Materiały źródłowe

• #1 Prediction models in first episode psychosis: a systematic review and critical appraisal

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7612705/

  People presenting with first episode psychosis (FEP) have heterogenous outcomes. More than 40% fail to achieve symptomatic remission. Accurate prediction of individual outcome in FEP could facilitate early intervention to change the clinical trajectory and improve prognosis. […] We aim to systematically review evidence for prediction models developed for predicting poor outcome in FEP. […] Thirteen studies reporting 31 prediction models across a range of clinical outcomes met criteria for inclusion. […] Methodological limitations identified included a lack of appropriate validation, small sample sizes, poor handling of missing data and inadequate reporting of calibration and discrimination measures. […] Future prediction studies in psychosis should prioritise methodological rigour and external validation in larger samples. The potential for prediction modelling in FEP is yet to be realised.

• #2 Prediction models in first-episode psychosis: systematic review and critical appraisal | The British Journal of Psychiatry | Cambridge Core

  https://www.cambridge.org/core/journals/the-british-journal-of-psychiatry/article/prediction-models-in-firstepisode-psychosis-systematic-review-and-critical-appraisal/597A326F6B5258801F61CA211322F96F

  People presenting with first-episode psychosis (FEP) have heterogenous outcomes. More than 40% fail to achieve symptomatic remission. Accurate prediction of individual outcome in FEP could facilitate early intervention to change the clinical trajectory and improve prognosis. […] We aim to systematically review evidence for prediction models developed for predicting poor outcome in FEP. […] Thirteen studies reporting 31 prediction models across a range of clinical outcomes met criteria for inclusion. […] Methodological limitations identified included a lack of appropriate validation, small sample sizes, poor handling of missing data and inadequate reporting of calibration and discrimination measures. […] Future prediction studies in psychosis should prioritise methodological rigour and external validation in larger samples. The potential for prediction modelling in FEP is yet to be realised.

• #3 Psychosis Prognosis Predictor: A Continuous and Uncertainty-Aware Prediction of Treatment Outcome in First-Episode Psychosis | medRxiv

  https://www.medrxiv.org/content/10.1101/2023.07.05.23292252v1.full-text

  Importance Presently, clinicians face challenges in accurately predicting the prognosis of patients with psychosis. […] Objective We propose and evaluate a multi-task recurrent neural network architecture specifically designed to overcome these challenges, enabling trustworthy prediction of psychosis prognosis. […] Conclusions and Relevance Our approach involved constructing prediction models utilizing a flexible neural network architecture tailored to clinical scenarios derived from a time series dataset. […] In conclusion, we developed and tested a psychosis prognosis prediction model that has properties that are required for use in clinical practice.

• #4 Predicting one-year outcome in first episode psychosis using machine learning | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0212846

  Early illness course correlates with long-term outcome in psychosis. Accurate prediction could allow more focused intervention. Earlier intervention corresponds to significantly better symptomatic and functional outcomes. […] Our study objective is to use routinely collected baseline demographic and clinical characteristics to predict employment, education or training (EET) status, and symptom remission in patients with first episode psychosis (FEP) at one-year. […] Using advanced statistical machine learning techniques, we provide the first externally validated evidence, in a temporally and geographically independent cohort, for the ability to predict one-year EET status and symptom remission in individual FEP patients. […] We believe our study to be the first externally validated evidence, in a temporally and geographically independent cohort, for predictive modelling in FEP at an individual patient level. This builds on existing studies of group-level differences and the elegant work of Koutsouleris et al, which outlined the first internally validated evidence of the ability to predict functional outcome in individual patients with FEP.

• #5 Predicting treatment resistance from first-episode psychosis using routinely collected clinical information

  https://www.repository.cam.ac.uk/items/be3d3b16-b65a-4c57-8c12-59735d9aca9a

  Around a quarter of people who experience a first episode of psychosis (FEP) will develop treatment-resistant schizophrenia (TRS), but there are currently no established clinically useful methods to predict this from baseline. […] The use of routinely collected clinical information including blood-based biomarkers taken at FEP onset can help to predict the individual risk of clozapine use, and should be considered equally alongside other potentially useful information such as symptom scores in large-scale efforts to predict psychiatric outcomes.

• #6 Is It Ethical to Use Prognostic Estimates from Machine Learning to Treat Psychosis? | Journal of Ethics | American Medical Association

  https://journalofethics.ama-assn.org/article/it-ethical-use-prognostic-estimates-machine-learning-treat-psychosis/2018-09

  Machine learning is a method for predicting clinically relevant variables, such as opportunities for early intervention, potential treatment response, prognosis, and health outcomes. […] A major challenge with these patients is that clinicians are unable to predict an individual patients clinical outcomes: some return to baseline, others experience only mild symptoms, while others deteriorate and might even become severely disabled. […] The model yields a prognostic estimate. Using the patients baseline information such as sex, occupational status, and history of major depressive episodes, the model predicts whether the patient will have a good or a poor outcome 1 year later. […] A good outcome defined as a GAF score of greater than or equal to 65 typically indicates that a patient is able to function with minimal impairments.

• #7 Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach | Schizophrenia

  https://www.nature.com/articles/s41537-021-00162-3

  Schizophrenia and related disorders have heterogeneous outcomes. Individualized prediction of long-term outcomes may be helpful in improving treatment decisions. Utilizing extensive baseline data of 523 patients with a psychotic disorder and variable illness duration, we predicted symptomatic and global outcomes at 3-year and 6-year follow-ups. Aiming for a robust and interpretable prediction model, we employed a linear support vector machine and recursive feature elimination within a nested cross-validation design to obtain a lean set of predictors. Generalization to out-of-study samples was estimated using leave-one-site-out cross-validation. Prediction accuracies were above chance and ranged from 62.2% to 64.7% (symptomatic outcome), and 63.5-67.6% (global outcome). These robust, albeit modestly accurate, long-term prognostic predictions based on lean predictor sets indicate the potential of machine learning models complementing clinical judgment and decision-making. Future model development may benefit from studies scoping patients and clinicians’ needs in prognostication.

• #8 Psychosis Prognosis Predictor: A continuous and uncertainty-aware prediction of treatment outcome in first-episode psychosis – PubMed

  https://pubmed.ncbi.nlm.nih.gov/39293941/

  Machine learning models have shown promising potential in individual-level outcome prediction for patients with psychosis, but also have several limitations. […] We predicted antipsychotic treatment outcomes in 446 first-episode psychosis patients in the OPTiMiSE study, for six different clinical scenarios. […] We provided evidence showcasing the significance of leveraging time series data for achieving more accurate treatment outcome prediction in the field of psychiatry. […] One crucial aspect we incorporated was the consideration of uncertainty in individual predictions, which enhances the reliability of decision-making based on the model’s output.

• #9 Prediction models in first-episode psychosis: systematic review and critical appraisal | The British Journal of Psychiatry | Cambridge Core

  https://www.cambridge.org/core/journals/the-british-journal-of-psychiatry/article/prediction-models-in-firstepisode-psychosis-systematic-review-and-critical-appraisal/597A326F6B5258801F61CA211322F96F

  Our systematic review identified 13 studies reporting 31 prognostic prediction models for the prediction of a wide range of clinical outcomes. […] There were several methodological limitations identified, including a lack of appropriate validation, issues with handling missing data and a lack of reporting of calibration and discrimination measures. […] Altogether, just two studies (15%) had an overall low risk of bias according to PROBAST, reflecting these methodological limitations. Neither study considered real-world implementation. […] Our goal in psychiatry should be to develop an innovative approach to care by using prediction models. Application of these approaches into clinical practice would enable rapid and targeted intervention, thereby limiting treatment-associated risks and reducing patient suffering.

• #10 Prediction models in first episode psychosis: a systematic review and critical appraisal

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7612705/

  Our systematic review identified 13 studies reporting 31 prognostic prediction models for the prediction of a wide range of clinical outcomes. The majority of models were developed via logistic regression. There were several methodological limitations identified including a lack of appropriate validation, issues with handling missing data and a lack of reporting of calibration and discrimination measures. […] We identified two studies with models at low risk of bias as assessed with PROBAST, both of which externally validated their models.

• #11 Predicting one-year outcome in first episode psychosis using machine learning | PLOS One

  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0212846

  Our results demonstrate the ability to predict both symptom remission and more importantly, functioning (in employment, education or training). The performance of our EET model was particularly robust, with an ability to accurately predict the one-year EET outcome in more than 85% of patients. […] We have demonstrated that it is possible to accurately predict one-year symptomatic and functional employment education or training status in first episode psychosis. This has not been reported previously in an externally validated cohort.

• #12 Clinical prediction model for transition to psychosis in individuals meeting At Risk Mental State criteria | Schizophrenia

  https://www.nature.com/articles/s41537-025-00582-5

  The At Risk Mental State (ARMS) (also known as the Ultra or Clinical High Risk) criteria identify individuals at high risk for psychotic disorder. However, there is a need to improve prediction as only about 18% of individuals meeting these criteria develop a psychosis with 12-months. […] The final prediction model included disorders of thought content, disorganised speech and functioning. Discrimination of 0.68 (0.5-1 scale; 1=perfect discrimination) and calibration of 0.91 (0-1 scale; 1=perfect calibration) showed the model had fairly good predictive ability. […] The statistically robust prediction model, built using the largest dataset in the field to date, could be used to guide frequency of monitoring and enable rational use of health resources following assessment of external validity and clinical utility.

• #13 Clinical prediction model for transition to psychosis in individuals meeting At Risk Mental State criteria | Schizophrenia

  https://www.nature.com/articles/s41537-025-00582-5

  The UHR criteria are associated with risk of developing a psychotic disorder. However, there is a need to identify which UHR individuals are at higher risk of transition and which are at lower risk. […] The final model included thought content disorders, disorganised speech, global functioning score, and treatment (forced into the model). It demonstrated fairly good predictive performance, with an optimism-adjusted c-statistic of 0.68 and a calibration slope of 0.91. […] All of the above variables that were significantly associated with risk of developing a psychotic disorder were considered suitable for use in routine clinical practice by consumers and staff members. […] Use of a clinical prediction model for risk of transition to psychosis in people meeting UHR criteria has the potential to improve treatment decisions, reduce unnecessary interventions, and maximise the use of resources.

• #14 Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach | Schizophrenia

  https://www.nature.com/articles/s41537-021-00162-3

  Our results indicate that while state-of-the-art methods may result in robust (generalizable) performance estimates, predictions are modestly accurate, similar to recent experimental prognostic models for depression based on machine learning predicting long-term clinical outcomes based on patient reportable data. The models did not reach the LOSO cross-validated accuracy of 71% in the study on the one-year outcome of first-episode psychosis, presumably due to the uncertainty introduced by time, care-as-usual setting, and the heterogeneity of baseline clinical status and illness duration within our target population. […] We demonstrate the feasibility of a machine-learning approach to long-term outcome prediction in a heterogeneous target population of schizophrenia-spectrum patients, based on a lean set of patient reportable features, overlapping with those predictive of short-term outcome of first-episode psychosis. Future models may benefit from considering patients and clinicians needs, the appropriate nature of the training sample (i.e. sample similarity to the population of interest as well as richness on (contextual) features), and implementation of advancements in machine learning methodology. Individual outcome prediction based on machine learning may inform the treatment stratification needed both from a patient and a public health perspective.

• #15 Is It Ethical to Use Prognostic Estimates from Machine Learning to Treat Psychosis? | Journal of Ethics | American Medical Association

  https://journalofethics.ama-assn.org/article/it-ethical-use-prognostic-estimates-machine-learning-treat-psychosis/2018-09

  A poor outcome a GAF score of less than 65 can indicate a broad range of impairment severity. […] The model predicts a good or poor outcome with approximately 75% accuracy. […] Dr K and colleagues think this model can enhance their treatment of psychotic patients and would like to incorporate it into their practice. […] In order to implement the predictive tool in an ethical manner, Dr K will need to carefully consider how to give appropriate information in an understandable manner to patients and families regarding use of the predictive model. […] In order to maximize benefits from the predictive model and minimize risks, Dr K and the institution as a whole will need to formulate ethically appropriate procedures and protocols surrounding the instrument.

Zobacz więcej