials and Methods: All the robotic systems and phantoms were developed using three-dimensional (3D) printing technology using plastic material. The tissue surrounding the bone in the phantoms was mimicked using agar-based solutions. Results: The article presents MRI-guided focused ultrasound robotic systems for brain, prostate, and gynecological targets. It also reports on MRI-compatible ultrasonic phantoms for brain, breast, bone, and motion. Conclusions: The popular 3D printing technology serves a major role in MRI-guided focused ultrasound surgery because MRI-guided focused ultrasound robotic systems can be developed. In addition, 3D printing can be used to develop MR-compatible phantoms that include bone structures for testing the safety and efficacy of focused ultrasound applications. All the developed structures have been evaluated in MRI environment using either mimicking materials or animals.

Background and Objectives: The diagnosis of cancer is concerned, and the prediction of cell carcinoma is of great importance for the treatment. Materials and Methods: First, we obtain a series of slices of tumor cell pathology in clinical data, with being followed training sets and test sets gained by adding data model. Then, we design a convolutional neural network training and prediction model. After that, we optimize parameters for training and prediction model, combining experience. Results: In experiment, the accuracy of the model predicting for cell carcinoma is 87.38%. Conclusions: This study provides a reference that predicts the extent of cell carcinoma progression by using deep learning model.

Background and Objectives: In this article, we propose an image segmentation model based on Chan-Vese (CV) for image segmentation. By taking into account the local features of the image, the new proposed model can successfully segment images with intensity nonuniformity. Materials and Methods: We quantitatively compare our method with other two state-of-the-art algorithms, namely, CV model and local binary fitting (LBF) model in segmenting synthetic MR images with the ground truth from BrainWeb; the data can be available at: https://www.mni/mcgill.ca/brainweb/. For segmenting the missing and weak boundaries, to deal with the intensity inhomogeneity, based on the LBF model, we introduced the convex total variation regularization term, for explicit smoothing of the level set function ø. The evolution equation will be solved through the level set method of calculus of variations. Results: In the experimental processing, we use some real images and magnetic resonance imaging brain images as the experimental images, to validate the stabilization of algorithm. The experimental results on comprehensive and sincerity images show the outstanding of our proposed model with reference to stabilization and availability. Conclusions: We propose a new segmentation local information of an image and introduce a new regularization functional is to keep the level set function smooth. Finally, various experimental results on real and low-contrast image, showing which is a powerful type of images, including some that would be difficult to segment with gradient-based methods. In addition, the advantages of the proposed model are better than CV model and the LBF model. Our new model can effectively segment a real image.

Background and Objectives: The increasing clinical use of torso positron emission tomography/computed tomography (PET/CT) demands automated segmentation of torso organs from PET/CT images. We attempt to use the multi-atlas segmentation approach for trunk organ segmentation from the low-dose CT images of PET/CT. Since atlas selection is a prerequisite step for multi-atlas segmentation, this study focuses on evaluating the performance of different atlas selection strategies for torso organ segmentation. Methods: We evaluated two criteria for atlas selection, including image similarity and body mass index (BMI) difference between the atlas and the target image. Based on the two criteria, ten atlases are selected and registered to the target image, followed by the label fusion step to achieve final segmentation. Results: The BMI criterion yields comparable segmentation accuracy to the image similarity criterion but with much less computation time. All the evaluated atlas selection methods have Dice >0.9 for the lungs, heart, and liver and Dice < 0.85 for the skeleton, spleen, and kidneys. The inter-method differences are not significant for the high-contrast and big-sized organs such as skeleton, lungs, heart, and liver. For the low-contrast and smaller-sized organs such as spleen and kidneys, none of the atlas selection methods significantly outperforms random atlas selection. Conclusions: BMI is an effective and efficient atlas selection criterion for low-dose torso CT images. The spleen and kidneys are difficult to get good segmentation, no matter which atlas selection method is used. It is important to develop more effective atlas selection methods for the spleen and kidneys.

Background and Objectives: Multimodal image registration is a crucial step in prostate cancer radiation therapy scheme. However, it can be challenging due to the obvious appearance difference between computed tomography (CT) and magnetic resonance imaging (MRI) and unavoidable organ motion. Accordingly, a nonrigid registration framework for precisely registering multimodal prostate images is proposed in this paper. Materials and Methods: In this work, multimodal prostate image registration between CT and MRI is achieved using a hybrid model that integrates multiresolution strategy and Demons algorithm. Furthermore, to precisely describe the deformation of prostate, B-spline-based registration is utilized to refine the initial registration result of multiresolution Demons algorithm. Results: To evaluate our method, experiments on clinical prostate data sets of nine participants and comparison with the conventional Demons algorithm are conducted. Experimental results demonstrate that the proposed registration method outperforms the Demons algorithm by a large margin in terms of mutual information and correlation coefficient. Conclusions: These results show that our method outperforms the Demons algorithm and can achieve excellent performance on multimodal prostate images even the appearances of prostate change significantly. In addition, the results demonstrate that the proposed method can help to localize the prostate accurately, which is feasible in clinical.

Background and Objectives: Three-dimensional (3D) printing has potential value in medical applications with increasing reports in the diagnostic assessment of cardiovascular diseases. The use of 3D printing in replicating pulmonary artery anatomy and diagnosing pulmonary embolism is very limited. The purpose of this study was to develop a 3D printed pulmonary artery model and test different computed tomography (CT) scanning protocols for determination of an optimal protocol with acceptable image quality but low radiation dose. Materials and Methods: A patient-specific 3D printed pulmonary artery model was created based on contrast-enhanced CT images in a patient with suspected pulmonary embolism. Different CT pulmonary angiography protocols consisting of 80, 100, and 120 kVp, pitch 0.7, 0.9, and 1.2 with 1 mm slice thickness, and 0.6 mm reconstruction interval were tested on the phantom. Quantitative assessment of image quality in terms of signal-to-noise ratio (SNR) was measured in the images acquired with different protocols. Measurements in pulmonary artery diameters were conducted and compared between pre- and post-3D printed images and 3D printed model. Results: The 3D printed model was found to replicate normal pulmonary artery with high accuracy. The mean difference in diameter measurements was <0.8 mm (<0.5% deviation in diameter). There was no significant difference in SNR measured between these CT protocols (P = 0.96–0.99). Radiation dose was reduced by 55% and 75% when lowering kVp from 120 to 100 and 80 kVp, without affecting image quality. Conclusions: It is feasible to produce a 3D printed pulmonary artery model with high accuracy in replicating normal anatomy. Different CT scanning protocols are successfully tested on the model with 80 kVp and pitch 0.9 being the optimal one with resultant diagnostic images but at much lower radiation dose.

Background and Objectives: The aim of this study is to investigate the application of three-dimensional (3D) visualization technique in the surgical treatment of malignant tumors of the hilar and common bile ducts. Materials and Methods: A total of 23 patients admitted from January 2015 to April 2017 for surgical treatment were analyzed, of whom 13 patients underwent medical image 3D visualization system (treatment group) while 10 underwent surgery alone (control group). Indicators to the treatment effects were recorded and compared between the two groups, including the operation time, intraoperative bleeding volume, postoperative hospitalization time, the number of dissected lymph nodes, the incidence of all postoperative complications, and the alanine transaminase (ALT), albumin (ALB), and total bilirubin (TBIL) monitored on days 1, 3, 5, and 7 after the operation. Results: In the treatment group and control group, the operation time was 194.66 ± 13.79 and 230.81 ± 27.07 min (t = 3.857, P = 0.002), the intraoperative bleeding volume was 274.28 ± 44.57 and 320.69 ± 35.90 mL (t = 2.686, P = 0.014), the postoperative hospitalization time was 11.15 ± 1.25 and 15.25 ± 1.75d (t = 6.557, P = 0.000), the number of dissected lymph nodes 10.46 ± 1.71 and 7.40 ± 0.97 (t = 5.050, P = 0.000), and the incidence of all postoperative complications 7.69% and 60% (χ² = 7.304, P = 0.019), respectively. The level of ALT and TBIL was significantly higher in the treatment group than in the control group, whereas the level of ALB was significantly lower in the treatment group than in the control group on days 3, 5, and 7 (P < 0.05). The recovery of liver function was better in the treatment group than in the control group. In addition, no perioperative deaths were found in either group. Conclusions: In the surgical treatment of malignant tumors occurring in the hilar to the common bile duct, 3D visualization technology can reduce the operation injury and intraoperative bleeding, decrease the incidence of postoperative complications, improve the safety and effectiveness of the operation, and promote the recovery of liver function, thus demonstrating promising short-term efficacy.

The pursuit of digital biomarkers wherein signal outputs from biosensors are collated to inform health-care decisions continues to evolve at a rapid pace. In the field of neurodegenerative disorders, a goal is to augment subjective patient-reported inputs with patient-independent verifiable data that can be used to recommend interventive measures. For example, in the case of Alzheimer's disease, such tools might preselect patients in the presymptomatic and prodromal phases for definitive positron emission tomographic analysis, allowing accurate staging of disease and providing a reference point for subsequent therapeutic and other measures. Selection of appropriate and meaningful digital biomarkers to pursue, however, requires deep understanding of the disease state and its ecological relationship to the instrumental activities of daily living scale. Similar opportunities and challenges exist in a number of other chronic disease states including Parkinson's, Huntington's, and Duchenne's disease, multiple sclerosis, and cardiovascular disease. This review will highlight progress in device technology, the need for holistic approaches for data inputs, and regulatory pathways for adoption. The review focuses on published work from the period 2012–2017 derived from online searches of the most widely used abstracting portals.