Many pitfalls in diagnosis of acute intermittent porphyria: a case report

Indika, Neluwa-Liyanage Ruwan; Kesavan, TM; Dilanthi, Hewa Warawitage; Jayasena, K.; Chandrasiri, Nambage Dona Priyani Dhammika; Jayasinghe, I. N.; Piumika, U. M. T.; Vidanapathirana, Dinesha Maduri; Gunarathne, K. D. A. V.; Dissanayake, Manel; Jasinge, Eresha; Arachchi, Wasantha Kodikara; Doheny, Dana; Desnick, Robert J.

doi:10.1186/s13104-018-3615-z

Cited by 14 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the predicted diseases of the system (A-NDCG), the excluded diseases for AIP (ex: appendicitis, lead poisoning) were listed at the top of the list. [Tsai et al, 2017], [Indika et al, 2018] In this case, the predicted diseases of the system provided useful information for the DDx process by physicians.…”

Section: Acute Intermittent Porphyriamentioning

confidence: 96%

Design, Implementation, and Evaluation of the Computer-aided Clinical Decision Support System based on Learning-to-Rank: Collaboration between physicians and machine learning in the differential diagnosis process

Miyachi¹,

Ishii²,

Torigoe³

2022

Preprint

View full text Add to dashboard Cite

OBJECTIVES We are developing the Clinical Decision Support System (CDSS) based on Learning-to-Rank (LTR). The main objectives are 1) Supporting differential diagnoses by internists and general practitioners and 2) Preventing diagnostic errors by physicians. The main features are that "A physician inputs a patient's symptoms, findings, and test results to the system, and the system outputs a ranking list of possible diseases." METHOD The software libraries for machine learning and artificial intelligence are TensorFlow and TensorFlow Ranking. The prediction algorithm is LTR with a listwise approach. The ranking metric is NDCG. The loss functions are Approximate NDCG (A-NDCG) and Gumbel Approximate NDCG (G-A-NDCG). We evaluated Machine Learning (ML) performance and Differential Diagnosis (DDx) performance with actual cases. RESULTS ML performance of our system was much higher than that of the conventional system. ML performance using G-A-NDCG was slightly higher than that of A-NDCG. DDx performance of our system was much higher than that of the conventional system. We have shown that CDSS prevents physicians' diagnostic errors due to confirmation bias. CONCLUSIONS We have demonstrated that the CDSS is useful for supporting differential diagnoses and preventing diagnostic errors. We believe that DDx by physicians and LTR have a high affinity. We found that Information Retrieval (IR) and Clinical Decision Support System (CDSS) have much in common (target data, LTR, etc.). We believe that CDSS has the potential to support 1) recall of rare diseases, 2) differential diagnoses for difficult-to-diagnose diseases, and 3) prevention of diagnostic errors. We also believe that our system has the potential for evolution to an Explainable Clinical Decision Support System (X-CDSS).

show abstract

Section: Acute Intermittent Porphyriamentioning

confidence: 96%

Design, Implementation, and Evaluation of the Computer-aided Clinical Decision Support System based on Learning-to-Rank: Collaboration between physicians and machine learning in the differential diagnosis process

Miyachi¹,

Ishii²,

Torigoe³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the predicted diseases of the system (A-NDCG), the excluded diseases for AIP (ex: lead poisoning) were listed at the top of the list. [24], [25] In this case, the predicted diseases of the system provided useful information for the DDx process by physicians.…”

Section: Disease With Characteristic Symptomsmentioning

confidence: 96%

Design, Implementation, and Evaluation of the Computer-aided Clinical Decision Support System based on Learning-to-Rank: Collaboration between physicians and machine learning in the differential diagnosis process

Miyachi¹,

Ishii²,

Torigoe

2022

Preprint

View full text Add to dashboard Cite

Background We are researching, developing, and publishing the Clinical Decision Support System based on Learning-to-Rank. The main objectives are 1) Supporting differential diagnoses by internists and general practitioners and 2) Preventing diagnostic errors by physicians. The main features are that "A physician inputs a patient's symptoms, findings, and test results to the system, and the system outputs a ranking list of possible diseases." Method The software libraries for machine learning and artificial intelligence are TensorFlow and TensorFlow Ranking. The prediction algorithm is Learning-to-Rank., with a listwise approach. The ranking metric is Normalized Discounted Cumulative Gain (NDCG). The loss functions are Approximate NDCG (A-NDCG) and Gumbel Approximate NDCG (G-A-NDCG). We evaluated the machine learning performance on k-fold cross-validation. We evaluated the differential diagnosis performance with actual cases. Results The machine learning performance of our system was much higher than that of the conventional system. The machine learning performance using G-A-NDCG was slightly higher than that of A-NDCG. The differential diagnosis performance of our system was much higher than that of the conventional system. We have shown that the Clinical Decision Support System prevents physicians' diagnostic errors due to confirmation bias. Conclusions We have demonstrated that the Clinical Decision Support System is useful for supporting differential diagnoses and preventing diagnostic errors. We believe that Differential diagnosis by physicians and Learning-to-Rank by machine has a high affinity. We found that Information Retrieval and Clinical Decision Support Systems have much in common (Target data, Learning-to-Rank, etc.). We believe that Clinical Decision Support Systems have the potential to support 1) recall of rare diseases, 2) differential diagnoses for difficult-to-diagnose diseases, and 3) prevention of diagnostic errors. We also believe that our system has the potential to evolve into an Explainable Clinical Decision Support System.

show abstract

“…Patients may undergo multiple abdominal surgeries; a case series reported an average diagnostic delay of 10 years. 7,9 The diagnosis of acute porphyria requires detection of increased urine porphobilinogen. 5 Initial urine screening for urine porphyrins may be completed more quickly than definitive quantification, although, in the presence of typical symptoms and absence of secondary causes, screening may be sufficient to initiate treatment.…”

Section: Diagnosismentioning

confidence: 99%