Background: Major depressive disorder (MDD) is a leading cause of disability worldwide. At present, however, there are no established biomarkers that have been validated for diagnosing and treating MDD. This study sought to assess the diagnostic and predictive potential of the differences in serum amino acid concentration levels between MDD patients and healthy controls (HCs), integrating them into interpretable machine learning models. Methods: In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. Serum amino acid profiling was conducted by means of chromatography-mass spectrometry. A total of 21 metabolites were analysed, with 17 from a preset amino acid panel and the remaining 4 from a preset kynurenine panel. Logistic regression was applied to differentiate MDD patients from HCs. Results: The best-performing model utilised both feature selection and hyperparameter optimisation and yielded a moderate area under the receiver operating curve (AUC) classification value of 0.76 on the testing data. The top five metabolites identified as potential biomarkers for MDD were 3-hydroxy-kynurenine, valine, kynurenine, glutamic acid, and xanthurenic acid. Conclusions: Our study highlights the potential of using an interpretable machine learning analysis model based on amino acids to aid and increase the diagnostic accuracy of MDD in clinical practice.

This case report demonstrates an atypical presentation of panic disorder which masqueraded as episodes of possession trance. Patient X is a 62-year-old Chinese female who presented with recurrent episodes of uncontrollable screaming and shaking of all four limbs. During these episodes, she reported auditory hallucinations (Buddhist chanting) and visual hallucinations (a rotting corpse) which she attributed to the influence of “evil spirits.” She was diagnosed with panic disorder with culture-specific symptoms on a background of major depressive disorder. With an understanding of the patient's belief system and an empathetic approach during psychoeducation, she eventually accepted the use of pharmacotherapy. She was prescribed escitalopram (started at 2.5 mg OM) and clobazam (10 mg ON) with good clinical effect and cessation of episodes afterward.

This report documents a rare case of delayed-onset multiple acute dystonias after treatment with low dose intramuscular (IM) haloperidol lactate injection in a setting of non-neuroleptic drug overdose. The drug–drug interactions between haloperidol and high levels of paracetamol and naproxen are deliberated upon. A 25-year-old Asian female was admitted after an intentional overdose of medications (paracetamol, naproxen and pregabalin). She received 5 mg of IM haloperidol injection for agitation. 21 hours later she experienced mild intermittent ocular deviation in an upward and outward direction and generalised stiffness, which were self-resolving. An hour later, she required another 2.5 mg of IM haloperidol injection for further agitation. In the 35 hours following her first IM haloperidol (13 hours after the second IM haloperidol), she developed a total of three episodes of oculogyric crisis (OGC) with torticollis. Each episode was treated promptly with IM diphenhydramine 25 mg, and there was remission of symptoms within 15 minutes of treatment. An objective causality assessment revealed a definite relationship between the episodes of acute dystonia with IM haloperidol therapy. Where oral alternatives and IM atypical antipsychotics/benzodiazepines are unavailable, rapid tranquillisation with a high-potency typical antipsychotic is a possibility. However, consideration should be made to combine haloperidol with an anticholinergic agent as prophylaxis against acute dystonia, especially in the setting of drug overdose, even if it is that of a non-neuroleptic drug (in this case, paracetamol and naproxen).