Optimizing Treatment Strategies in the Bipolar Disorder Spectrum With Classical AI Approaches: Systematic Review of Performance, Bias, and Clinical Applicability
Background: Bipolar disorder (BD) is a complex and heterogeneous psychiatric condition, characterized by fluctuating clinical courses that affect approximately 1%‐2% of the global population in their lifetime. Despite pharmacological advances, treatment response varies significantly among patients, making the identification of individualized treatment strategies a major challenge. Artificial Intelligence (AI), through its classical approaches, has emerged as a powerful tool in precision psychiatry to identify subtle patterns in complex data and inform personalized clinical decisions. Objective: The present systematic review aimed to examine the current evidence on classical AI-supported treatment optimization in the BD spectrum. Methods: The review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines. Four databases (PubMed, Web of Science, Scopus, and Embase) were searched for original studies published after 2015 on the application of classical AI in the treatment of BD in adult patients. Publication bias was evaluated by visual inspection of a funnel plot. The methodological quality, risk of bias, and clinical applicability of the predictive models were assessed using the Prediction Model Risk Of Bias Assessment Tool for prediction models using regression or AI methods (PROBAST+AI; PROBAST+AI Working Group) tool. Results: A total of 35 studies were included and classified into 5 outcome-based categories, including acute symptomatic response, long-term maintenance response, relapse and readmission risk, safety and dose optimization, and brain aging and phenotyping. Acute symptomatic response models performed modestly (pooled area under the curve [AUC] 0.68), while imaging improved accuracy (74%‐77%). Long-term maintenance response models showed moderate-to-high performance (pooled AUC 0.80), with biomarker- and cellular-based models reaching 96%‐99% accuracy. Relapse and readmission prediction achieved a pooled AUC of 0.71, with digital phenotyping and rule-based methods performing best (AUC 0.85‐0.88). Safety and dose optimization models achieved 85%‐97% accuracy. Brain aging and phenotyping studies highlighted accelerated brain aging in BD, partially mitigated by lithium, and revealed novel data-driven subgroups. However, 3 studies were considered at high risk of bias due to small sample sizes associated with disproportionately high-performance estimates. An additional study was identified as potentially biased because it lay markedly distant from the funnel plot’s confidence line. Finally, the PROBAST+AI assessment revealed a high risk of bias in most studies, primarily due to data analysis limitations, small sample sizes, and lack of external validation. Conclusions: The adoption of classical AI tools in BD serves as a driver for therapeutic optimization, although current AI tools in BD should still be considered exploratory rather than ready for clinical use. Effective implementation in real-world clinical scenarios requires more robust, transparent, and externally validated models to ensure reliability and generalizability.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/df358c951a2c44fbd20077fdda306baf" />
Transition Care for FEP
Interventions: Behavioral: Transition Care Team
Sponsors: University of Chicago; Sidney R. Baer, Jr. Foundation
Recruiting
See, Blind Mice: Consortium’s Drugs Restore Sight
A consortium led by scientists at the Institute for Bioengineering of Catalonia (IBEC) has developed a series of light-activated small molecule drugs that in preclinicial tests restored sight in blind mice. The team’s approach is based on photopharmacology, a technique for reversibly control drug activity using light.
The newly developed compounds, called prosthe6, mimic the function of light sensing photoreceptor cells, which degenerate in blinding diseases such as age-related macular degeneration (AMD) and retinitis pigmentosa (RP).
The prosthe6 compounds target ON-bipolar neurons and in tests were found to successfully restore saccadic eye movements (optokinetic reflex) in blinded zebrafish larvae, a widely used model for studying visual acuity. Even more strikingly, the researchers demonstrated recovery of innate light-avoidance behavior in mouse models of age-related macular degeneration and retinitis pigmentosa.
Test results suggest that the prosthe6 compounds may be administered by injecting them in the eye, or administered as eye drops. In animal studies the photoswitchable molecules also showed promising preliminary safety profiles, pointing to the development of potential drug candidates for restoring vision in patients with degenerative retinal diseases, without the need for genetic manipulation or implanted devices. Importantly, these compounds are designed to work under normal lighting conditions and do not require light-enhancing devices as optogenetics. They are small, water-soluble molecules that respond to ordinary visible or white light, such as indoor lighting or daylight, without requiring intense or specialized light sources.
“These molecules do not cure blindness, because they do not address the cause of photoreceptor degeneration,” said study co-lead Pau Gorostiza, PhD, ICREA Research Professor at IBEC, leader of the Nanoprobes and Nanoswitches group, member of CIBER-BBN. “But they are remarkably effective at restoring sight, and they do so using a very simple and potentially patient-friendly approach.”
Rosalba Sortino, former PhD student at the University de Barcelona, and currently post-doctoral researcher at Gorostiza’s group at IBEC, added, “Our goal was to restore vision using a molecular mechanism that is as close as possible to how the healthy retina works … Instead of bypassing retinal processing, we aimed to reactivate it right at the same level of the retinal circuit than the lost photoreceptor cells.”
Sortino is co-first author of the team’s published paper in Journal of the American Chemical Society, titled “Restoration of saccadic eye movements and visually guided behavior in ambient white light with photoswitchable small molecules.”
Diseases such as age-related macular degeneration and retinitis pigmentosa affect 200 million people worldwide and are the leading causes of visual impairment and blindness. Beyond the personal impact on quality of life and independence, vision loss places a global economic burden estimated at over US$400 billion per year in healthcare costs and lost productivity.
![Researchers Rosalba Sortino (left) and Joaquin Martinez Tambella (right) working in the laboratories of the Institute for Bioengineering of Catalonia (IBEC). Sortino is a post-doctoral researcher at the Nanoprobes and Nanoswitches group at IBEC and co-first author of the study. Martinez is a PhD student at the Nanoprobes and Nanoswitches group at IBEC and co-first author of the study. [Institute for Bioengineering of Catalonia (IBEC).]](https://www.genengnews.com/wp-content/uploads/2026/07/RSortino-JMartinez-300x223.jpeg)
In many of these conditions, photoreceptor (PhR) cells—the retina’s light detectors—progressively degenerate and die. Although the downstream retinal neuronal circuitry remains largely intact and functionally viable, it no longer receives the light signals needed to drive visual processing towards the brain. This opportunity has fueled intense research efforts to develop treatments capable of restoring light sensitivity to the eye. Current strategies include gene therapy—effective only for a very small subset of patients with specific mutations—and electronic retinal prostheses, which are invasive, expensive, and require extensive training for effective use.
More recently, optogenetics and light-responsive drugs have entered clinical testing, the latter with encouraging safety results. “Photopharmacology can develop photoswitchable small molecules to restore vision impairment by conferring light sensitivity to ion channels that are widely expressed in the remaining inner retinal neurons, and a first-in-human clinical trial is ongoing,” the team noted. However, achieving high-quality vision at ambient illumination levels remains a major challenge.
The (IBEC)-led consortium has now developed a new class of photoswitchable small-molecule drugs that are capable of restoring key visual functions in animal models of blindness. The team’s photopharmacology-based technique involves modifying a drug’s chemical structure by adding a light-activated molecular switch, enabling control of the pharmacological action using light. “Unlike (opto)genetic manipulation and surgically implanted retinal electronic prostheses, pharmacotherapy is noninvasive, readily reversible, and can be upgraded when new drugs are approved,” the authors noted. “Medicines are preferred by patients, clinicians, and public healthcare systems, they can be developed and manufactured at lower costs than other approaches and assessed by conventional regulatory procedures and clinical assays.”
The reported work builds on more than a decade of research and was carried out in collaboration with the team co-led by Pedro de la Villa at the University of Alcalá (UAH), as well as researchers from the Institut de Química Avançada de Catalunya (IQAC-CSIC), the University of Barcelona (UB), the Institute Ramón y Cajal of Health Research (IRYCIS), the Autonomous University of Barcelona (UAB), and the Fundació Eduard Soler.
![Researcher Joaquin Martinez Tambella working in the laboratories of the Institute for Bioengineering of Catalonia (IBEC). Martinez is a PhD student at the Nanoprobes and Nanoswitches group at IBEC and co-first author of the study. [Institute for Bioengineering of Catalonia (IBEC).]](https://www.genengnews.com/wp-content/uploads/2026/07/JMartinez-300x225.jpeg)
The prosthe6 compounds work by acting on a specific type of retinal cells called ON bipolar cells, which normally receive signals from the photoreceptors. “In healthy vision, ON bipolar cells play a key role in passing on information about the presence of light to the rest of the visual circuit,” explained study co-lead de la Villa. “In degenerative eye diseases, although the photoreceptors are lost, much of this underlying circuitry remains intact but inactive. This creates a major therapeutic opportunity.”
By targeting a protein (mGlu6) in this preserved part of the retina, prosthe6 compounds can take over the role of the missing photoreceptors. “… we have targeted metabotropic glutamate 6 (mGlu6) receptors, which are exclusively expressed in ON bipolar cells (OBCs) and localized postsynaptic to PhR cells, thereby leveraging a privileged position to drive physiological visual circuit,” the investigators explained. When light enters the eye, the molecules respond by changing their shape, triggering signals inside the retina in a way that closely resembles natural vision. In this way, the drugs effectively act as “molecular prostheses,” helping the eye process light again without the need for implants or genetic modifications.
Healthy mice naturally prefer to remain in dark environments and instinctively avoid brightly lit areas, a behavior that relies entirely on a functional visual system. Blind mice, by contrast, lose this preference and move indistinctly between light and dark spaces, as they are unable to perceive light. The team showed that after treatment with prosthe6, blind mice once again showed a clear and spontaneous preference for dark areas, indicating that they could perceive light and use this information to guide their behavior.
This recovery occurred without any training and under light levels comparable to those found indoors or on an overcast day, demonstrating that the treatment restores functional light perception capable of driving natural, visually guided behavior.
Two lead compounds, prosthe6-12 and prosthe6-15, showed particularly promising results. The restored behaviors were observed not only after intraocular injection, but also after topical administration as eye drops. “… at least two compounds (prosthe6-12 and -15) appear to be devoid of adverse effects and restore sight by topical administration, which is linked to higher overall clinical success rate than systemic routes for neurological drugs, and to stronger patient adherence,” the investigators pointed out.
The prosthe6 technology is protected by patent and the researchers are now evaluating its safety and formulation to extend the duration of visual rehabilitation. The team is working with Eyelumina, a spin-off company in formation to secure investments that support translational development and future clinical trials.
“Turning this into a therapy is a long and laborious process,” says Gorostiza. “But the results show that there is a realistic possibility of restoring high-quality vision with drugs, non-invasively, reversibly and with a mechanism that is independent of the specific retinal disorder or genetic mutation to reach a majority of patients.”
If successful in humans, the drug-based approach would offer a widely accessible and affordable alternative to existing vision restoration technologies, especially relevant for patients with advanced retinal degeneration for whom no effective treatments currently exist.
In their paper the team further stated, “From a fundamental perspective, prosthe6 constitute new tools for ophthalmology to study the physiopathology of mGlu6 receptors and retinal circuits in vitro and in vivo and contribute to the medicinal chemistry of allosteric modulators. They also achieve the prediction that upstream targeted photopharmacology can deliver nearly native output signals, taking full advantage of the retinal circuit for high-quality vision restoration.”
The post See, Blind Mice: Consortium’s Drugs Restore Sight appeared first on GEN – Genetic Engineering and Biotechnology News.
Fragile self, mechanical world: mechanistic delusions and ego fragility in schizotypal–affective spectrum disorder—a CARE case report
Local field potentials for target localization in centromedian deep brain stimulation for epilepsy
Smoking as a correlate of suicidal behavior and self-harm in adolescents with depressive disorders
Recommendations for Research and Clinical Implementation of Ambulatory Assessment, Mood Monitoring, Digital Phenotyping, and Remote Measurement Technology in Mood Disorders: Synthesis of Systematic Review Findings
Background: Ambulatory assessment and active and passive monitoring all offer a real-time, flexible approach to assessing mood and behavior in mood disorders. Despite their potential, concerns remain regarding the performance, usability, adherence, and potential safety of these tools. Objective: This study synthesizes the findings from 7 systematic reviews, integrating quantitative and qualitative data from randomized trials, observational studies, and user experience research to evaluate the performance, feasibility, acceptability, and clinical impact of ambulatory assessment and mood monitoring in people with depression and bipolar disorder. We assessed studies over the medium or long term (3 months or more). Methods: A summary of a series of systematic reviews was carried out by the authors—including meta-analyses (for quantitative data) and meta-syntheses (for qualitative data). Eight electronic databases were searched, and mixed methods studies were included. Studies were assessed for risk of bias. The results were checked for coherence, and recommendations were made by individuals with lived experience, methodologists, and psychiatrists. GRADE (Grading of Recommendations Assessment, Development, and Evaluation) was used to assess the quality and strength of the evidence. Results: The 111 included studies included 19,945 participants and used 69 different ambulatory assessment protocols or mood-monitoring interventions. Key barriers to implementation were identified, including performance inconsistency, adverse effects, and user disengagement. Evidence-based recommendations are provided to guide future clinical and research applications. Conclusions: Ambulatory assessment and mood monitoring hold promise in research and clinical practice, yet their implementation requires more rigorous evaluation, greater personalization, and responsible, user-centered design. Crucially, these measures can add granularity and confirmation, but additional context is often required, and none of these measures are robust enough yet to replace current outcomes.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/a83582c454b5b6028210d2cb063318df" />
Personalized Pharmaco-Lifestyle Interventions for Severe Mental Illnesses (LIFETRAIN)
Interventions: Drug: Semaglutide (SEMA); Behavioral: Exercise module; Behavioral: Anti-inflammatory diet module; Behavioral: Sleep intervention module; Behavioral: Social prescribing module; Device: Closed-loop transcranial alternating current stimulation (CL-tACS); Behavioral: Structured lifestyle psychoeducation; Device: Sham CL-tACS
Sponsors: Ludwig-Maximilians – University of Munich
Not yet recruiting
Structural Brain Network Alterations in Relation to Treatment and Illness Severity in Bipolar Disorder
Large-scale T1-weighted MRI studies have established grey-matter abnormalities in bipolar disorder (BD), with our group contributing to consensus findings. However, structural connectivity, particularly within emotion- and reward-related circuits, remains poorly understood. Diffusion-weighted MRI (dMRI) enables investigation of white-matter pathways, yet prior work is constrained by small samples, methodological heterogeneity, and unclear medication effects. We conducted the largest dMRI network analysis in BD, relating symptom burden and polypharmacy to tractography-derived connectivity and graph-theoretic metrics.

