Development of a Personalized Multiclass Classification Model to Detect Blood Pressure Variations Associated with Physical or Cognitive Workload.

Comprehending the regulatory mechanisms influencing blood pressure control is pivotal for continuous monitoring of this parameter. Implementing a personalized machine learning model, utilizing data-driven features, presents an opportunity to facilitate tracking blood pressure fluctuations in various conditions. In this work, data-driven photoplethysmograph features extracted from the brachial and digital arteries of 28 healthy subjects were used to feed a random forest classifier in an attempt to develop a system capable of tracking blood pressure. We evaluated the behavior of this latter classifier according to the different sizes of the training set and degrees of personalization used. Aggregated accuracy, precision, recall, and F1-score were equal to 95.1%, 95.2%, 95%, and 95.4% when 30% of a target subject's pulse waveforms were combined with five randomly selected source subjects available in the dataset. Experimental findings illustrated that incorporating a pre-training stage with data from different subjects made it viable to discern morphological distinctions in beat-to-beat pulse waveforms under conditions of cognitive or physical workload.

Wirelessly Powered 3D Printed Hierarchical Biohybrid Robots with Multiscale Mechanical Properties.

The integration of flexible and stretchable electronics into biohybrid soft robotics can spur the development of new approaches to fabricate biohybrid soft machines, thus enabling a wide variety of innovative applications. Inspired by flexible and stretchable wireless-based bioelectronic devices, we have developed untethered biohybrid soft robots that can execute swimming motions, which are remotely controllable by the wireless transmission of electrical power into a cell simulator. To this end, wirelessly-powered, stretchable, and lightweight cell stimulators were designed to be integrated into muscle bodies without impeding the robots' underwater swimming abilities. The cell stimulators function by generating controlled monophasic pulses of up to ∼9 V in biological environments. By differentiating induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) directly on the cell stimulators using an accordion-inspired, three-dimensional (3D) printing construct, we have replicated the native myofiber architecture with comparable robustness and enhanced contractibility. Wirelessly modulated electrical frequencies enabled us to control the speed and direction of the biohybrid soft robots. A maximum locomotion speed of ∼580 µm/s was achieved in robots possessing a large body size by adjusting the pacing frequency. This innovative approach will provide a platform for building untethered and biohybrid systems for various biomedical applications.

Zonal Intratumoral Delivery of Nanoparticles Guided by Surface Functionalization.

Delivery of small molecules and anticancer agents to malignant cells or specific regions within a tumor is limited by penetration depth and poor spatial drug distribution, hindering anticancer efficacy. Herein, we demonstrate control over gold nanoparticle (GNP) penetration and spatial distribution across solid tumors by administering GNPs with different surface chemistries at a constant injection rate via syringe pump. A key finding in this study is the discovery of different zone-specific accumulation patterns of intratumorally injected nanoparticles dependent on surface functionalization. Computed tomography (CT) imaging performed in vivo of C57BL/6 mice harboring Lewis lung carcinoma (LLC) tumors on their flank and gross visualization of excised tumors consistently revealed that intratumorally administered citrate-GNPs accumulate in particle clusters in central areas of the tumor, while GNPs functionalized with thiolated phosphothioethanol (PTE-GNPs) and thiolated polyethylene glycol (PEG-GNPs) regularly accumulate in the tumor periphery. Further, PEG functionalization resulted in larger tumoral surface coverage than PTE, reaching beyond the outer zone of the tumor mass and into the surrounding stroma. To understand the dissimilarities in spatiotemporal evolution across the different GNP surface chemistries, we modeled their intratumoral transport with reaction-diffusion equations. Our results suggest that GNP surface passivation affects nanoparticle reactivity with the tumor microenvironment, leading to differential transport behavior across tumor zones. The present study provides a mechanistic understanding of the factors affecting spatiotemporal distribution of nanoparticles in the tumor. Our proof of concept of zonal delivery within the tumor may prove useful for directing anticancer therapies to regions of biomarker overexpression.

A novel system for measuring visual potentials evoked by passive head-mounted display stimulators.

PURPOSE: The objective of this work is to evaluate the performances of a novel integrated device, based on passive head-mounted display (HMD), for the pattern reversal visual evoked potential (PR-VEP) clinical test. METHODS: Google Cardboard® is used as passive HMD to generate the checkerboard pattern stimuli through an Android® application. Electroencephalographic signals are retrieved and processed over 20 subjects, 12 females and 8 males between 20 and 26 years. Morphological PR-VEPs and frequency response were compared with previous literature results, to test the reproducibility and the efficacy of the proposed solution. RESULTS: PR-VEPs evoked by our novel prototype showed typical triphasic waveforms in moderate agreement with those obtained with other more expensive HMDs and standard commercial devices. Statistical analysis did not highlight strong differences among the systems over the features analyzed except for the P100 amplitude and peak time (**p < 0.005). CONCLUSION: The proposed solution opens the door for a new generation of non-invasive first-level diagnostic devices of optic nerve pathologies inexpensive and easy to access.

Combining Action Observation Treatment with a Brain-Computer Interface System: Perspectives on Neurorehabilitation.

Action observation treatment (AOT) exploits a neurophysiological mechanism, matching an observed action on the neural substrates where that action is motorically represented. This mechanism is also known as mirror mechanism. In a typical AOT session, one can distinguish an observation phase and an execution phase. During the observation phase, the patient observes a daily action and soon after, during the execution phase, he/she is asked to perform the observed action at the best of his/her ability. Indeed, the execution phase may sometimes be difficult for those patients where motor impairment is severe. Although, in the current practice, the physiotherapist does not intervene on the quality of the execution phase, here, we propose a stimulation system based on neurophysiological parameters. This perspective article focuses on the possibility to combine AOT with a brain-computer interface system (BCI) that stimulates upper limb muscles, thus facilitating the execution of actions during a rehabilitation session. Combining a rehabilitation tool that is well-grounded in neurophysiology with a stimulation system, such as the one proposed, may improve the efficacy of AOT in the treatment of severe neurological patients, including stroke patients, Parkinson's disease patients, and children with cerebral palsy.

Long lasting mucoadhesive membrane based on alginate and chitosan for intravaginal drug delivery.

The intravaginal route of administration can be exploited to treat local diseases and for systemic delivery. In this work, we developed an alginate/chitosan membrane sufficiently stable in a simulated vaginal fluid and able to dissolve over time at a very slow and linear rate. The membrane demonstrated good mechanical properties both in its swollen and dry form. As a study case, we evaluated the viability of this potential drug delivery system for the treatment of bacterial vaginosis, a common disease affecting women in their reproductive age. Metronidazole was effectively included in the alginate/chitosan membrane and its bactericide effect was demonstrated against Staphylococcus aureus and Gardnerella vaginalis, simultaneously showing good biocompatibility with a cervix epithelial cell line. Since this alginate/chitosan membrane is stable in a simulated vaginal environment, is easy to fabricate and can be used for the controlled release of a model drug, it represents a promising drug delivery system for local intravaginal applications.

AI technology for remote clinical assessment and monitoring.

OBJECTIVE: To report the clinical validation of an innovative, artificial intelligence (AI)-powered, portable and non-invasive medical device called Wound Viewer. The AI medical device uses dedicated sensors and AI algorithms to remotely collect objective and precise clinical data, including three-dimensional (3D) wound measurements, tissue composition and wound classification through the internationally recognised Wound Bed Preparation (WBP) protocol; this data can then be shared through a secure General Data Protection Regulation (GDPR)- and Health Insurance Portability and Accountability Act (HIPAA)-compliant data transfer system. This trial aims to test the reliability and precision of the AI medical device and its ability to aid health professionals in clinically evaluating wounds as efficiently remotely as at the bedside. METHOD: This non-randomised comparative clinical trial was conducted in the Clinica San Luca (Turin, Italy). Patients were divided into three groups: (i) patients with venous and arterial ulcers in the lower limbs; (ii) patients with diabetes and presenting with diabetic foot syndrome; and (iii) patients with pressure ulcers. Each wound was evaluated for area, depth, volume and WBP wound classification. Each patient was examined once and the results, analysed by the AI medical device, were compared against data obtained following visual evaluation by the physician and research team. The area and depth were compared with a Kruskal-Wallis one-way analysis of variations in the obtained distribution (expected p-value>0.1 for both tests). The WBP classification and tissue segmentation were analysed by directly comparing the classification obtained by the AI medical device against that of the testing physician. RESULTS: A total of 150 patients took part in the trial. The results demonstrated that the AI medical device's AI algorithm could acquire objective clinical parameters in a completely automated manner. The AI medical device reached 97% accuracy against the WBP classification and tissue segmentation analysis compared with that performed in person by the physician. Moreover, data regarding the measurements of the wounds, as analysed through the Kruskal-Wallis technique, showed that the data distribution proved comparable with the other methods of measurement previously clinically validated in the literature (p=0.9). CONCLUSION: These findings indicate that remote wound assessment undertaken by physicians is as effective through the AI medical device as bedside examination, and that the device was able to assess wounds and provide a precise WBP wound classification. Furthermore, there was no need for manual data entry, thereby reducing the risk of human error while preserving high-quality clinical diagnostic data.

Embedded Bio-Mimetic System for Functional Electrical Stimulation Controlled by Event-Driven sEMG.

The analysis of the surface ElectroMyoGraphic (sEMG) signal for controlling the Functional Electrical Stimulation (FES) therapy is being widely accepted as an active rehabilitation technique for the restoration of neuro-muscular disorders. Portability and real-time functionalities are major concerns, and, among others, two correlated challenges are the development of an embedded system and the implementation of lightweight signal processing approaches. In this respect, the event-driven nature of the Average Threshold Crossing (ATC) technique, considering its high correlation with the muscle force and the sparsity of its representation, could be an optimal solution. In this paper we present an embedded ATC-FES control system equipped with a multi-platform software featuring an easy-to-use Graphical User Interface (GUI). The system has been first characterized and validated by analyzing CPU and memory usage in different operating conditions, as well as measuring the system latency (fulfilling the real-time requirements with a 140 ms FES definition process). We also confirmed system effectiveness, testing it on 11 healthy subjects: The similarity between the voluntary movement and the stimulate one has been evaluated, computing the cross-correlation coefficient between the angular signals acquired during the limbs motion. We obtained high correlation values of 0.87 ± 0.07 and 0.93 ± 0.02 for the elbow flexion and knee extension exercises, respectively, proving good stimulation application in real therapy-scenarios.

Assessing the Feasibility of Augmenting Fall Detection Systems by Relying on UWB-Based Position Tracking and a Home Robot.

Falls in the home environment are a primary cause of injury in older adults. According to the U.S. Centers for Disease Control and Prevention, every year, one in four adults 65 years of age and older reports experiencing a fall. A variety of different technologies have been proposed to detect fall events. However, the need to detect all fall instances (i.e., to avoid false negatives) has led to the development of systems marked by high sensitivity and hence a significant number of false alarms. The occurrence of false alarms causes frequent and unnecessary calls to emergency response centers, which are critical resources that should be utilized only when necessary. Besides, false alarms decrease the level of confidence of end-users in the fall detection system with a negative impact on their compliance with using the system (e.g., wearing the sensor enabling the detection of fall events). Herein, we present a novel approach aimed to augment traditional fall detection systems that rely on wearable sensors and fall detection algorithms. The proposed approach utilizes a UWB-based tracking system and a home robot. When the fall detection system generates an alarm, the alarm is relayed to a base station that utilizes a UWB-based tracking system to identify where the older adult and the robot are so as to enable navigating the environment using the robot and reaching the older adult to check if he/she experienced a fall. This approach prevents unnecessary calls to emergency response centers while enabling a tele-presence using the robot when appropriate. In this paper, we report the results of a novel fall detection algorithm, the characteristics of the alarm notification system, and the accuracy of the UWB-based tracking system that we implemented. The fall detection algorithm displayed a sensitivity of 99.0% and a specificity of 97.8%. The alarm notification system relayed all simulated alarm notification instances with a maximum delay of 106 ms. The UWB-based tracking system was found to be suitable to locate radio tags both in line-of-sight and in no-line-of-sight conditions. This result was obtained by using a machine learning-based algorithm that we developed to detect and compensate for the multipath effect in no-line-of-sight conditions. When using this algorithm, the error affecting the estimated position of the radio tags was smaller than 0.2 m, which is satisfactory for the application at hand.

Scaling Organic Electrochemical Transistors Down to Nanosized Channels.

The perspective of downscaling organic electrochemical transistors (OECTs) in the nanorange is approached by depositing poly(3,4-ethylenedioxythiophene) polystyrene sulfonate (PEDOT:PSS) on electrodes with a nanogap designed and fabricated by electromigration induced break junction (EIBJ) technique. The electrical response of the fabricated devices is obtained by acquiring transfer characteristics in order to clarify the specific main characteristics of OECTs with sub-micrometer-sized active channels (nanogap-OECTs). On the basis of their electrical response to different scan times, the nanogap-OECT shows a maximum transconductance unaffected upon changing scan times in the time window from 1 s to 100 µs, meaning that fast varying signals can be easily acquired with unchanged amplifying performance. Hence, the scaling down of the channel size to the nanometer scale leads to a geometrical paradigm that minimizes effects on device response due to the cationic diffusion into the polymeric channel. A comprehensive study of these features is carried out by an electrochemical impedance spectroscopy (EIS) study, complemented by a quantitative analysis made by equivalent circuits. The propagation of a redox front into the polymer bulk due to ionic diffusion also known as the "intercalation pseudocapacitance" is identified as a limiting factor for the transduction dynamics.

Simultaneous quantification of multiple bacterial metabolites using surface-enhanced Raman scattering.

Given the commercial importance of the compounds produced by genetically modified organisms, there is a need for screening methods which facilitate the evaluation of newly developed strains, especially during the phase of proof-of-concept development. We report a time-efficient analysis method for the screening of bacterial strains, which enables the detection of two structurally similar secondary bacterial metabolites. By combining liquid-liquid extraction and surface-enhanced Raman scattering we were able to quantify p-coumaric acid and cinnamic acid, produced by genetically modified E. coli from tyrosine and phenylalanine, respectively. With the simple sample pre-treatment method, and by applying a partial least squares data analysis method, we simultaneously detected the analytes from four E. coli strains cultured in the presence or absence of tyrosine and phenylalanine.

Assessing aberrant muscle activity patterns via the analysis of surface EMG data collected during a functional evaluation.

BACKGROUND: Surface electromyographic (EMG) recordings collected during the performance of functional evaluations allow clinicians to assess aberrant patterns of muscle activity associated with musculoskeletal disorders. This assessment is typically achieved via visual inspection of the surface EMG data. This approach is time-consuming and leads to accurate results only when the assessment is carried out by an EMG expert. METHODS: A set of algorithms was developed to automatically evaluate aberrant patterns of muscle activity. EMG recordings collected during the performance of functional evaluations in 62 subjects (22 to 61 years old) were used to develop and characterize the algorithms. Clinical scores were generated via visual inspection by an EMG expert using an ordinal scale capturing the severity of aberrant patterns of muscle activity. The algorithms were used in a case study (i.e. the evaluation of a subject with persistent back pain following instrumented lumbar fusion who underwent lumbar hardware removal) to assess the clinical suitability of the proposed technique. RESULTS: The EMG-based algorithms produced accurate estimates of the clinical scores. Results were primarily obtained using a linear regression approach. However, when the results were not satisfactory, a regression implementation of a Random Forest was utilized, and the results compared with those obtained using a linear regression approach. The root-mean-square error of the clinical score estimates produced by the algorithms was a small fraction of the ordinal scale used to rate the severity of the aberrant patterns of muscle activity. Regression coefficients and associated 95% confidence intervals showed that the EMG-based estimates fit well the clinical scores generated by the EMG expert. When applied to the clinical case study, the algorithms appeared to capture the characteristics of the muscle activity patterns associated with persistent back pain following instrumented lumbar fusion. CONCLUSIONS: The proposed approach relies on EMG-based measures to generate accurate estimates of the severity of aberrant patterns of muscle activity. The results obtained in the case study suggest that the proposed technique is suitable to derive clinically-relevant information from EMG data collected during functional evaluations.

Remote magnetic switch off microgate for nanofluidic drug delivery implants.

In numerous pathologies, implantable drug delivery devices provide advantages over conventional oral or parenteral approaches. Based on the site of implantation and release characteristics, implants can afford either systemic delivery or local administration, whereby the drug is delivered at or near the site of intended action. Unfortunately, current implantable drug delivery systems provide limited options for intervention in the case of an adverse reaction to the drug or the need for dosage adjustment. In the event that drug delivery must be terminated, an urgent surgical retrieval may be the only reliable option. This could be a time sensitive and costly effort, requiring access to trained professionals and emergency medical facilities. To address such limitations, here we demonstrate, in vitro and ex vivo, a novel microsystem for the rapid and effective switch off of drug delivery from an implantable nanofluidic system, by applying a safe external electromagnetic field in the FDA approved dose range. This study represents a proof of concept for a technology with potential for broad applicability to reservoir-based delivery implants for both complete interruption or remote titration of drug administration.

A Multipurpose CMOS Platform for Nanosensing.

This paper presents a customizable sensing system based on functionalized nanowires (NWs) assembled onto complementary metal oxide semiconductor (CMOS) technology. The Micro-for-Nano (M4N) chip integrates on top of the electronics an array of aluminum microelectrodes covered with gold by means of a customized electroless plating process. The NW assembly process is driven by an array of on-chip dielectrophoresis (DEP) generators, enabling a custom layout of different nanosensors on the same microelectrode array. The electrical properties of each assembled NW are singularly sensed through an in situ CMOS read-out circuit (ROC) that guarantees a low noise and reliable measurement. The M4N chip is directly connected to an external microcontroller for configuration and data processing. The processed data are then redirected to a workstation for real-time data visualization and storage during sensing experiments. As proof of concept, ZnO nanowires have been integrated onto the M4N chip to validate the approach that enables different kind of sensing experiments. The device has been then irradiated by an external UV source with adjustable power to measure the ZnO sensitivity to UV-light exposure. A maximum variation of about 80% of the ZnO-NW resistance has been detected by the M4N system when the assembled 5 µ m × 500 nm single ZnO-NW is exposed to an estimated incident radiant UV-light flux in the range of 1 nW-229 nW. The performed experiments prove the efficiency of the platform conceived for exploiting any kind of material that can change its capacitance and/or resistance due to an external stimulus.

Electrophoretic deposition of mesoporous bioactive glass on glass-ceramic foam scaffolds for bone tissue engineering.

In this work, the coating of 3-D foam-like glass-ceramic scaffolds with a bioactive mesoporous glass (MBG) was investigated. The starting scaffolds, based on a non-commercial silicate glass, were fabricated by the polymer sponge replica technique followed by sintering; then, electrophoretic deposition (EPD) was applied to deposit a MBG layer on the scaffold struts. EPD was also compared with other techniques (dipping and direct in situ gelation) and it was shown to lead to the most promising results. The scaffold pore structure was maintained after the MBG coating by EPD, as assessed by SEM and micro-CT. In vitro bioactivity of the scaffolds was assessed by immersion in simulated body fluid and subsequent evaluation of hydroxyapatite (HA) formation. The deposition of a MBG coating can be a smart strategy to impart bioactive properties to the scaffold, allowing the formation of nano-structured HA agglomerates within 48 h from immersion, which does not occur on uncoated scaffold surfaces. The mechanical properties of the scaffold do not vary after the EPD (compressive strength ~19 MPa, fracture energy ~1.2 × 10(6) J m(-3)) and suggest the suitability of the prepared highly bioactive constructs as bone tissue engineering implants for load-bearing applications.

A Wearable Real-Time System for Simultaneous Wireless Power and Data Transmission to Cortical Visual Prosthesis.

Wireless, miniaturised and distributed neural interfaces are emerging neurotechnologies. Although extensive research efforts contribute to their technological advancement, the need for real-time systems enabling simultaneous wireless information and power transfer toward distributed neural implants remains crucial. Here we present a complete wearable system including a software for real-time image capturing, processing and digital data transfer; an hardware for high radiofrequency generation and modulation via amplitude shift keying; and a 3-coil inductive link adapt to operate with multiple miniaturised receivers. The system operates in real-time with a maximum frame rate of 20 Hz, reconstructing each frame with a matrix of 32 × 32 pixels. The device generates a carrier frequency of 433.92 MHz. It transmits the highest power of 32 dBm with a data rate of 6 Mbps and a variable modulation index as low as 8 %, thus potentially enabling wireless communication with 1024 miniaturised and distributed intracortical microstimulators. The system is primarily conceived as an external wearable device for distributed cortical visual prosthesis covering a visual field of 20 °. At the same time, it is modular and versatile, being suitable for multiple applications requiring simultaneous wireless information and power transfer to large-scale neural interfaces.

Synthesis and characterization of hybrid hyaluronic acid-gelatin hydrogels.

Biomimetic hybrid hydrogels have generated broad interest in tissue engineering and regenerative medicine. Hyaluronic acid (HA) and gelatin (hydrolyzed collagen) are naturally derived polymers and biodegradable under physiological conditions. Moreover, collagen and HA are major components of the extracellular matrix (ECM) in most of the tissues (e.g., cardiovascular, cartilage, neural). When used as a hybrid material, HA-gelatin hydrogels may enable mimicking the ECM of native tissues. Although HA-gelatin hybrid hydrogels are promising biomimetic substrates, their material properties have not been thoroughly characterized in the literature. Herein, we generated hybrid hydrogels with tunable physical and biological properties by using different concentrations of HA and gelatin. The physical properties of the fabricated hydrogels including swelling ratio, degradation, and mechanical properties were investigated. In addition, in vitro cellular responses in both two and three-dimensional culture conditions were assessed. It was found that the addition of gelatin methacrylate (GelMA) into HA methacrylate (HAMA) promoted cell spreading in the hybrid hydogels. Moreover, the hybrid hydrogels showed significantly improved mechanical properties compared to their single component analogs. The HAMA-GelMA hydrogels exhibited remarkable tunability behavior and may be useful for cardiovascular tissue engineering applications.

Kinetic Perimetry on Virtual Reality Headset.

OBJECTIVE: We present a portable automatic kinetic perimeter based on a virtual reality (VR) headset device as an innovative and alternative solution for the screening of clinical visual fields. We compared the performances of our solution with a gold standard perimeter, validating the test on healthy subjects. METHODS: The system is composed of an Oculus Quest 2 VR headset with a clicker for participant response feedback. An Android app was designed in Unity to generate moving stimuli along vectors, following a standard Goldmann kinetic perimetry approach. Sensitivity thresholds are obtained by moving centripetally three different targets (V/4e, IV/1e, III/1e) along 24 or 12 vectors from an area of non-seeing to an area of seeing and then transmitted wirelessly to a PC. A Python real-time algorithm processes the incoming kinetic results and displays the hill of vision in a two-dimensional map (isopter). We involved 21 subjects (5 males and 16 females, age range 22-73 years) for a total of 42 eyes tested with our proposed solution, and results were compared with a Humphrey visual field analyzer to test reproducibility and efficacy. RESULTS: isopters generated with the Oculus headset were in good agreement with those acquired with a commercial device (Pearson's correlation values r > 0.83 for each target). CONCLUSIONS: we demonstrate the feasibility of VR kinetic perimetry by comparing performances between our system and a clinically used perimeter in healthy subjects. SIGNIFICANCE: proposed device leads the way for a portable and more accessible visual field test, overcoming challenges in current kinetic perimetry practices.

Development of a PPG-based hardware and software system deployable on elbow and thumb for real-time estimation of pulse transit time.

Blood pressure (BP) is a vital parameter used by clinicians to diagnose issues in the human cardiovascular system. Cuff-based BP devices are currently the standard method for on-the-spot and ambulatory BP measurements. However, cuff-based devices are not comfortable and are not suitable for long-term BP monitoring. Many studies have reported a significant correlation between pulse transit time (PTT) with blood pressure. However, this relation is impacted by many internal and external factors which might lower the accuracy of the PTT method. In this paper, we present a novel hardware system consisting of two custom photoplethysmography (PPG) sensors designed particularly for the estimation of PTT. In addition, a software interface and algorithms have been implemented to perform a real-time assessment of the PTT and other features of interest from signals gathered between the brachial artery and the thumb. A preclinical study has been conducted to validate the system. Five healthy volunteer subjects were tested and the results were then compared with those gathered using a reference device. The analysis reports a mean difference among subjects equal to -3.75±7.28 ms. Moreover, the standard deviation values obtained for each individual showed comparable results with the reference device, proving to be a valuable tool to investigate the factors impacting the BP-PTT relationship.Clinical Relevance- The proposed system proved to be a feasible solution to detect blood volume changes providing good quality signals to be used in the study of BP-PTT relationship.

Moving perfusion culture and live-cell imaging from lab to disc: proof of concept toxicity assay with AI-based image analysis.

In vitro, cell-based assays are essential in diagnostics and drug development. There are ongoing efforts to establish new technologies that enable real-time detection of cell-drug interaction during culture under flow conditions. Our compact (10 × 10 × 8.5 cm) cell culture and microscope on disc (CMoD) platform aims to decrease the application barriers of existing lab-on-a-chip (LoC) approaches. For the first time in a centrifugal device, (i) cells were cultured for up to six days while a spindle motor facilitated culture medium perfusion, and (ii) an onboard microscope enabled live bright-field imaging of cells while the data wirelessly transmitted to a computer. The quantification of cells from the acquired images was done using artificial intelligence (AI) software. After optimization, the obtained cell viability data from the AI-based image analysis proved to correlate well with data collected from commonly used image analysis software. The CMoD was also suitable for conducting a proof-of-concept toxicity assay with HeLa cells under continuous flow. The half-maximal inhibitory time (IT50) for various concentrations of doxorubicin (DOX) in the case of HeLa cells in flow, was shown to be lower than the IT50 obtained from a static cytotoxicity assay, indicating a faster onset of cell death in flow. The CMoD proved to be easy to handle, enabled cell culture and monitoring without assistance, and is a promising tool for examining the dynamic processes of cells in real-time assays.